01-ai
Models by this creator
⚙️
Yi-34B
1.3K
specify theme context for images Building the Next Generation of Open-Source and Bilingual LLMs Hugging Face ModelScope WiseModel Ask questions or discuss ideas on GitHub Join us on Discord or WeChat Check out Yi Tech Report Grow at Yi Learning Hub Table of Contents What is Yi? Introduction Models Chat models Base models Model info News How to use Yi? Quick start Choose your path pip docker llama.cpp conda-lock Web demo Fine-tuning Quantization Deployment FAQ Learning hub Why Yi? Ecosystem Upstream Downstream Serving Quantization Fine-tuning API Benchmarks Base model performance Chat model performance Tech report Citation Who can use Yi? Misc. Acknowledgements Disclaimer License What is Yi? Introduction The Yi series models are the next generation of open-source large language models trained from scratch by 01.AI. Targeted as a bilingual language model and trained on 3T multilingual corpus, the Yi series models become one of the strongest LLM worldwide, showing promise in language understanding, commonsense reasoning, reading comprehension, and more. For example, Yi-34B-Chat model landed in second place (following GPT-4 Turbo), outperforming other LLMs (such as GPT-4, Mixtral, Claude) on the AlpacaEval Leaderboard (based on data available up to January 2024). Yi-34B model ranked first among all existing open-source models (such as Falcon-180B, Llama-70B, Claude) in both English and Chinese on various benchmarks, including Hugging Face Open LLM Leaderboard (pre-trained) and C-Eval (based on data available up to November 2023). (Credits to Llama) Thanks to the Transformer and Llama open-source communities, as they reduce the efforts required to build from scratch and enable the utilization of the same tools within the AI ecosystem. If you're interested in Yi's adoption of Llama architecture and license usage policy, see Yi's relation with Llama. > TL;DR > > The Yi series models adopt the same model architecture as Llama but are NOT derivatives of Llama. Both Yi and Llama are based on the Transformer structure, which has been the standard architecture for large language models since 2018. Grounded in the Transformer architecture, Llama has become a new cornerstone for the majority of state-of-the-art open-source models due to its excellent stability, reliable convergence, and robust compatibility. This positions Llama as the recognized foundational framework for models including Yi. Thanks to the Transformer and Llama architectures, other models can leverage their power, reducing the effort required to build from scratch and enabling the utilization of the same tools within their ecosystems. However, the Yi series models are NOT derivatives of Llama, as they do not use Llama's weights. As Llama's structure is employed by the majority of open-source models, the key factors of determining model performance are training datasets, training pipelines, and training infrastructure. Developing in a unique and proprietary way, Yi has independently created its own high-quality training datasets, efficient training pipelines, and robust training infrastructure entirely from the ground up. This effort has led to excellent performance with Yi series models ranking just behind GPT4 and surpassing Llama on the Alpaca Leaderboard in Dec 2023. \ [Back to top \] News 2024-03-16: The Yi-9B-200K is open-sourced and available to the public. 2024-03-08: Yi Tech Report is published! 2024-03-07: The long text capability of the Yi-34B-200K has been enhanced. In the "Needle-in-a-Haystack" test, the Yi-34B-200K's performance is improved by 10.5%, rising from 89.3% to an impressive 99.8%. We continue to pre-train the model on 5B tokens long-context data mixture and demonstrate a near-all-green performance. 2024-03-06: The Yi-9B is open-sourced and available to the public. Yi-9B stands out as the top performer among a range of similar-sized open-source models (including Mistral-7B, SOLAR-10.7B, Gemma-7B, DeepSeek-Coder-7B-Base-v1.5 and more), particularly excelling in code, math, common-sense reasoning, and reading comprehension. 2024-01-23: The Yi-VL models, Yi-VL-34B and Yi-VL-6B, are open-sourced and available to the public. Yi-VL-34B has ranked first among all existing open-source models in the latest benchmarks, including MMMU and CMMMU (based on data available up to January 2024). 2023-11-23: Chat models are open-sourced and available to the public. This release contains two chat models based on previously released base models, two 8-bit models quantized by GPTQ, and two 4-bit models quantized by AWQ. Yi-34B-Chat Yi-34B-Chat-4bits Yi-34B-Chat-8bits Yi-6B-Chat Yi-6B-Chat-4bits Yi-6B-Chat-8bits You can try some of them interactively at: Hugging Face Replicate 2023-11-23: The Yi Series Models Community License Agreement is updated to v2.1. 2023-11-08: Invited test of Yi-34B chat model. Application form: English Chinese 2023-11-05: The base models, Yi-6B-200K and Yi-34B-200K, are open-sourced and available to the public. This release contains two base models with the same parameter sizes as the previous release, except that the context window is extended to 200K. 2023-11-02: The base models, Yi-6B and Yi-34B, are open-sourced and available to the public. The first public release contains two bilingual (English/Chinese) base models with the parameter sizes of 6B and 34B. Both of them are trained with 4K sequence length and can be extended to 32K during inference time. \ [Back to top \] Models Yi models come in multiple sizes and cater to different use cases. You can also fine-tune Yi models to meet your specific requirements. If you want to deploy Yi models, make sure you meet the software and hardware requirements. Chat models Model Download Yi-34B-Chat Hugging Face ModelScope Yi-34B-Chat-4bits Hugging Face ModelScope Yi-34B-Chat-8bits Hugging Face ModelScope Yi-6B-Chat Hugging Face ModelScope Yi-6B-Chat-4bits Hugging Face ModelScope Yi-6B-Chat-8bits Hugging Face ModelScope \- 4-bit series models are quantized by AWQ. \- 8-bit series models are quantized by GPTQ \- All quantized models have a low barrier to use since they can be deployed on consumer-grade GPUs (e.g., 3090, 4090). Base models Model Download Yi-34B Hugging Face ModelScope Yi-34B-200K Hugging Face ModelScope Yi-9B Hugging Face ModelScope Yi-9B-200K Hugging Face ModelScope Yi-6B Hugging Face ModelScope Yi-6B-200K Hugging Face ModelScope \- 200k is roughly equivalent to 400,000 Chinese characters. \- If you want to use the previous version of the Yi-34B-200K (released on Nov 5, 2023), run git checkout 069cd341d60f4ce4b07ec394e82b79e94f656cf to download the weight. Model info For chat and base models Model Intro Default context window Pretrained tokens Training Data Date 6B series models They are suitable for personal and academic use. 4K 3T Up to June 2023 9B series models It is the best at coding and math in the Yi series models. Yi-9B is continuously trained based on Yi-6B, using 0.8T tokens. 34B series models They are suitable for personal, academic, and commercial (particularly for small and medium-sized enterprises) purposes. It's a cost-effective solution that's affordable and equipped with emergent ability. 3T For chat models For chat model limitations, see the explanations below. The released chat model has undergone exclusive training using Supervised Fine-Tuning (SFT). Compared to other standard chat models, our model produces more diverse responses, making it suitable for various downstream tasks, such as creative scenarios. Furthermore, this diversity is expected to enhance the likelihood of generating higher quality responses, which will be advantageous for subsequent Reinforcement Learning (RL) training. However, this higher diversity might amplify certain existing issues, including: Hallucination: This refers to the model generating factually incorrect or nonsensical information. With the model's responses being more varied, there's a higher chance of hallucination that are not based on accurate data or logical reasoning. Non-determinism in re-generation: When attempting to regenerate or sample responses, inconsistencies in the outcomes may occur. The increased diversity can lead to varying results even under similar input conditions. Cumulative Error: This occurs when errors in the model's responses compound over time. As the model generates more diverse responses, the likelihood of small inaccuracies building up into larger errors increases, especially in complex tasks like extended reasoning, mathematical problem-solving, etc. To achieve more coherent and consistent responses, it is advisable to adjust generation configuration parameters such as temperature, top\_p, or top\_k. These adjustments can help in the balance between creativity and coherence in the model's outputs. \ [Back to top \] How to use Yi? Quick start Choose your path pip docker conda-lock llama.cpp Web demo Fine-tuning Quantization Deployment FAQ Learning hub Quick start Getting up and running with Yi models is simple with multiple choices available. Choose your path Select one of the following paths to begin your journey with Yi! Quick start - Choose your path Deploy Yi locally If you prefer to deploy Yi models locally, and you have sufficient resources (for example, NVIDIA A800 80GB), you can choose one of the following methods: pip Docker conda-lock and you have limited resources (for example, a MacBook Pro), you can use llama.cpp. Not to deploy Yi locally If you prefer not to deploy Yi models locally, you can explore Yi's capabilities using any of the following options. Run Yi with APIs If you want to explore more features of Yi, you can adopt one of these methods: Yi APIs (Yi official) Early access has been granted to some applicants. Stay tuned for the next round of access! Yi APIs (Replicate) Run Yi in playground If you want to chat with Yi with more customizable options (e.g., system prompt, temperature, repetition penalty, etc.), you can try one of the following options: Yi-34B-Chat-Playground (Yi official) Access is available through a whitelist. Welcome to apply (fill out a form in English or Chinese). Yi-34B-Chat-Playground (Replicate) Chat with Yi If you want to chat with Yi, you can use one of these online services, which offer a similar user experience: Yi-34B-Chat (Yi official on Hugging Face) No registration is required. Yi-34B-Chat (Yi official beta) Access is available through a whitelist. Welcome to apply (fill out a form in English or Chinese). \ [Back to top \] Quick start - pip This tutorial guides you through every step of running Yi-34B-Chat locally on an A800 (80G) and then performing inference. Step 0: Prerequisites Make sure Python 3.10 or a later version is installed. If you want to run other Yi models, see software and hardware requirements. Step 1: Prepare your environment To set up the environment and install the required packages, execute the following command. git clone https://github.com/01-ai/Yi.git cd yi pip install -r requirements.txt Step 2: Download the Yi model You can download the weights and tokenizer of Yi models from the following sources: Hugging Face ModelScope WiseModel Step 3: Perform inference You can perform inference with Yi chat or base models as below. Perform inference with Yi chat model Create a file named quick_start.py and copy the following content to it. from transformers import AutoModelForCausalLM, AutoTokenizer model_path = '' tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False) Since transformers 4.35.0, the GPT-Q/AWQ model can be loaded using AutoModelForCausalLM. model = AutoModelForCausalLM.from_pretrained( model_path, device_map="auto", torch_dtype='auto' ).eval() Prompt content: "hi" messages = [ {"role": "user", "content": "hi"} ] input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt') output_ids = model.generate(input_ids.to('cuda')) response = tokenizer.decode(output_ids0:], skip_special_tokens=True) Model response: "Hello! How can I assist you today?" print(response) Run quick_start.py. python quick_start.py Then you can see an output similar to the one below. Hello! How can I assist you today? Perform inference with Yi base model Yi-34B The steps are similar to pip - Perform inference with Yi chat model. You can use the existing file text_generation.py. python demo/text_generation.py --model Then you can see an output similar to the one below. Output. Prompt: Let me tell you an interesting story about cat Tom and mouse Jerry, Generation: Let me tell you an interesting story about cat Tom and mouse Jerry, which happened in my childhood. My father had a big house with two cats living inside it to kill mice. One day when I was playing at home alone, I found one of the tomcats lying on his back near our kitchen door, looking very much like he wanted something from us but couldnt get up because there were too many people around him! He kept trying for several minutes before finally giving up... Yi-9B Input from transformers import AutoModelForCausalLM, AutoTokenizer MODEL_DIR = "01-ai/Yi-9B" model = AutoModelForCausalLM.from_pretrained(MODEL_DIR, torch_dtype="auto") tokenizer = AutoTokenizer.from_pretrained(MODEL_DIR, use_fast=False) input_text = "# write the quick sort algorithm" inputs = tokenizer(input_text, return_tensors="pt").to(model.device) outputs = model.generate(**inputs, max_length=256) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) Output \\\`bash write the quick sort algorithm def quick\_sort(arr): if len(arr) pivot\] return quick\_sort(left) + middle + quick\_sort(right) test the quick sort algorithm print(quick\_sort(\[3, 6, 8, 10, 1, 2, 1\])) [ Back to top ] Quick start - Docker Run Yi-34B-chat locally with Docker: a step-by-step guide. This tutorial guides you through every step of running Yi-34B-Chat on an A800 GPU or 4*4090 locally and then performing inference. Step 0: Prerequisites Make sure you've installed Docker and nvidia-container-toolkit. Step 1: Start Docker docker run -it --gpus all \ -v <your-model-path>: /models ghcr.io/01-ai/yi:latest Alternatively, you can pull the Yi Docker image from registry.lingyiwanwu.com/ci/01-ai/yi:latest. Step 2: Perform inference You can perform inference with Yi chat or base models as below. Perform inference with Yi chat model The steps are similar to pip - Perform inference with Yi chat model. Note that the only difference is to set model_path = '<your-model-mount-path>' instead of model_path = '<your-model-path>'. Perform inference with Yi base model The steps are similar to pip - Perform inference with Yi base model. Note that the only difference is to set --model <your-model-mount-path>' instead of model <your-model-path>. Quick start - conda-lock You can use conda-lock to generate fully reproducible lock files for conda environments. You can refer to conda-lock.yml for the exact versions of the dependencies. Additionally, you can utilize micromamba for installing these dependencies. To install the dependencies, follow these steps: Install micromamba by following the instructions available here. Execute micromamba install -y -n yi -f conda-lock.yml to create a conda environment named yi and install the necessary dependencies. Quick start - llama.cpp The following tutorial will guide you through every step of running a quantized model (Yi-chat-6B-2bits) locally and then performing inference. Run Yi-chat-6B-2bits locally with llama.cpp: a step-by-step guide. This tutorial guides you through every step of running a quantized model (Yi-chat-6B-2bits) locally and then performing inference. Step 0: Prerequisites Step 1: Download llama.cpp Step 2: Download Yi model Step 3: Perform inference Step 0: Prerequisites This tutorial assumes you use a MacBook Pro with 16GB of memory and an Apple M2 Pro chip. Make sure git-lfs is installed on your machine. Step 1: Download llama.cpp To clone the llama.cpp repository, run the following command. git clone [email protected]:ggerganov/llama.cpp.git Step 2: Download Yi model 2.1 To clone XeIaso/yi-chat-6B-GGUF with just pointers, run the following command. GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/XeIaso/yi-chat-6B-GGUF 2.2 To download a quantized Yi model (yi-chat-6b.Q2\_K.gguf), run the following command. git-lfs pull --include yi-chat-6b.Q2_K.gguf Step 3: Perform inference To perform inference with the Yi model, you can use one of the following methods. Method 1: Perform inference in terminal Method 2: Perform inference in web Method 1: Perform inference in terminal To compile llama.cpp using 4 threads and then conduct inference, navigate to the llama.cpp directory, and run the following command. Tips * Replace /Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.gguf with the actual path of your model. * By default, the model operates in completion mode. * For additional output customization options (for example, system prompt, temperature, repetition penalty, etc.), run ./main -h to check detailed descriptions and usage. make -j4 && ./main -m /Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.gguf -p "How do you feed your pet fox? Please answer this question in 6 simple steps:\nStep 1:" -n 384 -e ... How do you feed your pet fox? Please answer this question in 6 simple steps: Step 1: Select the appropriate food for your pet fox. You should choose high-quality, balanced prey items that are suitable for their unique dietary needs. These could include live or frozen mice, rats, pigeons, or other small mammals, as well as fresh fruits and vegetables. Step 2: Feed your pet fox once or twice a day, depending on the species and its individual preferences. Always ensure that they have access to fresh water throughout the day. Step 3: Provide an appropriate environment for your pet fox. Ensure it has a comfortable place to rest, plenty of space to move around, and opportunities to play and exercise. Step 4: Socialize your pet with other animals if possible. Interactions with other creatures can help them develop social skills and prevent boredom or stress. Step 5: Regularly check for signs of illness or discomfort in your fox. Be prepared to provide veterinary care as needed, especially for common issues such as parasites, dental health problems, or infections. Step 6: Educate yourself about the needs of your pet fox and be aware of any potential risks or concerns that could affect their well-being. Regularly consult with a veterinarian to ensure you are providing the best care. ... Now you have successfully asked a question to the Yi model and got an answer! Method 2: Perform inference in web To initialize a lightweight and swift chatbot, run the following command. cd llama.cpp ./server --ctx-size 2048 --host 0.0.0.0 --n-gpu-layers 64 --model /Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.gguf Then you can get an output like this: ... llama_new_context_with_model: n_ctx = 2048 llama_new_context_with_model: freq_base = 5000000.0 llama_new_context_with_model: freq_scale = 1 ggml_metal_init: allocating ggml_metal_init: found device: Apple M2 Pro ggml_metal_init: picking default device: Apple M2 Pro ggml_metal_init: ggml.metallib not found, loading from source ggml_metal_init: GGML_METAL_PATH_RESOURCES = nil ggml_metal_init: loading '/Users/yu/llama.cpp/ggml-metal.metal' ggml_metal_init: GPU name: Apple M2 Pro ggml_metal_init: GPU family: MTLGPUFamilyApple8 (1008) ggml_metal_init: hasUnifiedMemory = true ggml_metal_init: recommendedMaxWorkingSetSize = 11453.25 MB ggml_metal_init: maxTransferRate = built-in GPU ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 128.00 MiB, ( 2629.44 / 10922.67) llama_new_context_with_model: KV self size = 128.00 MiB, K (f16): 64.00 MiB, V (f16): 64.00 MiB ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 0.02 MiB, ( 2629.45 / 10922.67) llama_build_graph: non-view tensors processed: 676/676 llama_new_context_with_model: compute buffer total size = 159.19 MiB ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 156.02 MiB, ( 2785.45 / 10922.67) Available slots: -> Slot 0 - max context: 2048 llama server listening at http://0.0.0.0:8080 To access the chatbot interface, open your web browser and enter http://0.0.0.0:8080 into the address bar. Yi model chatbot interface - llama.cpp Enter a question, such as "How do you feed your pet fox? Please answer this question in 6 simple steps" into the prompt window, and you will receive a corresponding answer. Ask a question to Yi model - llama.cpp \ [Back to top \] Web demo You can build a web UI demo for Yi chat models (note that Yi base models are not supported in this senario). Step 1: Prepare your environment. Step 2: Download the Yi model. Step 3. To start a web service locally, run the following command. python demo/web_demo.py -c You can access the web UI by entering the address provided in the console into your browser. Quick start - web demo \ [Back to top \] Fine-tuning bash finetune/scripts/run_sft_Yi_6b.sh Once finished, you can compare the finetuned model and the base model with the following command: bash finetune/scripts/run_eval.sh For advanced usage (like fine-tuning based on your custom data), see the explanations below. Finetune code for Yi 6B and 34B Preparation From Image By default, we use a small dataset from BAAI/COIG to finetune the base model. You can also prepare your customized dataset in the following jsonl format: { "prompt": "Human: Who are you? Assistant:", "chosen": "I'm Yi." } And then mount them in the container to replace the default ones: docker run -it \ -v /path/to/save/finetuned/model/:/finetuned-model \ -v /path/to/train.jsonl:/yi/finetune/data/train.json \ -v /path/to/eval.jsonl:/yi/finetune/data/eval.json \ ghcr.io/01-ai/yi:latest \ bash finetune/scripts/run_sft_Yi_6b.sh From Local Server Make sure you have conda. If not, use mkdir -p ~/miniconda3 wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O ~/miniconda3/miniconda.sh bash /miniconda3/miniconda.sh -b -u -p /miniconda3 rm -rf ~/miniconda3/miniconda.sh ~/miniconda3/bin/conda init bash source ~/.bashrc Then, create a conda env: conda create -n dev_env python=3.10 -y conda activate dev_env pip install torch==2.0.1 deepspeed==0.10 tensorboard transformers datasets sentencepiece accelerate ray==2.7 Hardware Setup For the Yi-6B model, a node with 4 GPUs, each with GPU memory larger than 60GB, is recommended. For the Yi-34B model, because the usage of the zero-offload technique consumes a lot of CPU memory, please be careful to limit the number of GPUs in the 34B finetune training. Please use CUDA\_VISIBLE\_DEVICES to limit the number of GPUs (as shown in scripts/run\_sft\_Yi\_34b.sh). A typical hardware setup for finetuning the 34B model is a node with 8 GPUs (limited to 4 in running by CUDA\_VISIBLE\_DEVICES=0,1,2,3), each with GPU memory larger than 80GB, and total CPU memory larger than 900GB. Quick Start Download a LLM-base model to MODEL\_PATH (6B and 34B). A typical folder of models is like: |-- $MODEL_PATH | |-- config.json | |-- pytorch_model-00001-of-00002.bin | |-- pytorch_model-00002-of-00002.bin | |-- pytorch_model.bin.index.json | |-- tokenizer_config.json | |-- tokenizer.model | |-- ... Download a dataset from huggingface to local storage DATA\_PATH, e.g. Dahoas/rm-static. |-- $DATA_PATH | |-- data | | |-- train-00000-of-00001-2a1df75c6bce91ab.parquet | | |-- test-00000-of-00001-8c7c51afc6d45980.parquet | |-- dataset_infos.json | |-- README.md finetune/yi_example_dataset has example datasets, which are modified from BAAI/COIG |-- $DATA_PATH |--data |-- train.jsonl |-- eval.jsonl cd into the scripts folder, copy and paste the script, and run. For example: cd finetune/scripts bash run_sft_Yi_6b.sh For the Yi-6B base model, setting training\_debug\_steps=20 and num\_train\_epochs=4 can output a chat model, which takes about 20 minutes. For the Yi-34B base model, it takes a relatively long time for initialization. Please be patient. Evaluation cd finetune/scripts bash run_eval.sh Then you'll see the answer from both the base model and the finetuned model. \ [Back to top \] Quantization GPT-Q python quantization/gptq/quant_autogptq.py \ --model /base_model \ --output_dir /quantized_model \ --trust_remote_code Once finished, you can then evaluate the resulting model as follows: python quantization/gptq/eval_quantized_model.py \ --model /quantized_model \ --trust_remote_code For details, see the explanations below. GPT-Q quantization GPT-Q is a PTQ (Post-Training Quantization) method. It saves memory and provides potential speedups while retaining the accuracy of the model. Yi models can be GPT-Q quantized without a lot of efforts. We provide a step-by-step tutorial below. To run GPT-Q, we will use AutoGPTQ and exllama. And the huggingface transformers has integrated optimum and auto-gptq to perform GPTQ quantization on language models. Do Quantization The quant_autogptq.py script is provided for you to perform GPT-Q quantization: python quant_autogptq.py --model /base_model \ --output_dir /quantized_model --bits 4 --group_size 128 --trust_remote_code Run Quantized Model You can run a quantized model using the eval_quantized_model.py: python eval_quantized_model.py --model /quantized_model --trust_remote_code AWQ python quantization/awq/quant_autoawq.py \ --model /base_model \ --output_dir /quantized_model \ --trust_remote_code Once finished, you can then evaluate the resulting model as follows: python quantization/awq/eval_quantized_model.py \ --model /quantized_model \ --trust_remote_code For details, see the explanations below. AWQ quantization AWQ is a PTQ (Post-Training Quantization) method. It's an efficient and accurate low-bit weight quantization (INT3/4) for LLMs. Yi models can be AWQ quantized without a lot of efforts. We provide a step-by-step tutorial below. To run AWQ, we will use AutoAWQ. Do Quantization The quant_autoawq.py script is provided for you to perform AWQ quantization: python quant_autoawq.py --model /base_model \ --output_dir /quantized_model --bits 4 --group_size 128 --trust_remote_code Run Quantized Model You can run a quantized model using the eval_quantized_model.py: python eval_quantized_model.py --model /quantized_model --trust_remote_code \ [Back to top \] Deployment If you want to deploy Yi models, make sure you meet the software and hardware requirements. Software requirements Before using Yi quantized models, make sure you've installed the correct software listed below. Model Software Yi 4-bit quantized models AWQ and CUDA Yi 8-bit quantized models GPTQ and CUDA Hardware requirements Before deploying Yi in your environment, make sure your hardware meets the following requirements. Chat models Model Minimum VRAM Recommended GPU Example Yi-6B-Chat 15 GB 1 x RTX 3090 (24 GB) 1 x RTX 4090 (24 GB) 1 x A10 (24 GB) 1 x A30 (24 GB) Yi-6B-Chat-4bits 4 GB 1 x RTX 3060 (12 GB) 1 x RTX 4060 (8 GB) Yi-6B-Chat-8bits 8 GB 1 x RTX 3070 (8 GB) 1 x RTX 4060 (8 GB) Yi-34B-Chat 72 GB 4 x RTX 4090 (24 GB) 1 x A800 (80GB) Yi-34B-Chat-4bits 20 GB 1 x RTX 3090 (24 GB) 1 x RTX 4090 (24 GB) 1 x A10 (24 GB) 1 x A30 (24 GB) 1 x A100 (40 GB) Yi-34B-Chat-8bits 38 GB 2 x RTX 3090 (24 GB) 2 x RTX 4090 (24 GB) 1 x A800 (40 GB) Below are detailed minimum VRAM requirements under different batch use cases. Model batch=1 batch=4 batch=16 batch=32 Yi-6B-Chat 12 GB 13 GB 15 GB 18 GB Yi-6B-Chat-4bits 4 GB 5 GB 7 GB 10 GB Yi-6B-Chat-8bits 7 GB 8 GB 10 GB 14 GB Yi-34B-Chat 65 GB 68 GB 76 GB \> 80 GB Yi-34B-Chat-4bits 19 GB 20 GB 30 GB 40 GB Yi-34B-Chat-8bits 35 GB 37 GB 46 GB 58 GB Base models Model Minimum VRAM Recommended GPU Example Yi-6B 15 GB 1 x RTX 3090 (24 GB) 1 x RTX 4090 (24 GB) 1 x A10 (24 GB) 1 x A30 (24 GB) Yi-6B-200K 50 GB 1 x A800 (80 GB) Yi-9B 20 GB 1 x RTX 4090 (24 GB) Yi-34B 72 GB 4 x RTX 4090 (24 GB) 1 x A800 (80 GB) Yi-34B-200K 200 GB 4 x A800 (80 GB) \ [Back to top \] FAQ If you have any questions while using the Yi series models, the answers provided below could serve as a helpful reference for you. Fine-tuning Base model or Chat model - which to fine-tune?** The choice of pre-trained language model for fine-tuning hinges on the computational resources you have at your disposal and the particular demands of your task. If you are working with a substantial volume of fine-tuning data (say, over 10,000 samples), the Base model could be your go-to choice. On the other hand, if your fine-tuning data is not quite as extensive, opting for the Chat model might be a more fitting choice. It is generally advisable to fine-tune both the Base and Chat models, compare their performance, and then pick the model that best aligns with your specific requirements. Yi-34B versus Yi-34B-Chat for full-scale fine-tuning - what is the difference?** The key distinction between full-scale fine-tuning on \Yi-34B\and \Yi-34B-Chat\ comes down to the fine-tuning approach and outcomes. - Yi-34B-Chat employs a Special Fine-Tuning (SFT) method, resulting in responses that mirror human conversation style more closely. - The Base model's fine-tuning is more versatile, with a relatively high performance potential. - If you are confident in the quality of your data, fine-tuning with \Yi-34B\ could be your go-to. - If you are aiming for model-generated responses that better mimic human conversational style, or if you have doubts about your data quality, \Yi-34B-Chat\ might be your best bet. Quantization Quantized model versus original model - what is the performance gap?** The performance variance is largely contingent on the quantization method employed and the specific use cases of these models. For instance, when it comes to models provided by the AWQ official, from a Benchmark standpoint, quantization might result in a minor performance drop of a few percentage points. Subjectively speaking, in situations like logical reasoning, even a 1% performance shift could impact the accuracy of the output results. General Where can I source fine-tuning question answering datasets?** You can find fine-tuning question answering datasets on platforms like Hugging Face, with datasets like m-a-p/COIG-CQIA readily available. Additionally, Github offers fine-tuning frameworks, such as hiyouga/LLaMA-Factory, which integrates pre-made datasets. What is the GPU memory requirement for fine-tuning Yi-34B FP16?** The GPU memory needed for fine-tuning 34B FP16 hinges on the specific fine-tuning method employed. For full parameter fine-tuning, you'll need 8 GPUs each with 80 GB; however, more economical solutions like Lora require less. For more details, check out \hiyouga/LLaMA-Factory\. Also, consider using BF16 instead of FP16 for fine-tuning to optimize performance. Are there any third-party platforms that support chat functionality for the Yi-34b-200k model?** If you're looking for third-party Chats, options include \fireworks.ai\. Learning hub If you want to learn Yi, you can find a wealth of helpful educational resources here. Welcome to the Yi learning hub! Whether you're a seasoned developer or a newcomer, you can find a wealth of helpful educational resources to enhance your understanding and skills with Yi models, including insightful blog posts, comprehensive video tutorials, hands-on guides, and more. The content you find here has been generously contributed by knowledgeable Yi experts and passionate enthusiasts. We extend our heartfelt gratitude for your invaluable contributions! At the same time, we also warmly invite you to join our collaborative effort by contributing to Yi. If you have already made contributions to Yi, please don't hesitate to showcase your remarkable work in the table below. With all these resources at your fingertips, you're ready to start your exciting journey with Yi. Happy learning! Tutorials English tutorials Type Deliverable Date Author Video Run dolphin-2.2-yi-34b on IoT Devices 2023-11-30 Second State Blog Running Yi-34B-Chat locally using LlamaEdge 2023-11-30 Second State Video Install Yi 34B Locally - Chinese English Bilingual LLM 2023-11-05 Fahd Mirza Video Dolphin Yi 34b - Brand New Foundational Model TESTED 2023-11-27 Matthew Berman Chinese tutorials Type Deliverable Date Author GitHub project 2024-04-25 Blog yi-vl-plusAnki 2024-04-24 GitHub project yi-34b-chat-200k 2024-04-24 Blog Yi-VL 2024-02-02 Blog 34B Llama.cpp & 21G 2023-11-26 Blog Yi-34B 2023-12-10 Blog CPU 2023-12-12 Blog 3 Yi-6B Agent Llama Factory 2024-01-22 Blog Yi-VL& 2024-01-26 ModelScope Video 24G vllm Yi-34B 2023-12-28 Video Yi-VL-34B - A40 2023-01-28 Why Yi? Ecosystem Upstream Downstream Serving Quantization Fine-tuning API Benchmarks Chat model performance Base model performance Yi-34B and Yi-34B-200K Yi-9B Ecosystem Yi has a comprehensive ecosystem, offering a range of tools, services, and models to enrich your experiences and maximize productivity. Upstream Downstream Serving Quantization Fine-tuning API Upstream The Yi series models follow the same model architecture as Llama. By choosing Yi, you can leverage existing tools, libraries, and resources within the Llama ecosystem, eliminating the need to create new tools and enhancing development efficiency. For example, the Yi series models are saved in the format of the Llama model. You can directly use LlamaForCausalLM and LlamaTokenizer to load the model. For more information, see Use the chat model. from transformers import AutoModelForCausalLM, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("01-ai/Yi-34b", use_fast=False) model = AutoModelForCausalLM.from_pretrained("01-ai/Yi-34b", device_map="auto") \ [Back to top \] Downstream Tip * Feel free to create a PR and share the fantastic work you've built using the Yi series models. * To help others quickly understand your work, it is recommended to use the format of : + . Serving If you want to get up with Yi in a few minutes, you can use the following services built upon Yi. Yi-34B-Chat: you can chat with Yi using one of the following platforms: Yi-34B-Chat | Hugging Face Yi-34B-Chat | Yi Platform: Note that currently it's available through a whitelist. Welcome to apply (fill out a form in English or Chinese) and experience it firsthand! Yi-6B-Chat (Replicate): you can use this model with more options by setting additional parameters and calling APIs. ScaleLLM: you can use this service to run Yi models locally with added flexibility and customization. Quantization If you have limited computational capabilities, you can use Yi's quantized models as follows. These quantized models have reduced precision but offer increased efficiency, such as faster inference speed and smaller RAM usage. TheBloke/Yi-34B-GPTQ TheBloke/Yi-34B-GGUF TheBloke/Yi-34B-AWQ Fine-tuning If you're seeking to explore the diverse capabilities within Yi's thriving family, you can delve into Yi's fine-tuned models as below. TheBloke Models: this site hosts numerous fine-tuned models derived from various LLMs including Yi. This is not an exhaustive list for Yi, but to name a few sorted on downloads: TheBloke/dolphin-2\_2-yi-34b-AWQ TheBloke/Yi-34B-Chat-AWQ TheBloke/Yi-34B-Chat-GPTQ SUSTech/SUS-Chat-34B: this model ranked first among all models below 70B and outperformed the twice larger deepseek-llm-67b-chat. You can check the result on the Open LLM Leaderboard. OrionStarAI/OrionStar-Yi-34B-Chat-Llama: this model excelled beyond other models (such as GPT-4, Qwen-14B-Chat, Baichuan2-13B-Chat) in C-Eval and CMMLU evaluations on the OpenCompass LLM Leaderboard. NousResearch/Nous-Capybara-34B: this model is trained with 200K context length and 3 epochs on the Capybara dataset. API amazing-openai-api: this tool converts Yi model APIs into the OpenAI API format out of the box. LlamaEdge: this tool builds an OpenAI-compatible API server for Yi-34B-Chat using a portable Wasm (WebAssembly) file, powered by Rust. \ [Back to top \] Tech report For detailed capabilities of the Yi series model, see Yi: Open Foundation Models by 01.AI. Citation @misc{ai2024yi, title={Yi: Open Foundation Models by 01.AI}, author={01. AI and : and Alex Young and Bei Chen and Chao Li and Chengen Huang and Ge Zhang and Guanwei Zhang and Heng Li and Jiangcheng Zhu and Jianqun Chen and Jing Chang and Kaidong Yu and Peng Liu and Qiang Liu and Shawn Yue and Senbin Yang and Shiming Yang and Tao Yu and Wen Xie and Wenhao Huang and Xiaohui Hu and Xiaoyi Ren and Xinyao Niu and Pengcheng Nie and Yuchi Xu and Yudong Liu and Yue Wang and Yuxuan Cai and Zhenyu Gu and Zhiyuan Liu and Zonghong Dai}, year={2024}, eprint={2403.04652}, archivePrefix={arXiv}, primaryClass={cs.CL} } Benchmarks Chat model performance Base model performance Chat model performance Yi-34B-Chat model demonstrates exceptional performance, ranking first among all existing open-source models in the benchmarks including MMLU, CMMLU, BBH, GSM8k, and more. Chat model performance Evaluation methods and challenges. Evaluation methods**: we evaluated various benchmarks using both zero-shot and few-shot methods, except for TruthfulQA. Zero-shot vs. few-shot**: in chat models, the zero-shot approach is more commonly employed. Evaluation strategy**: our evaluation strategy involves generating responses while following instructions explicitly or implicitly (such as using few-shot examples). We then isolate relevant answers from the generated text. Challenges faced**: some models are not well-suited to produce output in the specific format required by instructions in few datasets, which leads to suboptimal results. \*: C-Eval results are evaluated on the validation datasets Base model performance Yi-34B and Yi-34B-200K The Yi-34B and Yi-34B-200K models stand out as the top performers among open-source models, especially excelling in MMLU, CMMLU, common-sense reasoning, reading comprehension, and more. Base model performance Evaluation methods. Disparity in results**: while benchmarking open-source models, a disparity has been noted between results from our pipeline and those reported by public sources like OpenCompass. Investigation findings**: a deeper investigation reveals that variations in prompts, post-processing strategies, and sampling techniques across models may lead to significant outcome differences. Uniform benchmarking process**: our methodology aligns with the original benchmarksconsistent prompts and post-processing strategies are used, and greedy decoding is applied during evaluations without any post-processing for the generated content. Efforts to retrieve unreported scores**: for scores that were not reported by the original authors (including scores reported with different settings), we try to get results with our pipeline. Extensive model evaluation**: to evaluate the models capability extensively, we adopted the methodology outlined in Llama2. Specifically, we included PIQA, SIQA, HellaSwag, WinoGrande, ARC, OBQA, and CSQA to assess common sense reasoning. SquAD, QuAC, and BoolQ were incorporated to evaluate reading comprehension. Special configurations**: CSQA was exclusively tested using a 7-shot setup, while all other tests were conducted with a 0-shot configuration. Additionally, we introduced GSM8K (8-shot@1), MATH (4-shot@1), HumanEval (0-shot@1), and MBPP (3-shot@1) under the category "Math & Code". Falcon-180B caveat**: Falcon-180B was not tested on QuAC and OBQA due to technical constraints. Its performance score is an average from other tasks, and considering the generally lower scores of these two tasks, Falcon-180B's capabilities are likely not underestimated. Yi-9B Yi-9B is almost the best among a range of similar-sized open-source models (including Mistral-7B, SOLAR-10.7B, Gemma-7B, DeepSeek-Coder-7B-Base-v1.5 and more), particularly excelling in code, math, common-sense reasoning, and reading comprehension. Yi-9B benchmark - details In terms of overall ability (Mean-All), Yi-9B performs the best among similarly sized open-source models, surpassing DeepSeek-Coder, DeepSeek-Math, Mistral-7B, SOLAR-10.7B, and Gemma-7B. Yi-9B benchmark - overall In terms of coding ability (Mean-Code), Yi-9B's performance is second only to DeepSeek-Coder-7B, surpassing Yi-34B, SOLAR-10.7B, Mistral-7B, and Gemma-7B. Yi-9B benchmark - code In terms of math ability (Mean-Math), Yi-9B's performance is second only to DeepSeek-Math-7B, surpassing SOLAR-10.7B, Mistral-7B, and Gemma-7B. Yi-9B benchmark - math In terms of common sense and reasoning ability (Mean-Text), Yi-9B's performance is on par with Mistral-7B, SOLAR-10.7B, and Gemma-7B. Yi-9B benchmark - text \ [Back to top \] Who can use Yi? Everyone! The Yi series models are free for personal usage, academic purposes, and commercial use. All usage must adhere to the Yi Series Models Community License Agreement 2.1 For free commercial use, you only need to complete this form to get a Yi Model Commercial License. \ [Back to top \] Misc. Acknowledgments A heartfelt thank you to each of you who have made contributions to the Yi community! You have helped Yi not just a project, but a vibrant, growing home for innovation. yi contributors \ [Back to top \] Disclaimer We use data compliance checking algorithms during the training process, to ensure the compliance of the trained model to the best of our ability. Due to complex data and the diversity of language model usage scenarios, we cannot guarantee that the model will generate correct, and reasonable output in all scenarios. Please be aware that there is still a risk of the model producing problematic outputs. We will not be responsible for any risks and issues resulting from misuse, misguidance, illegal usage, and related misinformation, as well as any associated data security concerns. \ [Back to top \] License The source code in this repo is licensed under the Apache 2.0 license. The Yi series models are fully open for academic research and free for commercial use, with automatic permission granted upon application. All usage must adhere to the Yi Series Models Community License Agreement 2.1. For free commercial use, you only need to send an email to get official commercial permission. \ [Back to top \]
Updated 5/28/2024
✅
Yi-6B
362
specify theme context for images Building the Next Generation of Open-Source and Bilingual LLMs Hugging Face ModelScope WiseModel Ask questions or discuss ideas on GitHub Join us on Discord or WeChat Check out Yi Tech Report Grow at Yi Learning Hub Table of Contents What is Yi? Introduction Models Chat models Base models Model info News How to use Yi? Quick start Choose your path pip docker llama.cpp conda-lock Web demo Fine-tuning Quantization Deployment FAQ Learning hub Why Yi? Ecosystem Upstream Downstream Serving Quantization Fine-tuning API Benchmarks Base model performance Chat model performance Tech report Citation Who can use Yi? Misc. Acknowledgements Disclaimer License What is Yi? Introduction The Yi series models are the next generation of open-source large language models trained from scratch by 01.AI. Targeted as a bilingual language model and trained on 3T multilingual corpus, the Yi series models become one of the strongest LLM worldwide, showing promise in language understanding, commonsense reasoning, reading comprehension, and more. For example, Yi-34B-Chat model landed in second place (following GPT-4 Turbo), outperforming other LLMs (such as GPT-4, Mixtral, Claude) on the AlpacaEval Leaderboard (based on data available up to January 2024). Yi-34B model ranked first among all existing open-source models (such as Falcon-180B, Llama-70B, Claude) in both English and Chinese on various benchmarks, including Hugging Face Open LLM Leaderboard (pre-trained) and C-Eval (based on data available up to November 2023). (Credits to Llama) Thanks to the Transformer and Llama open-source communities, as they reduce the efforts required to build from scratch and enable the utilization of the same tools within the AI ecosystem. If you're interested in Yi's adoption of Llama architecture and license usage policy, see Yi's relation with Llama. > TL;DR > > The Yi series models adopt the same model architecture as Llama but are NOT derivatives of Llama. Both Yi and Llama are based on the Transformer structure, which has been the standard architecture for large language models since 2018. Grounded in the Transformer architecture, Llama has become a new cornerstone for the majority of state-of-the-art open-source models due to its excellent stability, reliable convergence, and robust compatibility. This positions Llama as the recognized foundational framework for models including Yi. Thanks to the Transformer and Llama architectures, other models can leverage their power, reducing the effort required to build from scratch and enabling the utilization of the same tools within their ecosystems. However, the Yi series models are NOT derivatives of Llama, as they do not use Llama's weights. As Llama's structure is employed by the majority of open-source models, the key factors of determining model performance are training datasets, training pipelines, and training infrastructure. Developing in a unique and proprietary way, Yi has independently created its own high-quality training datasets, efficient training pipelines, and robust training infrastructure entirely from the ground up. This effort has led to excellent performance with Yi series models ranking just behind GPT4 and surpassing Llama on the Alpaca Leaderboard in Dec 2023. \ [Back to top \] News 2024-03-16: The Yi-9B-200K is open-sourced and available to the public. 2024-03-08: Yi Tech Report is published! 2024-03-07: The long text capability of the Yi-34B-200K has been enhanced. In the "Needle-in-a-Haystack" test, the Yi-34B-200K's performance is improved by 10.5%, rising from 89.3% to an impressive 99.8%. We continue to pre-train the model on 5B tokens long-context data mixture and demonstrate a near-all-green performance. 2024-03-06: The Yi-9B is open-sourced and available to the public. Yi-9B stands out as the top performer among a range of similar-sized open-source models (including Mistral-7B, SOLAR-10.7B, Gemma-7B, DeepSeek-Coder-7B-Base-v1.5 and more), particularly excelling in code, math, common-sense reasoning, and reading comprehension. 2024-01-23: The Yi-VL models, Yi-VL-34B and Yi-VL-6B, are open-sourced and available to the public. Yi-VL-34B has ranked first among all existing open-source models in the latest benchmarks, including MMMU and CMMMU (based on data available up to January 2024). 2023-11-23: Chat models are open-sourced and available to the public. This release contains two chat models based on previously released base models, two 8-bit models quantized by GPTQ, and two 4-bit models quantized by AWQ. Yi-34B-Chat Yi-34B-Chat-4bits Yi-34B-Chat-8bits Yi-6B-Chat Yi-6B-Chat-4bits Yi-6B-Chat-8bits You can try some of them interactively at: Hugging Face Replicate 2023-11-23: The Yi Series Models Community License Agreement is updated to v2.1. 2023-11-08: Invited test of Yi-34B chat model. Application form: English Chinese 2023-11-05: The base models, Yi-6B-200K and Yi-34B-200K, are open-sourced and available to the public. This release contains two base models with the same parameter sizes as the previous release, except that the context window is extended to 200K. 2023-11-02: The base models, Yi-6B and Yi-34B, are open-sourced and available to the public. The first public release contains two bilingual (English/Chinese) base models with the parameter sizes of 6B and 34B. Both of them are trained with 4K sequence length and can be extended to 32K during inference time. \ [Back to top \] Models Yi models come in multiple sizes and cater to different use cases. You can also fine-tune Yi models to meet your specific requirements. If you want to deploy Yi models, make sure you meet the software and hardware requirements. Chat models Model Download Yi-34B-Chat Hugging Face ModelScope Yi-34B-Chat-4bits Hugging Face ModelScope Yi-34B-Chat-8bits Hugging Face ModelScope Yi-6B-Chat Hugging Face ModelScope Yi-6B-Chat-4bits Hugging Face ModelScope Yi-6B-Chat-8bits Hugging Face ModelScope \- 4-bit series models are quantized by AWQ. \- 8-bit series models are quantized by GPTQ \- All quantized models have a low barrier to use since they can be deployed on consumer-grade GPUs (e.g., 3090, 4090). Base models Model Download Yi-34B Hugging Face ModelScope Yi-34B-200K Hugging Face ModelScope Yi-9B Hugging Face ModelScope Yi-9B-200K Hugging Face ModelScope Yi-6B Hugging Face ModelScope Yi-6B-200K Hugging Face ModelScope \- 200k is roughly equivalent to 400,000 Chinese characters. \- If you want to use the previous version of the Yi-34B-200K (released on Nov 5, 2023), run git checkout 069cd341d60f4ce4b07ec394e82b79e94f656cf to download the weight. Model info For chat and base models Model Intro Default context window Pretrained tokens Training Data Date 6B series models They are suitable for personal and academic use. 4K 3T Up to June 2023 9B series models It is the best at coding and math in the Yi series models. Yi-9B is continuously trained based on Yi-6B, using 0.8T tokens. 34B series models They are suitable for personal, academic, and commercial (particularly for small and medium-sized enterprises) purposes. It's a cost-effective solution that's affordable and equipped with emergent ability. 3T For chat models For chat model limitations, see the explanations below. The released chat model has undergone exclusive training using Supervised Fine-Tuning (SFT). Compared to other standard chat models, our model produces more diverse responses, making it suitable for various downstream tasks, such as creative scenarios. Furthermore, this diversity is expected to enhance the likelihood of generating higher quality responses, which will be advantageous for subsequent Reinforcement Learning (RL) training. However, this higher diversity might amplify certain existing issues, including: Hallucination: This refers to the model generating factually incorrect or nonsensical information. With the model's responses being more varied, there's a higher chance of hallucination that are not based on accurate data or logical reasoning. Non-determinism in re-generation: When attempting to regenerate or sample responses, inconsistencies in the outcomes may occur. The increased diversity can lead to varying results even under similar input conditions. Cumulative Error: This occurs when errors in the model's responses compound over time. As the model generates more diverse responses, the likelihood of small inaccuracies building up into larger errors increases, especially in complex tasks like extended reasoning, mathematical problem-solving, etc. To achieve more coherent and consistent responses, it is advisable to adjust generation configuration parameters such as temperature, top\_p, or top\_k. These adjustments can help in the balance between creativity and coherence in the model's outputs. \ [Back to top \] How to use Yi? Quick start Choose your path pip docker conda-lock llama.cpp Web demo Fine-tuning Quantization Deployment FAQ Learning hub Quick start Getting up and running with Yi models is simple with multiple choices available. Choose your path Select one of the following paths to begin your journey with Yi! Quick start - Choose your path Deploy Yi locally If you prefer to deploy Yi models locally, and you have sufficient resources (for example, NVIDIA A800 80GB), you can choose one of the following methods: pip Docker conda-lock and you have limited resources (for example, a MacBook Pro), you can use llama.cpp. Not to deploy Yi locally If you prefer not to deploy Yi models locally, you can explore Yi's capabilities using any of the following options. Run Yi with APIs If you want to explore more features of Yi, you can adopt one of these methods: Yi APIs (Yi official) Early access has been granted to some applicants. Stay tuned for the next round of access! Yi APIs (Replicate) Run Yi in playground If you want to chat with Yi with more customizable options (e.g., system prompt, temperature, repetition penalty, etc.), you can try one of the following options: Yi-34B-Chat-Playground (Yi official) Access is available through a whitelist. Welcome to apply (fill out a form in English or Chinese). Yi-34B-Chat-Playground (Replicate) Chat with Yi If you want to chat with Yi, you can use one of these online services, which offer a similar user experience: Yi-34B-Chat (Yi official on Hugging Face) No registration is required. Yi-34B-Chat (Yi official beta) Access is available through a whitelist. Welcome to apply (fill out a form in English or Chinese). \ [Back to top \] Quick start - pip This tutorial guides you through every step of running Yi-34B-Chat locally on an A800 (80G) and then performing inference. Step 0: Prerequisites Make sure Python 3.10 or a later version is installed. If you want to run other Yi models, see software and hardware requirements. Step 1: Prepare your environment To set up the environment and install the required packages, execute the following command. git clone https://github.com/01-ai/Yi.git cd yi pip install -r requirements.txt Step 2: Download the Yi model You can download the weights and tokenizer of Yi models from the following sources: Hugging Face ModelScope WiseModel Step 3: Perform inference You can perform inference with Yi chat or base models as below. Perform inference with Yi chat model Create a file named quick_start.py and copy the following content to it. from transformers import AutoModelForCausalLM, AutoTokenizer model_path = '' tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False) Since transformers 4.35.0, the GPT-Q/AWQ model can be loaded using AutoModelForCausalLM. model = AutoModelForCausalLM.from_pretrained( model_path, device_map="auto", torch_dtype='auto' ).eval() Prompt content: "hi" messages = [ {"role": "user", "content": "hi"} ] input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt') output_ids = model.generate(input_ids.to('cuda')) response = tokenizer.decode(output_ids0:], skip_special_tokens=True) Model response: "Hello! How can I assist you today?" print(response) Run quick_start.py. python quick_start.py Then you can see an output similar to the one below. Hello! How can I assist you today? Perform inference with Yi base model Yi-34B The steps are similar to pip - Perform inference with Yi chat model. You can use the existing file text_generation.py. python demo/text_generation.py --model Then you can see an output similar to the one below. Output. Prompt: Let me tell you an interesting story about cat Tom and mouse Jerry, Generation: Let me tell you an interesting story about cat Tom and mouse Jerry, which happened in my childhood. My father had a big house with two cats living inside it to kill mice. One day when I was playing at home alone, I found one of the tomcats lying on his back near our kitchen door, looking very much like he wanted something from us but couldnt get up because there were too many people around him! He kept trying for several minutes before finally giving up... Yi-9B Input from transformers import AutoModelForCausalLM, AutoTokenizer MODEL_DIR = "01-ai/Yi-9B" model = AutoModelForCausalLM.from_pretrained(MODEL_DIR, torch_dtype="auto") tokenizer = AutoTokenizer.from_pretrained(MODEL_DIR, use_fast=False) input_text = "# write the quick sort algorithm" inputs = tokenizer(input_text, return_tensors="pt").to(model.device) outputs = model.generate(**inputs, max_length=256) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) Output \\\`bash write the quick sort algorithm def quick\_sort(arr): if len(arr) pivot\] return quick\_sort(left) + middle + quick\_sort(right) test the quick sort algorithm print(quick\_sort(\[3, 6, 8, 10, 1, 2, 1\])) [ Back to top ] Quick start - Docker Run Yi-34B-chat locally with Docker: a step-by-step guide. This tutorial guides you through every step of running Yi-34B-Chat on an A800 GPU or 4*4090 locally and then performing inference. Step 0: Prerequisites Make sure you've installed Docker and nvidia-container-toolkit. Step 1: Start Docker docker run -it --gpus all \ -v <your-model-path>: /models ghcr.io/01-ai/yi:latest Alternatively, you can pull the Yi Docker image from registry.lingyiwanwu.com/ci/01-ai/yi:latest. Step 2: Perform inference You can perform inference with Yi chat or base models as below. Perform inference with Yi chat model The steps are similar to pip - Perform inference with Yi chat model. Note that the only difference is to set model_path = '<your-model-mount-path>' instead of model_path = '<your-model-path>'. Perform inference with Yi base model The steps are similar to pip - Perform inference with Yi base model. Note that the only difference is to set --model <your-model-mount-path>' instead of model <your-model-path>. Quick start - conda-lock You can use conda-lock to generate fully reproducible lock files for conda environments. You can refer to conda-lock.yml for the exact versions of the dependencies. Additionally, you can utilize micromamba for installing these dependencies. To install the dependencies, follow these steps: Install micromamba by following the instructions available here. Execute micromamba install -y -n yi -f conda-lock.yml to create a conda environment named yi and install the necessary dependencies. Quick start - llama.cpp The following tutorial will guide you through every step of running a quantized model (Yi-chat-6B-2bits) locally and then performing inference. Run Yi-chat-6B-2bits locally with llama.cpp: a step-by-step guide. This tutorial guides you through every step of running a quantized model (Yi-chat-6B-2bits) locally and then performing inference. Step 0: Prerequisites Step 1: Download llama.cpp Step 2: Download Yi model Step 3: Perform inference Step 0: Prerequisites This tutorial assumes you use a MacBook Pro with 16GB of memory and an Apple M2 Pro chip. Make sure git-lfs is installed on your machine. Step 1: Download llama.cpp To clone the llama.cpp repository, run the following command. git clone [email protected]:ggerganov/llama.cpp.git Step 2: Download Yi model 2.1 To clone XeIaso/yi-chat-6B-GGUF with just pointers, run the following command. GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/XeIaso/yi-chat-6B-GGUF 2.2 To download a quantized Yi model (yi-chat-6b.Q2\_K.gguf), run the following command. git-lfs pull --include yi-chat-6b.Q2_K.gguf Step 3: Perform inference To perform inference with the Yi model, you can use one of the following methods. Method 1: Perform inference in terminal Method 2: Perform inference in web Method 1: Perform inference in terminal To compile llama.cpp using 4 threads and then conduct inference, navigate to the llama.cpp directory, and run the following command. Tips * Replace /Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.gguf with the actual path of your model. * By default, the model operates in completion mode. * For additional output customization options (for example, system prompt, temperature, repetition penalty, etc.), run ./main -h to check detailed descriptions and usage. make -j4 && ./main -m /Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.gguf -p "How do you feed your pet fox? Please answer this question in 6 simple steps:\nStep 1:" -n 384 -e ... How do you feed your pet fox? Please answer this question in 6 simple steps: Step 1: Select the appropriate food for your pet fox. You should choose high-quality, balanced prey items that are suitable for their unique dietary needs. These could include live or frozen mice, rats, pigeons, or other small mammals, as well as fresh fruits and vegetables. Step 2: Feed your pet fox once or twice a day, depending on the species and its individual preferences. Always ensure that they have access to fresh water throughout the day. Step 3: Provide an appropriate environment for your pet fox. Ensure it has a comfortable place to rest, plenty of space to move around, and opportunities to play and exercise. Step 4: Socialize your pet with other animals if possible. Interactions with other creatures can help them develop social skills and prevent boredom or stress. Step 5: Regularly check for signs of illness or discomfort in your fox. Be prepared to provide veterinary care as needed, especially for common issues such as parasites, dental health problems, or infections. Step 6: Educate yourself about the needs of your pet fox and be aware of any potential risks or concerns that could affect their well-being. Regularly consult with a veterinarian to ensure you are providing the best care. ... Now you have successfully asked a question to the Yi model and got an answer! Method 2: Perform inference in web To initialize a lightweight and swift chatbot, run the following command. cd llama.cpp ./server --ctx-size 2048 --host 0.0.0.0 --n-gpu-layers 64 --model /Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.gguf Then you can get an output like this: ... llama_new_context_with_model: n_ctx = 2048 llama_new_context_with_model: freq_base = 5000000.0 llama_new_context_with_model: freq_scale = 1 ggml_metal_init: allocating ggml_metal_init: found device: Apple M2 Pro ggml_metal_init: picking default device: Apple M2 Pro ggml_metal_init: ggml.metallib not found, loading from source ggml_metal_init: GGML_METAL_PATH_RESOURCES = nil ggml_metal_init: loading '/Users/yu/llama.cpp/ggml-metal.metal' ggml_metal_init: GPU name: Apple M2 Pro ggml_metal_init: GPU family: MTLGPUFamilyApple8 (1008) ggml_metal_init: hasUnifiedMemory = true ggml_metal_init: recommendedMaxWorkingSetSize = 11453.25 MB ggml_metal_init: maxTransferRate = built-in GPU ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 128.00 MiB, ( 2629.44 / 10922.67) llama_new_context_with_model: KV self size = 128.00 MiB, K (f16): 64.00 MiB, V (f16): 64.00 MiB ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 0.02 MiB, ( 2629.45 / 10922.67) llama_build_graph: non-view tensors processed: 676/676 llama_new_context_with_model: compute buffer total size = 159.19 MiB ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 156.02 MiB, ( 2785.45 / 10922.67) Available slots: -> Slot 0 - max context: 2048 llama server listening at http://0.0.0.0:8080 To access the chatbot interface, open your web browser and enter http://0.0.0.0:8080 into the address bar. Yi model chatbot interface - llama.cpp Enter a question, such as "How do you feed your pet fox? Please answer this question in 6 simple steps" into the prompt window, and you will receive a corresponding answer. Ask a question to Yi model - llama.cpp \ [Back to top \] Web demo You can build a web UI demo for Yi chat models (note that Yi base models are not supported in this senario). Step 1: Prepare your environment. Step 2: Download the Yi model. Step 3. To start a web service locally, run the following command. python demo/web_demo.py -c You can access the web UI by entering the address provided in the console into your browser. Quick start - web demo \ [Back to top \] Fine-tuning bash finetune/scripts/run_sft_Yi_6b.sh Once finished, you can compare the finetuned model and the base model with the following command: bash finetune/scripts/run_eval.sh For advanced usage (like fine-tuning based on your custom data), see the explanations below. Finetune code for Yi 6B and 34B Preparation From Image By default, we use a small dataset from BAAI/COIG to finetune the base model. You can also prepare your customized dataset in the following jsonl format: { "prompt": "Human: Who are you? Assistant:", "chosen": "I'm Yi." } And then mount them in the container to replace the default ones: docker run -it \ -v /path/to/save/finetuned/model/:/finetuned-model \ -v /path/to/train.jsonl:/yi/finetune/data/train.json \ -v /path/to/eval.jsonl:/yi/finetune/data/eval.json \ ghcr.io/01-ai/yi:latest \ bash finetune/scripts/run_sft_Yi_6b.sh From Local Server Make sure you have conda. If not, use mkdir -p ~/miniconda3 wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O ~/miniconda3/miniconda.sh bash /miniconda3/miniconda.sh -b -u -p /miniconda3 rm -rf ~/miniconda3/miniconda.sh ~/miniconda3/bin/conda init bash source ~/.bashrc Then, create a conda env: conda create -n dev_env python=3.10 -y conda activate dev_env pip install torch==2.0.1 deepspeed==0.10 tensorboard transformers datasets sentencepiece accelerate ray==2.7 Hardware Setup For the Yi-6B model, a node with 4 GPUs, each with GPU memory larger than 60GB, is recommended. For the Yi-34B model, because the usage of the zero-offload technique consumes a lot of CPU memory, please be careful to limit the number of GPUs in the 34B finetune training. Please use CUDA\_VISIBLE\_DEVICES to limit the number of GPUs (as shown in scripts/run\_sft\_Yi\_34b.sh). A typical hardware setup for finetuning the 34B model is a node with 8 GPUs (limited to 4 in running by CUDA\_VISIBLE\_DEVICES=0,1,2,3), each with GPU memory larger than 80GB, and total CPU memory larger than 900GB. Quick Start Download a LLM-base model to MODEL\_PATH (6B and 34B). A typical folder of models is like: |-- $MODEL_PATH | |-- config.json | |-- pytorch_model-00001-of-00002.bin | |-- pytorch_model-00002-of-00002.bin | |-- pytorch_model.bin.index.json | |-- tokenizer_config.json | |-- tokenizer.model | |-- ... Download a dataset from huggingface to local storage DATA\_PATH, e.g. Dahoas/rm-static. |-- $DATA_PATH | |-- data | | |-- train-00000-of-00001-2a1df75c6bce91ab.parquet | | |-- test-00000-of-00001-8c7c51afc6d45980.parquet | |-- dataset_infos.json | |-- README.md finetune/yi_example_dataset has example datasets, which are modified from BAAI/COIG |-- $DATA_PATH |--data |-- train.jsonl |-- eval.jsonl cd into the scripts folder, copy and paste the script, and run. For example: cd finetune/scripts bash run_sft_Yi_6b.sh For the Yi-6B base model, setting training\_debug\_steps=20 and num\_train\_epochs=4 can output a chat model, which takes about 20 minutes. For the Yi-34B base model, it takes a relatively long time for initialization. Please be patient. Evaluation cd finetune/scripts bash run_eval.sh Then you'll see the answer from both the base model and the finetuned model. \ [Back to top \] Quantization GPT-Q python quantization/gptq/quant_autogptq.py \ --model /base_model \ --output_dir /quantized_model \ --trust_remote_code Once finished, you can then evaluate the resulting model as follows: python quantization/gptq/eval_quantized_model.py \ --model /quantized_model \ --trust_remote_code For details, see the explanations below. GPT-Q quantization GPT-Q is a PTQ (Post-Training Quantization) method. It saves memory and provides potential speedups while retaining the accuracy of the model. Yi models can be GPT-Q quantized without a lot of efforts. We provide a step-by-step tutorial below. To run GPT-Q, we will use AutoGPTQ and exllama. And the huggingface transformers has integrated optimum and auto-gptq to perform GPTQ quantization on language models. Do Quantization The quant_autogptq.py script is provided for you to perform GPT-Q quantization: python quant_autogptq.py --model /base_model \ --output_dir /quantized_model --bits 4 --group_size 128 --trust_remote_code Run Quantized Model You can run a quantized model using the eval_quantized_model.py: python eval_quantized_model.py --model /quantized_model --trust_remote_code AWQ python quantization/awq/quant_autoawq.py \ --model /base_model \ --output_dir /quantized_model \ --trust_remote_code Once finished, you can then evaluate the resulting model as follows: python quantization/awq/eval_quantized_model.py \ --model /quantized_model \ --trust_remote_code For details, see the explanations below. AWQ quantization AWQ is a PTQ (Post-Training Quantization) method. It's an efficient and accurate low-bit weight quantization (INT3/4) for LLMs. Yi models can be AWQ quantized without a lot of efforts. We provide a step-by-step tutorial below. To run AWQ, we will use AutoAWQ. Do Quantization The quant_autoawq.py script is provided for you to perform AWQ quantization: python quant_autoawq.py --model /base_model \ --output_dir /quantized_model --bits 4 --group_size 128 --trust_remote_code Run Quantized Model You can run a quantized model using the eval_quantized_model.py: python eval_quantized_model.py --model /quantized_model --trust_remote_code \ [Back to top \] Deployment If you want to deploy Yi models, make sure you meet the software and hardware requirements. Software requirements Before using Yi quantized models, make sure you've installed the correct software listed below. Model Software Yi 4-bit quantized models AWQ and CUDA Yi 8-bit quantized models GPTQ and CUDA Hardware requirements Before deploying Yi in your environment, make sure your hardware meets the following requirements. Chat models Model Minimum VRAM Recommended GPU Example Yi-6B-Chat 15 GB 1 x RTX 3090 (24 GB) 1 x RTX 4090 (24 GB) 1 x A10 (24 GB) 1 x A30 (24 GB) Yi-6B-Chat-4bits 4 GB 1 x RTX 3060 (12 GB) 1 x RTX 4060 (8 GB) Yi-6B-Chat-8bits 8 GB 1 x RTX 3070 (8 GB) 1 x RTX 4060 (8 GB) Yi-34B-Chat 72 GB 4 x RTX 4090 (24 GB) 1 x A800 (80GB) Yi-34B-Chat-4bits 20 GB 1 x RTX 3090 (24 GB) 1 x RTX 4090 (24 GB) 1 x A10 (24 GB) 1 x A30 (24 GB) 1 x A100 (40 GB) Yi-34B-Chat-8bits 38 GB 2 x RTX 3090 (24 GB) 2 x RTX 4090 (24 GB) 1 x A800 (40 GB) Below are detailed minimum VRAM requirements under different batch use cases. Model batch=1 batch=4 batch=16 batch=32 Yi-6B-Chat 12 GB 13 GB 15 GB 18 GB Yi-6B-Chat-4bits 4 GB 5 GB 7 GB 10 GB Yi-6B-Chat-8bits 7 GB 8 GB 10 GB 14 GB Yi-34B-Chat 65 GB 68 GB 76 GB \> 80 GB Yi-34B-Chat-4bits 19 GB 20 GB 30 GB 40 GB Yi-34B-Chat-8bits 35 GB 37 GB 46 GB 58 GB Base models Model Minimum VRAM Recommended GPU Example Yi-6B 15 GB 1 x RTX 3090 (24 GB) 1 x RTX 4090 (24 GB) 1 x A10 (24 GB) 1 x A30 (24 GB) Yi-6B-200K 50 GB 1 x A800 (80 GB) Yi-9B 20 GB 1 x RTX 4090 (24 GB) Yi-34B 72 GB 4 x RTX 4090 (24 GB) 1 x A800 (80 GB) Yi-34B-200K 200 GB 4 x A800 (80 GB) \ [Back to top \] FAQ If you have any questions while using the Yi series models, the answers provided below could serve as a helpful reference for you. Fine-tuning Base model or Chat model - which to fine-tune?** The choice of pre-trained language model for fine-tuning hinges on the computational resources you have at your disposal and the particular demands of your task. If you are working with a substantial volume of fine-tuning data (say, over 10,000 samples), the Base model could be your go-to choice. On the other hand, if your fine-tuning data is not quite as extensive, opting for the Chat model might be a more fitting choice. It is generally advisable to fine-tune both the Base and Chat models, compare their performance, and then pick the model that best aligns with your specific requirements. Yi-34B versus Yi-34B-Chat for full-scale fine-tuning - what is the difference?** The key distinction between full-scale fine-tuning on \Yi-34B\and \Yi-34B-Chat\ comes down to the fine-tuning approach and outcomes. - Yi-34B-Chat employs a Special Fine-Tuning (SFT) method, resulting in responses that mirror human conversation style more closely. - The Base model's fine-tuning is more versatile, with a relatively high performance potential. - If you are confident in the quality of your data, fine-tuning with \Yi-34B\ could be your go-to. - If you are aiming for model-generated responses that better mimic human conversational style, or if you have doubts about your data quality, \Yi-34B-Chat\ might be your best bet. Quantization Quantized model versus original model - what is the performance gap?** The performance variance is largely contingent on the quantization method employed and the specific use cases of these models. For instance, when it comes to models provided by the AWQ official, from a Benchmark standpoint, quantization might result in a minor performance drop of a few percentage points. Subjectively speaking, in situations like logical reasoning, even a 1% performance shift could impact the accuracy of the output results. General Where can I source fine-tuning question answering datasets?** You can find fine-tuning question answering datasets on platforms like Hugging Face, with datasets like m-a-p/COIG-CQIA readily available. Additionally, Github offers fine-tuning frameworks, such as hiyouga/LLaMA-Factory, which integrates pre-made datasets. What is the GPU memory requirement for fine-tuning Yi-34B FP16?** The GPU memory needed for fine-tuning 34B FP16 hinges on the specific fine-tuning method employed. For full parameter fine-tuning, you'll need 8 GPUs each with 80 GB; however, more economical solutions like Lora require less. For more details, check out \hiyouga/LLaMA-Factory\. Also, consider using BF16 instead of FP16 for fine-tuning to optimize performance. Are there any third-party platforms that support chat functionality for the Yi-34b-200k model?** If you're looking for third-party Chats, options include \fireworks.ai\. Learning hub If you want to learn Yi, you can find a wealth of helpful educational resources here. Welcome to the Yi learning hub! Whether you're a seasoned developer or a newcomer, you can find a wealth of helpful educational resources to enhance your understanding and skills with Yi models, including insightful blog posts, comprehensive video tutorials, hands-on guides, and more. The content you find here has been generously contributed by knowledgeable Yi experts and passionate enthusiasts. We extend our heartfelt gratitude for your invaluable contributions! At the same time, we also warmly invite you to join our collaborative effort by contributing to Yi. If you have already made contributions to Yi, please don't hesitate to showcase your remarkable work in the table below. With all these resources at your fingertips, you're ready to start your exciting journey with Yi. Happy learning! Tutorials English tutorials Type Deliverable Date Author Video Run dolphin-2.2-yi-34b on IoT Devices 2023-11-30 Second State Blog Running Yi-34B-Chat locally using LlamaEdge 2023-11-30 Second State Video Install Yi 34B Locally - Chinese English Bilingual LLM 2023-11-05 Fahd Mirza Video Dolphin Yi 34b - Brand New Foundational Model TESTED 2023-11-27 Matthew Berman Chinese tutorials Type Deliverable Date Author GitHub project 2024-04-25 Blog yi-vl-plusAnki 2024-04-24 GitHub project yi-34b-chat-200k 2024-04-24 Blog Yi-VL 2024-02-02 Blog 34B Llama.cpp & 21G 2023-11-26 Blog Yi-34B 2023-12-10 Blog CPU 2023-12-12 Blog 3 Yi-6B Agent Llama Factory 2024-01-22 Blog Yi-VL& 2024-01-26 ModelScope Video 24G vllm Yi-34B 2023-12-28 Video Yi-VL-34B - A40 2023-01-28 Why Yi? Ecosystem Upstream Downstream Serving Quantization Fine-tuning API Benchmarks Chat model performance Base model performance Yi-34B and Yi-34B-200K Yi-9B Ecosystem Yi has a comprehensive ecosystem, offering a range of tools, services, and models to enrich your experiences and maximize productivity. Upstream Downstream Serving Quantization Fine-tuning API Upstream The Yi series models follow the same model architecture as Llama. By choosing Yi, you can leverage existing tools, libraries, and resources within the Llama ecosystem, eliminating the need to create new tools and enhancing development efficiency. For example, the Yi series models are saved in the format of the Llama model. You can directly use LlamaForCausalLM and LlamaTokenizer to load the model. For more information, see Use the chat model. from transformers import AutoModelForCausalLM, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("01-ai/Yi-34b", use_fast=False) model = AutoModelForCausalLM.from_pretrained("01-ai/Yi-34b", device_map="auto") \ [Back to top \] Downstream Tip * Feel free to create a PR and share the fantastic work you've built using the Yi series models. * To help others quickly understand your work, it is recommended to use the format of : + . Serving If you want to get up with Yi in a few minutes, you can use the following services built upon Yi. Yi-34B-Chat: you can chat with Yi using one of the following platforms: Yi-34B-Chat | Hugging Face Yi-34B-Chat | Yi Platform: Note that currently it's available through a whitelist. Welcome to apply (fill out a form in English or Chinese) and experience it firsthand! Yi-6B-Chat (Replicate): you can use this model with more options by setting additional parameters and calling APIs. ScaleLLM: you can use this service to run Yi models locally with added flexibility and customization. Quantization If you have limited computational capabilities, you can use Yi's quantized models as follows. These quantized models have reduced precision but offer increased efficiency, such as faster inference speed and smaller RAM usage. TheBloke/Yi-34B-GPTQ TheBloke/Yi-34B-GGUF TheBloke/Yi-34B-AWQ Fine-tuning If you're seeking to explore the diverse capabilities within Yi's thriving family, you can delve into Yi's fine-tuned models as below. TheBloke Models: this site hosts numerous fine-tuned models derived from various LLMs including Yi. This is not an exhaustive list for Yi, but to name a few sorted on downloads: TheBloke/dolphin-2\_2-yi-34b-AWQ TheBloke/Yi-34B-Chat-AWQ TheBloke/Yi-34B-Chat-GPTQ SUSTech/SUS-Chat-34B: this model ranked first among all models below 70B and outperformed the twice larger deepseek-llm-67b-chat. You can check the result on the Open LLM Leaderboard. OrionStarAI/OrionStar-Yi-34B-Chat-Llama: this model excelled beyond other models (such as GPT-4, Qwen-14B-Chat, Baichuan2-13B-Chat) in C-Eval and CMMLU evaluations on the OpenCompass LLM Leaderboard. NousResearch/Nous-Capybara-34B: this model is trained with 200K context length and 3 epochs on the Capybara dataset. API amazing-openai-api: this tool converts Yi model APIs into the OpenAI API format out of the box. LlamaEdge: this tool builds an OpenAI-compatible API server for Yi-34B-Chat using a portable Wasm (WebAssembly) file, powered by Rust. \ [Back to top \] Tech report For detailed capabilities of the Yi series model, see Yi: Open Foundation Models by 01.AI. Citation @misc{ai2024yi, title={Yi: Open Foundation Models by 01.AI}, author={01. AI and : and Alex Young and Bei Chen and Chao Li and Chengen Huang and Ge Zhang and Guanwei Zhang and Heng Li and Jiangcheng Zhu and Jianqun Chen and Jing Chang and Kaidong Yu and Peng Liu and Qiang Liu and Shawn Yue and Senbin Yang and Shiming Yang and Tao Yu and Wen Xie and Wenhao Huang and Xiaohui Hu and Xiaoyi Ren and Xinyao Niu and Pengcheng Nie and Yuchi Xu and Yudong Liu and Yue Wang and Yuxuan Cai and Zhenyu Gu and Zhiyuan Liu and Zonghong Dai}, year={2024}, eprint={2403.04652}, archivePrefix={arXiv}, primaryClass={cs.CL} } Benchmarks Chat model performance Base model performance Chat model performance Yi-34B-Chat model demonstrates exceptional performance, ranking first among all existing open-source models in the benchmarks including MMLU, CMMLU, BBH, GSM8k, and more. Chat model performance Evaluation methods and challenges. Evaluation methods**: we evaluated various benchmarks using both zero-shot and few-shot methods, except for TruthfulQA. Zero-shot vs. few-shot**: in chat models, the zero-shot approach is more commonly employed. Evaluation strategy**: our evaluation strategy involves generating responses while following instructions explicitly or implicitly (such as using few-shot examples). We then isolate relevant answers from the generated text. Challenges faced**: some models are not well-suited to produce output in the specific format required by instructions in few datasets, which leads to suboptimal results. \*: C-Eval results are evaluated on the validation datasets Base model performance Yi-34B and Yi-34B-200K The Yi-34B and Yi-34B-200K models stand out as the top performers among open-source models, especially excelling in MMLU, CMMLU, common-sense reasoning, reading comprehension, and more. Base model performance Evaluation methods. Disparity in results**: while benchmarking open-source models, a disparity has been noted between results from our pipeline and those reported by public sources like OpenCompass. Investigation findings**: a deeper investigation reveals that variations in prompts, post-processing strategies, and sampling techniques across models may lead to significant outcome differences. Uniform benchmarking process**: our methodology aligns with the original benchmarksconsistent prompts and post-processing strategies are used, and greedy decoding is applied during evaluations without any post-processing for the generated content. Efforts to retrieve unreported scores**: for scores that were not reported by the original authors (including scores reported with different settings), we try to get results with our pipeline. Extensive model evaluation**: to evaluate the models capability extensively, we adopted the methodology outlined in Llama2. Specifically, we included PIQA, SIQA, HellaSwag, WinoGrande, ARC, OBQA, and CSQA to assess common sense reasoning. SquAD, QuAC, and BoolQ were incorporated to evaluate reading comprehension. Special configurations**: CSQA was exclusively tested using a 7-shot setup, while all other tests were conducted with a 0-shot configuration. Additionally, we introduced GSM8K (8-shot@1), MATH (4-shot@1), HumanEval (0-shot@1), and MBPP (3-shot@1) under the category "Math & Code". Falcon-180B caveat**: Falcon-180B was not tested on QuAC and OBQA due to technical constraints. Its performance score is an average from other tasks, and considering the generally lower scores of these two tasks, Falcon-180B's capabilities are likely not underestimated. Yi-9B Yi-9B is almost the best among a range of similar-sized open-source models (including Mistral-7B, SOLAR-10.7B, Gemma-7B, DeepSeek-Coder-7B-Base-v1.5 and more), particularly excelling in code, math, common-sense reasoning, and reading comprehension. Yi-9B benchmark - details In terms of overall ability (Mean-All), Yi-9B performs the best among similarly sized open-source models, surpassing DeepSeek-Coder, DeepSeek-Math, Mistral-7B, SOLAR-10.7B, and Gemma-7B. Yi-9B benchmark - overall In terms of coding ability (Mean-Code), Yi-9B's performance is second only to DeepSeek-Coder-7B, surpassing Yi-34B, SOLAR-10.7B, Mistral-7B, and Gemma-7B. Yi-9B benchmark - code In terms of math ability (Mean-Math), Yi-9B's performance is second only to DeepSeek-Math-7B, surpassing SOLAR-10.7B, Mistral-7B, and Gemma-7B. Yi-9B benchmark - math In terms of common sense and reasoning ability (Mean-Text), Yi-9B's performance is on par with Mistral-7B, SOLAR-10.7B, and Gemma-7B. Yi-9B benchmark - text \ [Back to top \] Who can use Yi? Everyone! The Yi series models are free for personal usage, academic purposes, and commercial use. All usage must adhere to the Yi Series Models Community License Agreement 2.1 For free commercial use, you only need to complete this form to get a Yi Model Commercial License. \ [Back to top \] Misc. Acknowledgments A heartfelt thank you to each of you who have made contributions to the Yi community! You have helped Yi not just a project, but a vibrant, growing home for innovation. yi contributors \ [Back to top \] Disclaimer We use data compliance checking algorithms during the training process, to ensure the compliance of the trained model to the best of our ability. Due to complex data and the diversity of language model usage scenarios, we cannot guarantee that the model will generate correct, and reasonable output in all scenarios. Please be aware that there is still a risk of the model producing problematic outputs. We will not be responsible for any risks and issues resulting from misuse, misguidance, illegal usage, and related misinformation, as well as any associated data security concerns. \ [Back to top \] License The source code in this repo is licensed under the Apache 2.0 license. The Yi series models are fully open for academic research and free for commercial use, with automatic permission granted upon application. All usage must adhere to the Yi Series Models Community License Agreement 2.1. For free commercial use, you only need to send an email to get official commercial permission. \ [Back to top \]
Updated 5/28/2024
🤯
Yi-34B-Chat
326
specify theme context for images Building the Next Generation of Open-Source and Bilingual LLMs Hugging Face ModelScope WiseModel Ask questions or discuss ideas on GitHub Join us on Discord or WeChat Check out Yi Tech Report Grow at Yi Learning Hub Table of Contents What is Yi? Introduction Models Chat models Base models Model info News How to use Yi? Quick start Choose your path pip docker llama.cpp conda-lock Web demo Fine-tuning Quantization Deployment FAQ Learning hub Why Yi? Ecosystem Upstream Downstream Serving Quantization Fine-tuning API Benchmarks Base model performance Chat model performance Tech report Citation Who can use Yi? Misc. Acknowledgements Disclaimer License What is Yi? Introduction The Yi series models are the next generation of open-source large language models trained from scratch by 01.AI. Targeted as a bilingual language model and trained on 3T multilingual corpus, the Yi series models become one of the strongest LLM worldwide, showing promise in language understanding, commonsense reasoning, reading comprehension, and more. For example, Yi-34B-Chat model landed in second place (following GPT-4 Turbo), outperforming other LLMs (such as GPT-4, Mixtral, Claude) on the AlpacaEval Leaderboard (based on data available up to January 2024). Yi-34B model ranked first among all existing open-source models (such as Falcon-180B, Llama-70B, Claude) in both English and Chinese on various benchmarks, including Hugging Face Open LLM Leaderboard (pre-trained) and C-Eval (based on data available up to November 2023). (Credits to Llama) Thanks to the Transformer and Llama open-source communities, as they reduce the efforts required to build from scratch and enable the utilization of the same tools within the AI ecosystem. If you're interested in Yi's adoption of Llama architecture and license usage policy, see Yi's relation with Llama. > TL;DR > > The Yi series models adopt the same model architecture as Llama but are NOT derivatives of Llama. Both Yi and Llama are based on the Transformer structure, which has been the standard architecture for large language models since 2018. Grounded in the Transformer architecture, Llama has become a new cornerstone for the majority of state-of-the-art open-source models due to its excellent stability, reliable convergence, and robust compatibility. This positions Llama as the recognized foundational framework for models including Yi. Thanks to the Transformer and Llama architectures, other models can leverage their power, reducing the effort required to build from scratch and enabling the utilization of the same tools within their ecosystems. However, the Yi series models are NOT derivatives of Llama, as they do not use Llama's weights. As Llama's structure is employed by the majority of open-source models, the key factors of determining model performance are training datasets, training pipelines, and training infrastructure. Developing in a unique and proprietary way, Yi has independently created its own high-quality training datasets, efficient training pipelines, and robust training infrastructure entirely from the ground up. This effort has led to excellent performance with Yi series models ranking just behind GPT4 and surpassing Llama on the Alpaca Leaderboard in Dec 2023. \ [Back to top \] News 2024-03-16: The Yi-9B-200K is open-sourced and available to the public. 2024-03-08: Yi Tech Report is published! 2024-03-07: The long text capability of the Yi-34B-200K has been enhanced. In the "Needle-in-a-Haystack" test, the Yi-34B-200K's performance is improved by 10.5%, rising from 89.3% to an impressive 99.8%. We continue to pre-train the model on 5B tokens long-context data mixture and demonstrate a near-all-green performance. 2024-03-06: The Yi-9B is open-sourced and available to the public. Yi-9B stands out as the top performer among a range of similar-sized open-source models (including Mistral-7B, SOLAR-10.7B, Gemma-7B, DeepSeek-Coder-7B-Base-v1.5 and more), particularly excelling in code, math, common-sense reasoning, and reading comprehension. 2024-01-23: The Yi-VL models, Yi-VL-34B and Yi-VL-6B, are open-sourced and available to the public. Yi-VL-34B has ranked first among all existing open-source models in the latest benchmarks, including MMMU and CMMMU (based on data available up to January 2024). 2023-11-23: Chat models are open-sourced and available to the public. This release contains two chat models based on previously released base models, two 8-bit models quantized by GPTQ, and two 4-bit models quantized by AWQ. Yi-34B-Chat Yi-34B-Chat-4bits Yi-34B-Chat-8bits Yi-6B-Chat Yi-6B-Chat-4bits Yi-6B-Chat-8bits You can try some of them interactively at: Hugging Face Replicate 2023-11-23: The Yi Series Models Community License Agreement is updated to v2.1. 2023-11-08: Invited test of Yi-34B chat model. Application form: English Chinese 2023-11-05: The base models, Yi-6B-200K and Yi-34B-200K, are open-sourced and available to the public. This release contains two base models with the same parameter sizes as the previous release, except that the context window is extended to 200K. 2023-11-02: The base models, Yi-6B and Yi-34B, are open-sourced and available to the public. The first public release contains two bilingual (English/Chinese) base models with the parameter sizes of 6B and 34B. Both of them are trained with 4K sequence length and can be extended to 32K during inference time. \ [Back to top \] Models Yi models come in multiple sizes and cater to different use cases. You can also fine-tune Yi models to meet your specific requirements. If you want to deploy Yi models, make sure you meet the software and hardware requirements. Chat models Model Download Yi-34B-Chat Hugging Face ModelScope Yi-34B-Chat-4bits Hugging Face ModelScope Yi-34B-Chat-8bits Hugging Face ModelScope Yi-6B-Chat Hugging Face ModelScope Yi-6B-Chat-4bits Hugging Face ModelScope Yi-6B-Chat-8bits Hugging Face ModelScope \- 4-bit series models are quantized by AWQ. \- 8-bit series models are quantized by GPTQ \- All quantized models have a low barrier to use since they can be deployed on consumer-grade GPUs (e.g., 3090, 4090). Base models Model Download Yi-34B Hugging Face ModelScope Yi-34B-200K Hugging Face ModelScope Yi-9B Hugging Face ModelScope Yi-9B-200K Hugging Face ModelScope Yi-6B Hugging Face ModelScope Yi-6B-200K Hugging Face ModelScope \- 200k is roughly equivalent to 400,000 Chinese characters. \- If you want to use the previous version of the Yi-34B-200K (released on Nov 5, 2023), run git checkout 069cd341d60f4ce4b07ec394e82b79e94f656cf to download the weight. Model info For chat and base models Model Intro Default context window Pretrained tokens Training Data Date 6B series models They are suitable for personal and academic use. 4K 3T Up to June 2023 9B series models It is the best at coding and math in the Yi series models. Yi-9B is continuously trained based on Yi-6B, using 0.8T tokens. 34B series models They are suitable for personal, academic, and commercial (particularly for small and medium-sized enterprises) purposes. It's a cost-effective solution that's affordable and equipped with emergent ability. 3T For chat models For chat model limitations, see the explanations below. The released chat model has undergone exclusive training using Supervised Fine-Tuning (SFT). Compared to other standard chat models, our model produces more diverse responses, making it suitable for various downstream tasks, such as creative scenarios. Furthermore, this diversity is expected to enhance the likelihood of generating higher quality responses, which will be advantageous for subsequent Reinforcement Learning (RL) training. However, this higher diversity might amplify certain existing issues, including: Hallucination: This refers to the model generating factually incorrect or nonsensical information. With the model's responses being more varied, there's a higher chance of hallucination that are not based on accurate data or logical reasoning. Non-determinism in re-generation: When attempting to regenerate or sample responses, inconsistencies in the outcomes may occur. The increased diversity can lead to varying results even under similar input conditions. Cumulative Error: This occurs when errors in the model's responses compound over time. As the model generates more diverse responses, the likelihood of small inaccuracies building up into larger errors increases, especially in complex tasks like extended reasoning, mathematical problem-solving, etc. To achieve more coherent and consistent responses, it is advisable to adjust generation configuration parameters such as temperature, top\_p, or top\_k. These adjustments can help in the balance between creativity and coherence in the model's outputs. \ [Back to top \] How to use Yi? Quick start Choose your path pip docker conda-lock llama.cpp Web demo Fine-tuning Quantization Deployment FAQ Learning hub Quick start Getting up and running with Yi models is simple with multiple choices available. Choose your path Select one of the following paths to begin your journey with Yi! Quick start - Choose your path Deploy Yi locally If you prefer to deploy Yi models locally, and you have sufficient resources (for example, NVIDIA A800 80GB), you can choose one of the following methods: pip Docker conda-lock and you have limited resources (for example, a MacBook Pro), you can use llama.cpp. Not to deploy Yi locally If you prefer not to deploy Yi models locally, you can explore Yi's capabilities using any of the following options. Run Yi with APIs If you want to explore more features of Yi, you can adopt one of these methods: Yi APIs (Yi official) Early access has been granted to some applicants. Stay tuned for the next round of access! Yi APIs (Replicate) Run Yi in playground If you want to chat with Yi with more customizable options (e.g., system prompt, temperature, repetition penalty, etc.), you can try one of the following options: Yi-34B-Chat-Playground (Yi official) Access is available through a whitelist. Welcome to apply (fill out a form in English or Chinese). Yi-34B-Chat-Playground (Replicate) Chat with Yi If you want to chat with Yi, you can use one of these online services, which offer a similar user experience: Yi-34B-Chat (Yi official on Hugging Face) No registration is required. Yi-34B-Chat (Yi official beta) Access is available through a whitelist. Welcome to apply (fill out a form in English or Chinese). \ [Back to top \] Quick start - pip This tutorial guides you through every step of running Yi-34B-Chat locally on an A800 (80G) and then performing inference. Step 0: Prerequisites Make sure Python 3.10 or a later version is installed. If you want to run other Yi models, see software and hardware requirements. Step 1: Prepare your environment To set up the environment and install the required packages, execute the following command. git clone https://github.com/01-ai/Yi.git cd yi pip install -r requirements.txt Step 2: Download the Yi model You can download the weights and tokenizer of Yi models from the following sources: Hugging Face ModelScope WiseModel Step 3: Perform inference You can perform inference with Yi chat or base models as below. Perform inference with Yi chat model Create a file named quick_start.py and copy the following content to it. from transformers import AutoModelForCausalLM, AutoTokenizer model_path = '' tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False) Since transformers 4.35.0, the GPT-Q/AWQ model can be loaded using AutoModelForCausalLM. model = AutoModelForCausalLM.from_pretrained( model_path, device_map="auto", torch_dtype='auto' ).eval() Prompt content: "hi" messages = [ {"role": "user", "content": "hi"} ] input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt') output_ids = model.generate(input_ids.to('cuda')) response = tokenizer.decode(output_ids0:], skip_special_tokens=True) Model response: "Hello! How can I assist you today?" print(response) Run quick_start.py. python quick_start.py Then you can see an output similar to the one below. Hello! How can I assist you today? Perform inference with Yi base model Yi-34B The steps are similar to pip - Perform inference with Yi chat model. You can use the existing file text_generation.py. python demo/text_generation.py --model Then you can see an output similar to the one below. Output. Prompt: Let me tell you an interesting story about cat Tom and mouse Jerry, Generation: Let me tell you an interesting story about cat Tom and mouse Jerry, which happened in my childhood. My father had a big house with two cats living inside it to kill mice. One day when I was playing at home alone, I found one of the tomcats lying on his back near our kitchen door, looking very much like he wanted something from us but couldnt get up because there were too many people around him! He kept trying for several minutes before finally giving up... Yi-9B Input from transformers import AutoModelForCausalLM, AutoTokenizer MODEL_DIR = "01-ai/Yi-9B" model = AutoModelForCausalLM.from_pretrained(MODEL_DIR, torch_dtype="auto") tokenizer = AutoTokenizer.from_pretrained(MODEL_DIR, use_fast=False) input_text = "# write the quick sort algorithm" inputs = tokenizer(input_text, return_tensors="pt").to(model.device) outputs = model.generate(**inputs, max_length=256) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) Output \\\`bash write the quick sort algorithm def quick\_sort(arr): if len(arr) pivot\] return quick\_sort(left) + middle + quick\_sort(right) test the quick sort algorithm print(quick\_sort(\[3, 6, 8, 10, 1, 2, 1\])) [ Back to top ] Quick start - Docker Run Yi-34B-chat locally with Docker: a step-by-step guide. This tutorial guides you through every step of running Yi-34B-Chat on an A800 GPU or 4*4090 locally and then performing inference. Step 0: Prerequisites Make sure you've installed Docker and nvidia-container-toolkit. Step 1: Start Docker docker run -it --gpus all \ -v <your-model-path>: /models ghcr.io/01-ai/yi:latest Alternatively, you can pull the Yi Docker image from registry.lingyiwanwu.com/ci/01-ai/yi:latest. Step 2: Perform inference You can perform inference with Yi chat or base models as below. Perform inference with Yi chat model The steps are similar to pip - Perform inference with Yi chat model. Note that the only difference is to set model_path = '<your-model-mount-path>' instead of model_path = '<your-model-path>'. Perform inference with Yi base model The steps are similar to pip - Perform inference with Yi base model. Note that the only difference is to set --model <your-model-mount-path>' instead of model <your-model-path>. Quick start - conda-lock You can use conda-lock to generate fully reproducible lock files for conda environments. You can refer to conda-lock.yml for the exact versions of the dependencies. Additionally, you can utilize micromamba for installing these dependencies. To install the dependencies, follow these steps: Install micromamba by following the instructions available here. Execute micromamba install -y -n yi -f conda-lock.yml to create a conda environment named yi and install the necessary dependencies. Quick start - llama.cpp The following tutorial will guide you through every step of running a quantized model (Yi-chat-6B-2bits) locally and then performing inference. Run Yi-chat-6B-2bits locally with llama.cpp: a step-by-step guide. This tutorial guides you through every step of running a quantized model (Yi-chat-6B-2bits) locally and then performing inference. Step 0: Prerequisites Step 1: Download llama.cpp Step 2: Download Yi model Step 3: Perform inference Step 0: Prerequisites This tutorial assumes you use a MacBook Pro with 16GB of memory and an Apple M2 Pro chip. Make sure git-lfs is installed on your machine. Step 1: Download llama.cpp To clone the llama.cpp repository, run the following command. git clone [email protected]:ggerganov/llama.cpp.git Step 2: Download Yi model 2.1 To clone XeIaso/yi-chat-6B-GGUF with just pointers, run the following command. GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/XeIaso/yi-chat-6B-GGUF 2.2 To download a quantized Yi model (yi-chat-6b.Q2\_K.gguf), run the following command. git-lfs pull --include yi-chat-6b.Q2_K.gguf Step 3: Perform inference To perform inference with the Yi model, you can use one of the following methods. Method 1: Perform inference in terminal Method 2: Perform inference in web Method 1: Perform inference in terminal To compile llama.cpp using 4 threads and then conduct inference, navigate to the llama.cpp directory, and run the following command. Tips * Replace /Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.gguf with the actual path of your model. * By default, the model operates in completion mode. * For additional output customization options (for example, system prompt, temperature, repetition penalty, etc.), run ./main -h to check detailed descriptions and usage. make -j4 && ./main -m /Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.gguf -p "How do you feed your pet fox? Please answer this question in 6 simple steps:\nStep 1:" -n 384 -e ... How do you feed your pet fox? Please answer this question in 6 simple steps: Step 1: Select the appropriate food for your pet fox. You should choose high-quality, balanced prey items that are suitable for their unique dietary needs. These could include live or frozen mice, rats, pigeons, or other small mammals, as well as fresh fruits and vegetables. Step 2: Feed your pet fox once or twice a day, depending on the species and its individual preferences. Always ensure that they have access to fresh water throughout the day. Step 3: Provide an appropriate environment for your pet fox. Ensure it has a comfortable place to rest, plenty of space to move around, and opportunities to play and exercise. Step 4: Socialize your pet with other animals if possible. Interactions with other creatures can help them develop social skills and prevent boredom or stress. Step 5: Regularly check for signs of illness or discomfort in your fox. Be prepared to provide veterinary care as needed, especially for common issues such as parasites, dental health problems, or infections. Step 6: Educate yourself about the needs of your pet fox and be aware of any potential risks or concerns that could affect their well-being. Regularly consult with a veterinarian to ensure you are providing the best care. ... Now you have successfully asked a question to the Yi model and got an answer! Method 2: Perform inference in web To initialize a lightweight and swift chatbot, run the following command. cd llama.cpp ./server --ctx-size 2048 --host 0.0.0.0 --n-gpu-layers 64 --model /Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.gguf Then you can get an output like this: ... llama_new_context_with_model: n_ctx = 2048 llama_new_context_with_model: freq_base = 5000000.0 llama_new_context_with_model: freq_scale = 1 ggml_metal_init: allocating ggml_metal_init: found device: Apple M2 Pro ggml_metal_init: picking default device: Apple M2 Pro ggml_metal_init: ggml.metallib not found, loading from source ggml_metal_init: GGML_METAL_PATH_RESOURCES = nil ggml_metal_init: loading '/Users/yu/llama.cpp/ggml-metal.metal' ggml_metal_init: GPU name: Apple M2 Pro ggml_metal_init: GPU family: MTLGPUFamilyApple8 (1008) ggml_metal_init: hasUnifiedMemory = true ggml_metal_init: recommendedMaxWorkingSetSize = 11453.25 MB ggml_metal_init: maxTransferRate = built-in GPU ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 128.00 MiB, ( 2629.44 / 10922.67) llama_new_context_with_model: KV self size = 128.00 MiB, K (f16): 64.00 MiB, V (f16): 64.00 MiB ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 0.02 MiB, ( 2629.45 / 10922.67) llama_build_graph: non-view tensors processed: 676/676 llama_new_context_with_model: compute buffer total size = 159.19 MiB ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 156.02 MiB, ( 2785.45 / 10922.67) Available slots: -> Slot 0 - max context: 2048 llama server listening at http://0.0.0.0:8080 To access the chatbot interface, open your web browser and enter http://0.0.0.0:8080 into the address bar. Yi model chatbot interface - llama.cpp Enter a question, such as "How do you feed your pet fox? Please answer this question in 6 simple steps" into the prompt window, and you will receive a corresponding answer. Ask a question to Yi model - llama.cpp \ [Back to top \] Web demo You can build a web UI demo for Yi chat models (note that Yi base models are not supported in this senario). Step 1: Prepare your environment. Step 2: Download the Yi model. Step 3. To start a web service locally, run the following command. python demo/web_demo.py -c You can access the web UI by entering the address provided in the console into your browser. Quick start - web demo \ [Back to top \] Fine-tuning bash finetune/scripts/run_sft_Yi_6b.sh Once finished, you can compare the finetuned model and the base model with the following command: bash finetune/scripts/run_eval.sh For advanced usage (like fine-tuning based on your custom data), see the explanations below. Finetune code for Yi 6B and 34B Preparation From Image By default, we use a small dataset from BAAI/COIG to finetune the base model. You can also prepare your customized dataset in the following jsonl format: { "prompt": "Human: Who are you? Assistant:", "chosen": "I'm Yi." } And then mount them in the container to replace the default ones: docker run -it \ -v /path/to/save/finetuned/model/:/finetuned-model \ -v /path/to/train.jsonl:/yi/finetune/data/train.json \ -v /path/to/eval.jsonl:/yi/finetune/data/eval.json \ ghcr.io/01-ai/yi:latest \ bash finetune/scripts/run_sft_Yi_6b.sh From Local Server Make sure you have conda. If not, use mkdir -p ~/miniconda3 wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O ~/miniconda3/miniconda.sh bash /miniconda3/miniconda.sh -b -u -p /miniconda3 rm -rf ~/miniconda3/miniconda.sh ~/miniconda3/bin/conda init bash source ~/.bashrc Then, create a conda env: conda create -n dev_env python=3.10 -y conda activate dev_env pip install torch==2.0.1 deepspeed==0.10 tensorboard transformers datasets sentencepiece accelerate ray==2.7 Hardware Setup For the Yi-6B model, a node with 4 GPUs, each with GPU memory larger than 60GB, is recommended. For the Yi-34B model, because the usage of the zero-offload technique consumes a lot of CPU memory, please be careful to limit the number of GPUs in the 34B finetune training. Please use CUDA\_VISIBLE\_DEVICES to limit the number of GPUs (as shown in scripts/run\_sft\_Yi\_34b.sh). A typical hardware setup for finetuning the 34B model is a node with 8 GPUs (limited to 4 in running by CUDA\_VISIBLE\_DEVICES=0,1,2,3), each with GPU memory larger than 80GB, and total CPU memory larger than 900GB. Quick Start Download a LLM-base model to MODEL\_PATH (6B and 34B). A typical folder of models is like: |-- $MODEL_PATH | |-- config.json | |-- pytorch_model-00001-of-00002.bin | |-- pytorch_model-00002-of-00002.bin | |-- pytorch_model.bin.index.json | |-- tokenizer_config.json | |-- tokenizer.model | |-- ... Download a dataset from huggingface to local storage DATA\_PATH, e.g. Dahoas/rm-static. |-- $DATA_PATH | |-- data | | |-- train-00000-of-00001-2a1df75c6bce91ab.parquet | | |-- test-00000-of-00001-8c7c51afc6d45980.parquet | |-- dataset_infos.json | |-- README.md finetune/yi_example_dataset has example datasets, which are modified from BAAI/COIG |-- $DATA_PATH |--data |-- train.jsonl |-- eval.jsonl cd into the scripts folder, copy and paste the script, and run. For example: cd finetune/scripts bash run_sft_Yi_6b.sh For the Yi-6B base model, setting training\_debug\_steps=20 and num\_train\_epochs=4 can output a chat model, which takes about 20 minutes. For the Yi-34B base model, it takes a relatively long time for initialization. Please be patient. Evaluation cd finetune/scripts bash run_eval.sh Then you'll see the answer from both the base model and the finetuned model. \ [Back to top \] Quantization GPT-Q python quantization/gptq/quant_autogptq.py \ --model /base_model \ --output_dir /quantized_model \ --trust_remote_code Once finished, you can then evaluate the resulting model as follows: python quantization/gptq/eval_quantized_model.py \ --model /quantized_model \ --trust_remote_code For details, see the explanations below. GPT-Q quantization GPT-Q is a PTQ (Post-Training Quantization) method. It saves memory and provides potential speedups while retaining the accuracy of the model. Yi models can be GPT-Q quantized without a lot of efforts. We provide a step-by-step tutorial below. To run GPT-Q, we will use AutoGPTQ and exllama. And the huggingface transformers has integrated optimum and auto-gptq to perform GPTQ quantization on language models. Do Quantization The quant_autogptq.py script is provided for you to perform GPT-Q quantization: python quant_autogptq.py --model /base_model \ --output_dir /quantized_model --bits 4 --group_size 128 --trust_remote_code Run Quantized Model You can run a quantized model using the eval_quantized_model.py: python eval_quantized_model.py --model /quantized_model --trust_remote_code AWQ python quantization/awq/quant_autoawq.py \ --model /base_model \ --output_dir /quantized_model \ --trust_remote_code Once finished, you can then evaluate the resulting model as follows: python quantization/awq/eval_quantized_model.py \ --model /quantized_model \ --trust_remote_code For details, see the explanations below. AWQ quantization AWQ is a PTQ (Post-Training Quantization) method. It's an efficient and accurate low-bit weight quantization (INT3/4) for LLMs. Yi models can be AWQ quantized without a lot of efforts. We provide a step-by-step tutorial below. To run AWQ, we will use AutoAWQ. Do Quantization The quant_autoawq.py script is provided for you to perform AWQ quantization: python quant_autoawq.py --model /base_model \ --output_dir /quantized_model --bits 4 --group_size 128 --trust_remote_code Run Quantized Model You can run a quantized model using the eval_quantized_model.py: python eval_quantized_model.py --model /quantized_model --trust_remote_code \ [Back to top \] Deployment If you want to deploy Yi models, make sure you meet the software and hardware requirements. Software requirements Before using Yi quantized models, make sure you've installed the correct software listed below. Model Software Yi 4-bit quantized models AWQ and CUDA Yi 8-bit quantized models GPTQ and CUDA Hardware requirements Before deploying Yi in your environment, make sure your hardware meets the following requirements. Chat models Model Minimum VRAM Recommended GPU Example Yi-6B-Chat 15 GB 1 x RTX 3090 (24 GB) 1 x RTX 4090 (24 GB) 1 x A10 (24 GB) 1 x A30 (24 GB) Yi-6B-Chat-4bits 4 GB 1 x RTX 3060 (12 GB) 1 x RTX 4060 (8 GB) Yi-6B-Chat-8bits 8 GB 1 x RTX 3070 (8 GB) 1 x RTX 4060 (8 GB) Yi-34B-Chat 72 GB 4 x RTX 4090 (24 GB) 1 x A800 (80GB) Yi-34B-Chat-4bits 20 GB 1 x RTX 3090 (24 GB) 1 x RTX 4090 (24 GB) 1 x A10 (24 GB) 1 x A30 (24 GB) 1 x A100 (40 GB) Yi-34B-Chat-8bits 38 GB 2 x RTX 3090 (24 GB) 2 x RTX 4090 (24 GB) 1 x A800 (40 GB) Below are detailed minimum VRAM requirements under different batch use cases. Model batch=1 batch=4 batch=16 batch=32 Yi-6B-Chat 12 GB 13 GB 15 GB 18 GB Yi-6B-Chat-4bits 4 GB 5 GB 7 GB 10 GB Yi-6B-Chat-8bits 7 GB 8 GB 10 GB 14 GB Yi-34B-Chat 65 GB 68 GB 76 GB \> 80 GB Yi-34B-Chat-4bits 19 GB 20 GB 30 GB 40 GB Yi-34B-Chat-8bits 35 GB 37 GB 46 GB 58 GB Base models Model Minimum VRAM Recommended GPU Example Yi-6B 15 GB 1 x RTX 3090 (24 GB) 1 x RTX 4090 (24 GB) 1 x A10 (24 GB) 1 x A30 (24 GB) Yi-6B-200K 50 GB 1 x A800 (80 GB) Yi-9B 20 GB 1 x RTX 4090 (24 GB) Yi-34B 72 GB 4 x RTX 4090 (24 GB) 1 x A800 (80 GB) Yi-34B-200K 200 GB 4 x A800 (80 GB) \ [Back to top \] FAQ If you have any questions while using the Yi series models, the answers provided below could serve as a helpful reference for you. Fine-tuning Base model or Chat model - which to fine-tune?** The choice of pre-trained language model for fine-tuning hinges on the computational resources you have at your disposal and the particular demands of your task. If you are working with a substantial volume of fine-tuning data (say, over 10,000 samples), the Base model could be your go-to choice. On the other hand, if your fine-tuning data is not quite as extensive, opting for the Chat model might be a more fitting choice. It is generally advisable to fine-tune both the Base and Chat models, compare their performance, and then pick the model that best aligns with your specific requirements. Yi-34B versus Yi-34B-Chat for full-scale fine-tuning - what is the difference?** The key distinction between full-scale fine-tuning on \Yi-34B\and \Yi-34B-Chat\ comes down to the fine-tuning approach and outcomes. - Yi-34B-Chat employs a Special Fine-Tuning (SFT) method, resulting in responses that mirror human conversation style more closely. - The Base model's fine-tuning is more versatile, with a relatively high performance potential. - If you are confident in the quality of your data, fine-tuning with \Yi-34B\ could be your go-to. - If you are aiming for model-generated responses that better mimic human conversational style, or if you have doubts about your data quality, \Yi-34B-Chat\ might be your best bet. Quantization Quantized model versus original model - what is the performance gap?** The performance variance is largely contingent on the quantization method employed and the specific use cases of these models. For instance, when it comes to models provided by the AWQ official, from a Benchmark standpoint, quantization might result in a minor performance drop of a few percentage points. Subjectively speaking, in situations like logical reasoning, even a 1% performance shift could impact the accuracy of the output results. General Where can I source fine-tuning question answering datasets?** You can find fine-tuning question answering datasets on platforms like Hugging Face, with datasets like m-a-p/COIG-CQIA readily available. Additionally, Github offers fine-tuning frameworks, such as hiyouga/LLaMA-Factory, which integrates pre-made datasets. What is the GPU memory requirement for fine-tuning Yi-34B FP16?** The GPU memory needed for fine-tuning 34B FP16 hinges on the specific fine-tuning method employed. For full parameter fine-tuning, you'll need 8 GPUs each with 80 GB; however, more economical solutions like Lora require less. For more details, check out \hiyouga/LLaMA-Factory\. Also, consider using BF16 instead of FP16 for fine-tuning to optimize performance. Are there any third-party platforms that support chat functionality for the Yi-34b-200k model?** If you're looking for third-party Chats, options include \fireworks.ai\. Learning hub If you want to learn Yi, you can find a wealth of helpful educational resources here. Welcome to the Yi learning hub! Whether you're a seasoned developer or a newcomer, you can find a wealth of helpful educational resources to enhance your understanding and skills with Yi models, including insightful blog posts, comprehensive video tutorials, hands-on guides, and more. The content you find here has been generously contributed by knowledgeable Yi experts and passionate enthusiasts. We extend our heartfelt gratitude for your invaluable contributions! At the same time, we also warmly invite you to join our collaborative effort by contributing to Yi. If you have already made contributions to Yi, please don't hesitate to showcase your remarkable work in the table below. With all these resources at your fingertips, you're ready to start your exciting journey with Yi. Happy learning! Tutorials English tutorials Type Deliverable Date Author Video Run dolphin-2.2-yi-34b on IoT Devices 2023-11-30 Second State Blog Running Yi-34B-Chat locally using LlamaEdge 2023-11-30 Second State Video Install Yi 34B Locally - Chinese English Bilingual LLM 2023-11-05 Fahd Mirza Video Dolphin Yi 34b - Brand New Foundational Model TESTED 2023-11-27 Matthew Berman Chinese tutorials Type Deliverable Date Author GitHub project 2024-04-25 Blog yi-vl-plusAnki 2024-04-24 GitHub project yi-34b-chat-200k 2024-04-24 Blog Yi-VL 2024-02-02 Blog 34B Llama.cpp & 21G 2023-11-26 Blog Yi-34B 2023-12-10 Blog CPU 2023-12-12 Blog 3 Yi-6B Agent Llama Factory 2024-01-22 Blog Yi-VL& 2024-01-26 ModelScope Video 24G vllm Yi-34B 2023-12-28 Video Yi-VL-34B - A40 2023-01-28 Why Yi? Ecosystem Upstream Downstream Serving Quantization Fine-tuning API Benchmarks Chat model performance Base model performance Yi-34B and Yi-34B-200K Yi-9B Ecosystem Yi has a comprehensive ecosystem, offering a range of tools, services, and models to enrich your experiences and maximize productivity. Upstream Downstream Serving Quantization Fine-tuning API Upstream The Yi series models follow the same model architecture as Llama. By choosing Yi, you can leverage existing tools, libraries, and resources within the Llama ecosystem, eliminating the need to create new tools and enhancing development efficiency. For example, the Yi series models are saved in the format of the Llama model. You can directly use LlamaForCausalLM and LlamaTokenizer to load the model. For more information, see Use the chat model. from transformers import AutoModelForCausalLM, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("01-ai/Yi-34b", use_fast=False) model = AutoModelForCausalLM.from_pretrained("01-ai/Yi-34b", device_map="auto") \ [Back to top \] Downstream Tip * Feel free to create a PR and share the fantastic work you've built using the Yi series models. * To help others quickly understand your work, it is recommended to use the format of : + . Serving If you want to get up with Yi in a few minutes, you can use the following services built upon Yi. Yi-34B-Chat: you can chat with Yi using one of the following platforms: Yi-34B-Chat | Hugging Face Yi-34B-Chat | Yi Platform: Note that currently it's available through a whitelist. Welcome to apply (fill out a form in English or Chinese) and experience it firsthand! Yi-6B-Chat (Replicate): you can use this model with more options by setting additional parameters and calling APIs. ScaleLLM: you can use this service to run Yi models locally with added flexibility and customization. Quantization If you have limited computational capabilities, you can use Yi's quantized models as follows. These quantized models have reduced precision but offer increased efficiency, such as faster inference speed and smaller RAM usage. TheBloke/Yi-34B-GPTQ TheBloke/Yi-34B-GGUF TheBloke/Yi-34B-AWQ Fine-tuning If you're seeking to explore the diverse capabilities within Yi's thriving family, you can delve into Yi's fine-tuned models as below. TheBloke Models: this site hosts numerous fine-tuned models derived from various LLMs including Yi. This is not an exhaustive list for Yi, but to name a few sorted on downloads: TheBloke/dolphin-2\_2-yi-34b-AWQ TheBloke/Yi-34B-Chat-AWQ TheBloke/Yi-34B-Chat-GPTQ SUSTech/SUS-Chat-34B: this model ranked first among all models below 70B and outperformed the twice larger deepseek-llm-67b-chat. You can check the result on the Open LLM Leaderboard. OrionStarAI/OrionStar-Yi-34B-Chat-Llama: this model excelled beyond other models (such as GPT-4, Qwen-14B-Chat, Baichuan2-13B-Chat) in C-Eval and CMMLU evaluations on the OpenCompass LLM Leaderboard. NousResearch/Nous-Capybara-34B: this model is trained with 200K context length and 3 epochs on the Capybara dataset. API amazing-openai-api: this tool converts Yi model APIs into the OpenAI API format out of the box. LlamaEdge: this tool builds an OpenAI-compatible API server for Yi-34B-Chat using a portable Wasm (WebAssembly) file, powered by Rust. \ [Back to top \] Tech report For detailed capabilities of the Yi series model, see Yi: Open Foundation Models by 01.AI. Citation @misc{ai2024yi, title={Yi: Open Foundation Models by 01.AI}, author={01. AI and : and Alex Young and Bei Chen and Chao Li and Chengen Huang and Ge Zhang and Guanwei Zhang and Heng Li and Jiangcheng Zhu and Jianqun Chen and Jing Chang and Kaidong Yu and Peng Liu and Qiang Liu and Shawn Yue and Senbin Yang and Shiming Yang and Tao Yu and Wen Xie and Wenhao Huang and Xiaohui Hu and Xiaoyi Ren and Xinyao Niu and Pengcheng Nie and Yuchi Xu and Yudong Liu and Yue Wang and Yuxuan Cai and Zhenyu Gu and Zhiyuan Liu and Zonghong Dai}, year={2024}, eprint={2403.04652}, archivePrefix={arXiv}, primaryClass={cs.CL} } Benchmarks Chat model performance Base model performance Chat model performance Yi-34B-Chat model demonstrates exceptional performance, ranking first among all existing open-source models in the benchmarks including MMLU, CMMLU, BBH, GSM8k, and more. Chat model performance Evaluation methods and challenges. Evaluation methods**: we evaluated various benchmarks using both zero-shot and few-shot methods, except for TruthfulQA. Zero-shot vs. few-shot**: in chat models, the zero-shot approach is more commonly employed. Evaluation strategy**: our evaluation strategy involves generating responses while following instructions explicitly or implicitly (such as using few-shot examples). We then isolate relevant answers from the generated text. Challenges faced**: some models are not well-suited to produce output in the specific format required by instructions in few datasets, which leads to suboptimal results. \*: C-Eval results are evaluated on the validation datasets Base model performance Yi-34B and Yi-34B-200K The Yi-34B and Yi-34B-200K models stand out as the top performers among open-source models, especially excelling in MMLU, CMMLU, common-sense reasoning, reading comprehension, and more. Base model performance Evaluation methods. Disparity in results**: while benchmarking open-source models, a disparity has been noted between results from our pipeline and those reported by public sources like OpenCompass. Investigation findings**: a deeper investigation reveals that variations in prompts, post-processing strategies, and sampling techniques across models may lead to significant outcome differences. Uniform benchmarking process**: our methodology aligns with the original benchmarksconsistent prompts and post-processing strategies are used, and greedy decoding is applied during evaluations without any post-processing for the generated content. Efforts to retrieve unreported scores**: for scores that were not reported by the original authors (including scores reported with different settings), we try to get results with our pipeline. Extensive model evaluation**: to evaluate the models capability extensively, we adopted the methodology outlined in Llama2. Specifically, we included PIQA, SIQA, HellaSwag, WinoGrande, ARC, OBQA, and CSQA to assess common sense reasoning. SquAD, QuAC, and BoolQ were incorporated to evaluate reading comprehension. Special configurations**: CSQA was exclusively tested using a 7-shot setup, while all other tests were conducted with a 0-shot configuration. Additionally, we introduced GSM8K (8-shot@1), MATH (4-shot@1), HumanEval (0-shot@1), and MBPP (3-shot@1) under the category "Math & Code". Falcon-180B caveat**: Falcon-180B was not tested on QuAC and OBQA due to technical constraints. Its performance score is an average from other tasks, and considering the generally lower scores of these two tasks, Falcon-180B's capabilities are likely not underestimated. Yi-9B Yi-9B is almost the best among a range of similar-sized open-source models (including Mistral-7B, SOLAR-10.7B, Gemma-7B, DeepSeek-Coder-7B-Base-v1.5 and more), particularly excelling in code, math, common-sense reasoning, and reading comprehension. Yi-9B benchmark - details In terms of overall ability (Mean-All), Yi-9B performs the best among similarly sized open-source models, surpassing DeepSeek-Coder, DeepSeek-Math, Mistral-7B, SOLAR-10.7B, and Gemma-7B. Yi-9B benchmark - overall In terms of coding ability (Mean-Code), Yi-9B's performance is second only to DeepSeek-Coder-7B, surpassing Yi-34B, SOLAR-10.7B, Mistral-7B, and Gemma-7B. Yi-9B benchmark - code In terms of math ability (Mean-Math), Yi-9B's performance is second only to DeepSeek-Math-7B, surpassing SOLAR-10.7B, Mistral-7B, and Gemma-7B. Yi-9B benchmark - math In terms of common sense and reasoning ability (Mean-Text), Yi-9B's performance is on par with Mistral-7B, SOLAR-10.7B, and Gemma-7B. Yi-9B benchmark - text \ [Back to top \] Who can use Yi? Everyone! The Yi series models are free for personal usage, academic purposes, and commercial use. All usage must adhere to the Yi Series Models Community License Agreement 2.1 For free commercial use, you only need to complete this form to get a Yi Model Commercial License. \ [Back to top \] Misc. Acknowledgments A heartfelt thank you to each of you who have made contributions to the Yi community! You have helped Yi not just a project, but a vibrant, growing home for innovation. yi contributors \ [Back to top \] Disclaimer We use data compliance checking algorithms during the training process, to ensure the compliance of the trained model to the best of our ability. Due to complex data and the diversity of language model usage scenarios, we cannot guarantee that the model will generate correct, and reasonable output in all scenarios. Please be aware that there is still a risk of the model producing problematic outputs. We will not be responsible for any risks and issues resulting from misuse, misguidance, illegal usage, and related misinformation, as well as any associated data security concerns. \ [Back to top \] License The source code in this repo is licensed under the Apache 2.0 license. The Yi series models are fully open for academic research and free for commercial use, with automatic permission granted upon application. All usage must adhere to the Yi Series Models Community License Agreement 2.1. For free commercial use, you only need to send an email to get official commercial permission. \ [Back to top \]
Updated 5/28/2024
📊
Yi-34B-200K
306
specify theme context for images Building the Next Generation of Open-Source and Bilingual LLMs Hugging Face ModelScope WiseModel Ask questions or discuss ideas on GitHub Join us on Discord or WeChat Check out Yi Tech Report Grow at Yi Learning Hub Table of Contents What is Yi? Introduction Models Chat models Base models Model info News How to use Yi? Quick start Choose your path pip docker llama.cpp conda-lock Web demo Fine-tuning Quantization Deployment FAQ Learning hub Why Yi? Ecosystem Upstream Downstream Serving Quantization Fine-tuning API Benchmarks Base model performance Chat model performance Tech report Citation Who can use Yi? Misc. Acknowledgements Disclaimer License What is Yi? Introduction The Yi series models are the next generation of open-source large language models trained from scratch by 01.AI. Targeted as a bilingual language model and trained on 3T multilingual corpus, the Yi series models become one of the strongest LLM worldwide, showing promise in language understanding, commonsense reasoning, reading comprehension, and more. For example, Yi-34B-Chat model landed in second place (following GPT-4 Turbo), outperforming other LLMs (such as GPT-4, Mixtral, Claude) on the AlpacaEval Leaderboard (based on data available up to January 2024). Yi-34B model ranked first among all existing open-source models (such as Falcon-180B, Llama-70B, Claude) in both English and Chinese on various benchmarks, including Hugging Face Open LLM Leaderboard (pre-trained) and C-Eval (based on data available up to November 2023). (Credits to Llama) Thanks to the Transformer and Llama open-source communities, as they reduce the efforts required to build from scratch and enable the utilization of the same tools within the AI ecosystem. If you're interested in Yi's adoption of Llama architecture and license usage policy, see Yi's relation with Llama. > TL;DR > > The Yi series models adopt the same model architecture as Llama but are NOT derivatives of Llama. Both Yi and Llama are based on the Transformer structure, which has been the standard architecture for large language models since 2018. Grounded in the Transformer architecture, Llama has become a new cornerstone for the majority of state-of-the-art open-source models due to its excellent stability, reliable convergence, and robust compatibility. This positions Llama as the recognized foundational framework for models including Yi. Thanks to the Transformer and Llama architectures, other models can leverage their power, reducing the effort required to build from scratch and enabling the utilization of the same tools within their ecosystems. However, the Yi series models are NOT derivatives of Llama, as they do not use Llama's weights. As Llama's structure is employed by the majority of open-source models, the key factors of determining model performance are training datasets, training pipelines, and training infrastructure. Developing in a unique and proprietary way, Yi has independently created its own high-quality training datasets, efficient training pipelines, and robust training infrastructure entirely from the ground up. This effort has led to excellent performance with Yi series models ranking just behind GPT4 and surpassing Llama on the Alpaca Leaderboard in Dec 2023. \ [Back to top \] News 2024-03-16: The Yi-9B-200K is open-sourced and available to the public. 2024-03-08: Yi Tech Report is published! 2024-03-07: The long text capability of the Yi-34B-200K has been enhanced. In the "Needle-in-a-Haystack" test, the Yi-34B-200K's performance is improved by 10.5%, rising from 89.3% to an impressive 99.8%. We continue to pre-train the model on 5B tokens long-context data mixture and demonstrate a near-all-green performance. 2024-03-06: The Yi-9B is open-sourced and available to the public. Yi-9B stands out as the top performer among a range of similar-sized open-source models (including Mistral-7B, SOLAR-10.7B, Gemma-7B, DeepSeek-Coder-7B-Base-v1.5 and more), particularly excelling in code, math, common-sense reasoning, and reading comprehension. 2024-01-23: The Yi-VL models, Yi-VL-34B and Yi-VL-6B, are open-sourced and available to the public. Yi-VL-34B has ranked first among all existing open-source models in the latest benchmarks, including MMMU and CMMMU (based on data available up to January 2024). 2023-11-23: Chat models are open-sourced and available to the public. This release contains two chat models based on previously released base models, two 8-bit models quantized by GPTQ, and two 4-bit models quantized by AWQ. Yi-34B-Chat Yi-34B-Chat-4bits Yi-34B-Chat-8bits Yi-6B-Chat Yi-6B-Chat-4bits Yi-6B-Chat-8bits You can try some of them interactively at: Hugging Face Replicate 2023-11-23: The Yi Series Models Community License Agreement is updated to v2.1. 2023-11-08: Invited test of Yi-34B chat model. Application form: English Chinese 2023-11-05: The base models, Yi-6B-200K and Yi-34B-200K, are open-sourced and available to the public. This release contains two base models with the same parameter sizes as the previous release, except that the context window is extended to 200K. 2023-11-02: The base models, Yi-6B and Yi-34B, are open-sourced and available to the public. The first public release contains two bilingual (English/Chinese) base models with the parameter sizes of 6B and 34B. Both of them are trained with 4K sequence length and can be extended to 32K during inference time. \ [Back to top \] Models Yi models come in multiple sizes and cater to different use cases. You can also fine-tune Yi models to meet your specific requirements. If you want to deploy Yi models, make sure you meet the software and hardware requirements. Chat models Model Download Yi-34B-Chat Hugging Face ModelScope Yi-34B-Chat-4bits Hugging Face ModelScope Yi-34B-Chat-8bits Hugging Face ModelScope Yi-6B-Chat Hugging Face ModelScope Yi-6B-Chat-4bits Hugging Face ModelScope Yi-6B-Chat-8bits Hugging Face ModelScope \- 4-bit series models are quantized by AWQ. \- 8-bit series models are quantized by GPTQ \- All quantized models have a low barrier to use since they can be deployed on consumer-grade GPUs (e.g., 3090, 4090). Base models Model Download Yi-34B Hugging Face ModelScope Yi-34B-200K Hugging Face ModelScope Yi-9B Hugging Face ModelScope Yi-9B-200K Hugging Face ModelScope Yi-6B Hugging Face ModelScope Yi-6B-200K Hugging Face ModelScope \- 200k is roughly equivalent to 400,000 Chinese characters. \- If you want to use the previous version of the Yi-34B-200K (released on Nov 5, 2023), run git checkout 069cd341d60f4ce4b07ec394e82b79e94f656cf to download the weight. Model info For chat and base models Model Intro Default context window Pretrained tokens Training Data Date 6B series models They are suitable for personal and academic use. 4K 3T Up to June 2023 9B series models It is the best at coding and math in the Yi series models. Yi-9B is continuously trained based on Yi-6B, using 0.8T tokens. 34B series models They are suitable for personal, academic, and commercial (particularly for small and medium-sized enterprises) purposes. It's a cost-effective solution that's affordable and equipped with emergent ability. 3T For chat models For chat model limitations, see the explanations below. The released chat model has undergone exclusive training using Supervised Fine-Tuning (SFT). Compared to other standard chat models, our model produces more diverse responses, making it suitable for various downstream tasks, such as creative scenarios. Furthermore, this diversity is expected to enhance the likelihood of generating higher quality responses, which will be advantageous for subsequent Reinforcement Learning (RL) training. However, this higher diversity might amplify certain existing issues, including: Hallucination: This refers to the model generating factually incorrect or nonsensical information. With the model's responses being more varied, there's a higher chance of hallucination that are not based on accurate data or logical reasoning. Non-determinism in re-generation: When attempting to regenerate or sample responses, inconsistencies in the outcomes may occur. The increased diversity can lead to varying results even under similar input conditions. Cumulative Error: This occurs when errors in the model's responses compound over time. As the model generates more diverse responses, the likelihood of small inaccuracies building up into larger errors increases, especially in complex tasks like extended reasoning, mathematical problem-solving, etc. To achieve more coherent and consistent responses, it is advisable to adjust generation configuration parameters such as temperature, top\_p, or top\_k. These adjustments can help in the balance between creativity and coherence in the model's outputs. \ [Back to top \] How to use Yi? Quick start Choose your path pip docker conda-lock llama.cpp Web demo Fine-tuning Quantization Deployment FAQ Learning hub Quick start Getting up and running with Yi models is simple with multiple choices available. Choose your path Select one of the following paths to begin your journey with Yi! Quick start - Choose your path Deploy Yi locally If you prefer to deploy Yi models locally, and you have sufficient resources (for example, NVIDIA A800 80GB), you can choose one of the following methods: pip Docker conda-lock and you have limited resources (for example, a MacBook Pro), you can use llama.cpp. Not to deploy Yi locally If you prefer not to deploy Yi models locally, you can explore Yi's capabilities using any of the following options. Run Yi with APIs If you want to explore more features of Yi, you can adopt one of these methods: Yi APIs (Yi official) Early access has been granted to some applicants. Stay tuned for the next round of access! Yi APIs (Replicate) Run Yi in playground If you want to chat with Yi with more customizable options (e.g., system prompt, temperature, repetition penalty, etc.), you can try one of the following options: Yi-34B-Chat-Playground (Yi official) Access is available through a whitelist. Welcome to apply (fill out a form in English or Chinese). Yi-34B-Chat-Playground (Replicate) Chat with Yi If you want to chat with Yi, you can use one of these online services, which offer a similar user experience: Yi-34B-Chat (Yi official on Hugging Face) No registration is required. Yi-34B-Chat (Yi official beta) Access is available through a whitelist. Welcome to apply (fill out a form in English or Chinese). \ [Back to top \] Quick start - pip This tutorial guides you through every step of running Yi-34B-Chat locally on an A800 (80G) and then performing inference. Step 0: Prerequisites Make sure Python 3.10 or a later version is installed. If you want to run other Yi models, see software and hardware requirements. Step 1: Prepare your environment To set up the environment and install the required packages, execute the following command. git clone https://github.com/01-ai/Yi.git cd yi pip install -r requirements.txt Step 2: Download the Yi model You can download the weights and tokenizer of Yi models from the following sources: Hugging Face ModelScope WiseModel Step 3: Perform inference You can perform inference with Yi chat or base models as below. Perform inference with Yi chat model Create a file named quick_start.py and copy the following content to it. from transformers import AutoModelForCausalLM, AutoTokenizer model_path = '' tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False) Since transformers 4.35.0, the GPT-Q/AWQ model can be loaded using AutoModelForCausalLM. model = AutoModelForCausalLM.from_pretrained( model_path, device_map="auto", torch_dtype='auto' ).eval() Prompt content: "hi" messages = [ {"role": "user", "content": "hi"} ] input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt') output_ids = model.generate(input_ids.to('cuda')) response = tokenizer.decode(output_ids0:], skip_special_tokens=True) Model response: "Hello! How can I assist you today?" print(response) Run quick_start.py. python quick_start.py Then you can see an output similar to the one below. Hello! How can I assist you today? Perform inference with Yi base model Yi-34B The steps are similar to pip - Perform inference with Yi chat model. You can use the existing file text_generation.py. python demo/text_generation.py --model Then you can see an output similar to the one below. Output. Prompt: Let me tell you an interesting story about cat Tom and mouse Jerry, Generation: Let me tell you an interesting story about cat Tom and mouse Jerry, which happened in my childhood. My father had a big house with two cats living inside it to kill mice. One day when I was playing at home alone, I found one of the tomcats lying on his back near our kitchen door, looking very much like he wanted something from us but couldnt get up because there were too many people around him! He kept trying for several minutes before finally giving up... Yi-9B Input from transformers import AutoModelForCausalLM, AutoTokenizer MODEL_DIR = "01-ai/Yi-9B" model = AutoModelForCausalLM.from_pretrained(MODEL_DIR, torch_dtype="auto") tokenizer = AutoTokenizer.from_pretrained(MODEL_DIR, use_fast=False) input_text = "# write the quick sort algorithm" inputs = tokenizer(input_text, return_tensors="pt").to(model.device) outputs = model.generate(**inputs, max_length=256) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) Output \\\`bash write the quick sort algorithm def quick\_sort(arr): if len(arr) pivot\] return quick\_sort(left) + middle + quick\_sort(right) test the quick sort algorithm print(quick\_sort(\[3, 6, 8, 10, 1, 2, 1\])) [ Back to top ] Quick start - Docker Run Yi-34B-chat locally with Docker: a step-by-step guide. This tutorial guides you through every step of running Yi-34B-Chat on an A800 GPU or 4*4090 locally and then performing inference. Step 0: Prerequisites Make sure you've installed Docker and nvidia-container-toolkit. Step 1: Start Docker docker run -it --gpus all \ -v <your-model-path>: /models ghcr.io/01-ai/yi:latest Alternatively, you can pull the Yi Docker image from registry.lingyiwanwu.com/ci/01-ai/yi:latest. Step 2: Perform inference You can perform inference with Yi chat or base models as below. Perform inference with Yi chat model The steps are similar to pip - Perform inference with Yi chat model. Note that the only difference is to set model_path = '<your-model-mount-path>' instead of model_path = '<your-model-path>'. Perform inference with Yi base model The steps are similar to pip - Perform inference with Yi base model. Note that the only difference is to set --model <your-model-mount-path>' instead of model <your-model-path>. Quick start - conda-lock You can use conda-lock to generate fully reproducible lock files for conda environments. You can refer to conda-lock.yml for the exact versions of the dependencies. Additionally, you can utilize micromamba for installing these dependencies. To install the dependencies, follow these steps: Install micromamba by following the instructions available here. Execute micromamba install -y -n yi -f conda-lock.yml to create a conda environment named yi and install the necessary dependencies. Quick start - llama.cpp The following tutorial will guide you through every step of running a quantized model (Yi-chat-6B-2bits) locally and then performing inference. Run Yi-chat-6B-2bits locally with llama.cpp: a step-by-step guide. This tutorial guides you through every step of running a quantized model (Yi-chat-6B-2bits) locally and then performing inference. Step 0: Prerequisites Step 1: Download llama.cpp Step 2: Download Yi model Step 3: Perform inference Step 0: Prerequisites This tutorial assumes you use a MacBook Pro with 16GB of memory and an Apple M2 Pro chip. Make sure git-lfs is installed on your machine. Step 1: Download llama.cpp To clone the llama.cpp repository, run the following command. git clone [email protected]:ggerganov/llama.cpp.git Step 2: Download Yi model 2.1 To clone XeIaso/yi-chat-6B-GGUF with just pointers, run the following command. GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/XeIaso/yi-chat-6B-GGUF 2.2 To download a quantized Yi model (yi-chat-6b.Q2\_K.gguf), run the following command. git-lfs pull --include yi-chat-6b.Q2_K.gguf Step 3: Perform inference To perform inference with the Yi model, you can use one of the following methods. Method 1: Perform inference in terminal Method 2: Perform inference in web Method 1: Perform inference in terminal To compile llama.cpp using 4 threads and then conduct inference, navigate to the llama.cpp directory, and run the following command. Tips * Replace /Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.gguf with the actual path of your model. * By default, the model operates in completion mode. * For additional output customization options (for example, system prompt, temperature, repetition penalty, etc.), run ./main -h to check detailed descriptions and usage. make -j4 && ./main -m /Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.gguf -p "How do you feed your pet fox? Please answer this question in 6 simple steps:\nStep 1:" -n 384 -e ... How do you feed your pet fox? Please answer this question in 6 simple steps: Step 1: Select the appropriate food for your pet fox. You should choose high-quality, balanced prey items that are suitable for their unique dietary needs. These could include live or frozen mice, rats, pigeons, or other small mammals, as well as fresh fruits and vegetables. Step 2: Feed your pet fox once or twice a day, depending on the species and its individual preferences. Always ensure that they have access to fresh water throughout the day. Step 3: Provide an appropriate environment for your pet fox. Ensure it has a comfortable place to rest, plenty of space to move around, and opportunities to play and exercise. Step 4: Socialize your pet with other animals if possible. Interactions with other creatures can help them develop social skills and prevent boredom or stress. Step 5: Regularly check for signs of illness or discomfort in your fox. Be prepared to provide veterinary care as needed, especially for common issues such as parasites, dental health problems, or infections. Step 6: Educate yourself about the needs of your pet fox and be aware of any potential risks or concerns that could affect their well-being. Regularly consult with a veterinarian to ensure you are providing the best care. ... Now you have successfully asked a question to the Yi model and got an answer! Method 2: Perform inference in web To initialize a lightweight and swift chatbot, run the following command. cd llama.cpp ./server --ctx-size 2048 --host 0.0.0.0 --n-gpu-layers 64 --model /Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.gguf Then you can get an output like this: ... llama_new_context_with_model: n_ctx = 2048 llama_new_context_with_model: freq_base = 5000000.0 llama_new_context_with_model: freq_scale = 1 ggml_metal_init: allocating ggml_metal_init: found device: Apple M2 Pro ggml_metal_init: picking default device: Apple M2 Pro ggml_metal_init: ggml.metallib not found, loading from source ggml_metal_init: GGML_METAL_PATH_RESOURCES = nil ggml_metal_init: loading '/Users/yu/llama.cpp/ggml-metal.metal' ggml_metal_init: GPU name: Apple M2 Pro ggml_metal_init: GPU family: MTLGPUFamilyApple8 (1008) ggml_metal_init: hasUnifiedMemory = true ggml_metal_init: recommendedMaxWorkingSetSize = 11453.25 MB ggml_metal_init: maxTransferRate = built-in GPU ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 128.00 MiB, ( 2629.44 / 10922.67) llama_new_context_with_model: KV self size = 128.00 MiB, K (f16): 64.00 MiB, V (f16): 64.00 MiB ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 0.02 MiB, ( 2629.45 / 10922.67) llama_build_graph: non-view tensors processed: 676/676 llama_new_context_with_model: compute buffer total size = 159.19 MiB ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 156.02 MiB, ( 2785.45 / 10922.67) Available slots: -> Slot 0 - max context: 2048 llama server listening at http://0.0.0.0:8080 To access the chatbot interface, open your web browser and enter http://0.0.0.0:8080 into the address bar. Yi model chatbot interface - llama.cpp Enter a question, such as "How do you feed your pet fox? Please answer this question in 6 simple steps" into the prompt window, and you will receive a corresponding answer. Ask a question to Yi model - llama.cpp \ [Back to top \] Web demo You can build a web UI demo for Yi chat models (note that Yi base models are not supported in this senario). Step 1: Prepare your environment. Step 2: Download the Yi model. Step 3. To start a web service locally, run the following command. python demo/web_demo.py -c You can access the web UI by entering the address provided in the console into your browser. Quick start - web demo \ [Back to top \] Fine-tuning bash finetune/scripts/run_sft_Yi_6b.sh Once finished, you can compare the finetuned model and the base model with the following command: bash finetune/scripts/run_eval.sh For advanced usage (like fine-tuning based on your custom data), see the explanations below. Finetune code for Yi 6B and 34B Preparation From Image By default, we use a small dataset from BAAI/COIG to finetune the base model. You can also prepare your customized dataset in the following jsonl format: { "prompt": "Human: Who are you? Assistant:", "chosen": "I'm Yi." } And then mount them in the container to replace the default ones: docker run -it \ -v /path/to/save/finetuned/model/:/finetuned-model \ -v /path/to/train.jsonl:/yi/finetune/data/train.json \ -v /path/to/eval.jsonl:/yi/finetune/data/eval.json \ ghcr.io/01-ai/yi:latest \ bash finetune/scripts/run_sft_Yi_6b.sh From Local Server Make sure you have conda. If not, use mkdir -p ~/miniconda3 wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O ~/miniconda3/miniconda.sh bash /miniconda3/miniconda.sh -b -u -p /miniconda3 rm -rf ~/miniconda3/miniconda.sh ~/miniconda3/bin/conda init bash source ~/.bashrc Then, create a conda env: conda create -n dev_env python=3.10 -y conda activate dev_env pip install torch==2.0.1 deepspeed==0.10 tensorboard transformers datasets sentencepiece accelerate ray==2.7 Hardware Setup For the Yi-6B model, a node with 4 GPUs, each with GPU memory larger than 60GB, is recommended. For the Yi-34B model, because the usage of the zero-offload technique consumes a lot of CPU memory, please be careful to limit the number of GPUs in the 34B finetune training. Please use CUDA\_VISIBLE\_DEVICES to limit the number of GPUs (as shown in scripts/run\_sft\_Yi\_34b.sh). A typical hardware setup for finetuning the 34B model is a node with 8 GPUs (limited to 4 in running by CUDA\_VISIBLE\_DEVICES=0,1,2,3), each with GPU memory larger than 80GB, and total CPU memory larger than 900GB. Quick Start Download a LLM-base model to MODEL\_PATH (6B and 34B). A typical folder of models is like: |-- $MODEL_PATH | |-- config.json | |-- pytorch_model-00001-of-00002.bin | |-- pytorch_model-00002-of-00002.bin | |-- pytorch_model.bin.index.json | |-- tokenizer_config.json | |-- tokenizer.model | |-- ... Download a dataset from huggingface to local storage DATA\_PATH, e.g. Dahoas/rm-static. |-- $DATA_PATH | |-- data | | |-- train-00000-of-00001-2a1df75c6bce91ab.parquet | | |-- test-00000-of-00001-8c7c51afc6d45980.parquet | |-- dataset_infos.json | |-- README.md finetune/yi_example_dataset has example datasets, which are modified from BAAI/COIG |-- $DATA_PATH |--data |-- train.jsonl |-- eval.jsonl cd into the scripts folder, copy and paste the script, and run. For example: cd finetune/scripts bash run_sft_Yi_6b.sh For the Yi-6B base model, setting training\_debug\_steps=20 and num\_train\_epochs=4 can output a chat model, which takes about 20 minutes. For the Yi-34B base model, it takes a relatively long time for initialization. Please be patient. Evaluation cd finetune/scripts bash run_eval.sh Then you'll see the answer from both the base model and the finetuned model. \ [Back to top \] Quantization GPT-Q python quantization/gptq/quant_autogptq.py \ --model /base_model \ --output_dir /quantized_model \ --trust_remote_code Once finished, you can then evaluate the resulting model as follows: python quantization/gptq/eval_quantized_model.py \ --model /quantized_model \ --trust_remote_code For details, see the explanations below. GPT-Q quantization GPT-Q is a PTQ (Post-Training Quantization) method. It saves memory and provides potential speedups while retaining the accuracy of the model. Yi models can be GPT-Q quantized without a lot of efforts. We provide a step-by-step tutorial below. To run GPT-Q, we will use AutoGPTQ and exllama. And the huggingface transformers has integrated optimum and auto-gptq to perform GPTQ quantization on language models. Do Quantization The quant_autogptq.py script is provided for you to perform GPT-Q quantization: python quant_autogptq.py --model /base_model \ --output_dir /quantized_model --bits 4 --group_size 128 --trust_remote_code Run Quantized Model You can run a quantized model using the eval_quantized_model.py: python eval_quantized_model.py --model /quantized_model --trust_remote_code AWQ python quantization/awq/quant_autoawq.py \ --model /base_model \ --output_dir /quantized_model \ --trust_remote_code Once finished, you can then evaluate the resulting model as follows: python quantization/awq/eval_quantized_model.py \ --model /quantized_model \ --trust_remote_code For details, see the explanations below. AWQ quantization AWQ is a PTQ (Post-Training Quantization) method. It's an efficient and accurate low-bit weight quantization (INT3/4) for LLMs. Yi models can be AWQ quantized without a lot of efforts. We provide a step-by-step tutorial below. To run AWQ, we will use AutoAWQ. Do Quantization The quant_autoawq.py script is provided for you to perform AWQ quantization: python quant_autoawq.py --model /base_model \ --output_dir /quantized_model --bits 4 --group_size 128 --trust_remote_code Run Quantized Model You can run a quantized model using the eval_quantized_model.py: python eval_quantized_model.py --model /quantized_model --trust_remote_code \ [Back to top \] Deployment If you want to deploy Yi models, make sure you meet the software and hardware requirements. Software requirements Before using Yi quantized models, make sure you've installed the correct software listed below. Model Software Yi 4-bit quantized models AWQ and CUDA Yi 8-bit quantized models GPTQ and CUDA Hardware requirements Before deploying Yi in your environment, make sure your hardware meets the following requirements. Chat models Model Minimum VRAM Recommended GPU Example Yi-6B-Chat 15 GB 1 x RTX 3090 (24 GB) 1 x RTX 4090 (24 GB) 1 x A10 (24 GB) 1 x A30 (24 GB) Yi-6B-Chat-4bits 4 GB 1 x RTX 3060 (12 GB) 1 x RTX 4060 (8 GB) Yi-6B-Chat-8bits 8 GB 1 x RTX 3070 (8 GB) 1 x RTX 4060 (8 GB) Yi-34B-Chat 72 GB 4 x RTX 4090 (24 GB) 1 x A800 (80GB) Yi-34B-Chat-4bits 20 GB 1 x RTX 3090 (24 GB) 1 x RTX 4090 (24 GB) 1 x A10 (24 GB) 1 x A30 (24 GB) 1 x A100 (40 GB) Yi-34B-Chat-8bits 38 GB 2 x RTX 3090 (24 GB) 2 x RTX 4090 (24 GB) 1 x A800 (40 GB) Below are detailed minimum VRAM requirements under different batch use cases. Model batch=1 batch=4 batch=16 batch=32 Yi-6B-Chat 12 GB 13 GB 15 GB 18 GB Yi-6B-Chat-4bits 4 GB 5 GB 7 GB 10 GB Yi-6B-Chat-8bits 7 GB 8 GB 10 GB 14 GB Yi-34B-Chat 65 GB 68 GB 76 GB \> 80 GB Yi-34B-Chat-4bits 19 GB 20 GB 30 GB 40 GB Yi-34B-Chat-8bits 35 GB 37 GB 46 GB 58 GB Base models Model Minimum VRAM Recommended GPU Example Yi-6B 15 GB 1 x RTX 3090 (24 GB) 1 x RTX 4090 (24 GB) 1 x A10 (24 GB) 1 x A30 (24 GB) Yi-6B-200K 50 GB 1 x A800 (80 GB) Yi-9B 20 GB 1 x RTX 4090 (24 GB) Yi-34B 72 GB 4 x RTX 4090 (24 GB) 1 x A800 (80 GB) Yi-34B-200K 200 GB 4 x A800 (80 GB) \ [Back to top \] FAQ If you have any questions while using the Yi series models, the answers provided below could serve as a helpful reference for you. Fine-tuning Base model or Chat model - which to fine-tune?** The choice of pre-trained language model for fine-tuning hinges on the computational resources you have at your disposal and the particular demands of your task. If you are working with a substantial volume of fine-tuning data (say, over 10,000 samples), the Base model could be your go-to choice. On the other hand, if your fine-tuning data is not quite as extensive, opting for the Chat model might be a more fitting choice. It is generally advisable to fine-tune both the Base and Chat models, compare their performance, and then pick the model that best aligns with your specific requirements. Yi-34B versus Yi-34B-Chat for full-scale fine-tuning - what is the difference?** The key distinction between full-scale fine-tuning on \Yi-34B\and \Yi-34B-Chat\ comes down to the fine-tuning approach and outcomes. - Yi-34B-Chat employs a Special Fine-Tuning (SFT) method, resulting in responses that mirror human conversation style more closely. - The Base model's fine-tuning is more versatile, with a relatively high performance potential. - If you are confident in the quality of your data, fine-tuning with \Yi-34B\ could be your go-to. - If you are aiming for model-generated responses that better mimic human conversational style, or if you have doubts about your data quality, \Yi-34B-Chat\ might be your best bet. Quantization Quantized model versus original model - what is the performance gap?** The performance variance is largely contingent on the quantization method employed and the specific use cases of these models. For instance, when it comes to models provided by the AWQ official, from a Benchmark standpoint, quantization might result in a minor performance drop of a few percentage points. Subjectively speaking, in situations like logical reasoning, even a 1% performance shift could impact the accuracy of the output results. General Where can I source fine-tuning question answering datasets?** You can find fine-tuning question answering datasets on platforms like Hugging Face, with datasets like m-a-p/COIG-CQIA readily available. Additionally, Github offers fine-tuning frameworks, such as hiyouga/LLaMA-Factory, which integrates pre-made datasets. What is the GPU memory requirement for fine-tuning Yi-34B FP16?** The GPU memory needed for fine-tuning 34B FP16 hinges on the specific fine-tuning method employed. For full parameter fine-tuning, you'll need 8 GPUs each with 80 GB; however, more economical solutions like Lora require less. For more details, check out \hiyouga/LLaMA-Factory\. Also, consider using BF16 instead of FP16 for fine-tuning to optimize performance. Are there any third-party platforms that support chat functionality for the Yi-34b-200k model?** If you're looking for third-party Chats, options include \fireworks.ai\. Learning hub If you want to learn Yi, you can find a wealth of helpful educational resources here. Welcome to the Yi learning hub! Whether you're a seasoned developer or a newcomer, you can find a wealth of helpful educational resources to enhance your understanding and skills with Yi models, including insightful blog posts, comprehensive video tutorials, hands-on guides, and more. The content you find here has been generously contributed by knowledgeable Yi experts and passionate enthusiasts. We extend our heartfelt gratitude for your invaluable contributions! At the same time, we also warmly invite you to join our collaborative effort by contributing to Yi. If you have already made contributions to Yi, please don't hesitate to showcase your remarkable work in the table below. With all these resources at your fingertips, you're ready to start your exciting journey with Yi. Happy learning! Tutorials English tutorials Type Deliverable Date Author Video Run dolphin-2.2-yi-34b on IoT Devices 2023-11-30 Second State Blog Running Yi-34B-Chat locally using LlamaEdge 2023-11-30 Second State Video Install Yi 34B Locally - Chinese English Bilingual LLM 2023-11-05 Fahd Mirza Video Dolphin Yi 34b - Brand New Foundational Model TESTED 2023-11-27 Matthew Berman Chinese tutorials Type Deliverable Date Author GitHub project 2024-04-25 Blog yi-vl-plusAnki 2024-04-24 GitHub project yi-34b-chat-200k 2024-04-24 Blog Yi-VL 2024-02-02 Blog 34B Llama.cpp & 21G 2023-11-26 Blog Yi-34B 2023-12-10 Blog CPU 2023-12-12 Blog 3 Yi-6B Agent Llama Factory 2024-01-22 Blog Yi-VL& 2024-01-26 ModelScope Video 24G vllm Yi-34B 2023-12-28 Video Yi-VL-34B - A40 2023-01-28 Why Yi? Ecosystem Upstream Downstream Serving Quantization Fine-tuning API Benchmarks Chat model performance Base model performance Yi-34B and Yi-34B-200K Yi-9B Ecosystem Yi has a comprehensive ecosystem, offering a range of tools, services, and models to enrich your experiences and maximize productivity. Upstream Downstream Serving Quantization Fine-tuning API Upstream The Yi series models follow the same model architecture as Llama. By choosing Yi, you can leverage existing tools, libraries, and resources within the Llama ecosystem, eliminating the need to create new tools and enhancing development efficiency. For example, the Yi series models are saved in the format of the Llama model. You can directly use LlamaForCausalLM and LlamaTokenizer to load the model. For more information, see Use the chat model. from transformers import AutoModelForCausalLM, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("01-ai/Yi-34b", use_fast=False) model = AutoModelForCausalLM.from_pretrained("01-ai/Yi-34b", device_map="auto") \ [Back to top \] Downstream Tip * Feel free to create a PR and share the fantastic work you've built using the Yi series models. * To help others quickly understand your work, it is recommended to use the format of : + . Serving If you want to get up with Yi in a few minutes, you can use the following services built upon Yi. Yi-34B-Chat: you can chat with Yi using one of the following platforms: Yi-34B-Chat | Hugging Face Yi-34B-Chat | Yi Platform: Note that currently it's available through a whitelist. Welcome to apply (fill out a form in English or Chinese) and experience it firsthand! Yi-6B-Chat (Replicate): you can use this model with more options by setting additional parameters and calling APIs. ScaleLLM: you can use this service to run Yi models locally with added flexibility and customization. Quantization If you have limited computational capabilities, you can use Yi's quantized models as follows. These quantized models have reduced precision but offer increased efficiency, such as faster inference speed and smaller RAM usage. TheBloke/Yi-34B-GPTQ TheBloke/Yi-34B-GGUF TheBloke/Yi-34B-AWQ Fine-tuning If you're seeking to explore the diverse capabilities within Yi's thriving family, you can delve into Yi's fine-tuned models as below. TheBloke Models: this site hosts numerous fine-tuned models derived from various LLMs including Yi. This is not an exhaustive list for Yi, but to name a few sorted on downloads: TheBloke/dolphin-2\_2-yi-34b-AWQ TheBloke/Yi-34B-Chat-AWQ TheBloke/Yi-34B-Chat-GPTQ SUSTech/SUS-Chat-34B: this model ranked first among all models below 70B and outperformed the twice larger deepseek-llm-67b-chat. You can check the result on the Open LLM Leaderboard. OrionStarAI/OrionStar-Yi-34B-Chat-Llama: this model excelled beyond other models (such as GPT-4, Qwen-14B-Chat, Baichuan2-13B-Chat) in C-Eval and CMMLU evaluations on the OpenCompass LLM Leaderboard. NousResearch/Nous-Capybara-34B: this model is trained with 200K context length and 3 epochs on the Capybara dataset. API amazing-openai-api: this tool converts Yi model APIs into the OpenAI API format out of the box. LlamaEdge: this tool builds an OpenAI-compatible API server for Yi-34B-Chat using a portable Wasm (WebAssembly) file, powered by Rust. \ [Back to top \] Tech report For detailed capabilities of the Yi series model, see Yi: Open Foundation Models by 01.AI. Citation @misc{ai2024yi, title={Yi: Open Foundation Models by 01.AI}, author={01. AI and : and Alex Young and Bei Chen and Chao Li and Chengen Huang and Ge Zhang and Guanwei Zhang and Heng Li and Jiangcheng Zhu and Jianqun Chen and Jing Chang and Kaidong Yu and Peng Liu and Qiang Liu and Shawn Yue and Senbin Yang and Shiming Yang and Tao Yu and Wen Xie and Wenhao Huang and Xiaohui Hu and Xiaoyi Ren and Xinyao Niu and Pengcheng Nie and Yuchi Xu and Yudong Liu and Yue Wang and Yuxuan Cai and Zhenyu Gu and Zhiyuan Liu and Zonghong Dai}, year={2024}, eprint={2403.04652}, archivePrefix={arXiv}, primaryClass={cs.CL} } Benchmarks Chat model performance Base model performance Chat model performance Yi-34B-Chat model demonstrates exceptional performance, ranking first among all existing open-source models in the benchmarks including MMLU, CMMLU, BBH, GSM8k, and more. Chat model performance Evaluation methods and challenges. Evaluation methods**: we evaluated various benchmarks using both zero-shot and few-shot methods, except for TruthfulQA. Zero-shot vs. few-shot**: in chat models, the zero-shot approach is more commonly employed. Evaluation strategy**: our evaluation strategy involves generating responses while following instructions explicitly or implicitly (such as using few-shot examples). We then isolate relevant answers from the generated text. Challenges faced**: some models are not well-suited to produce output in the specific format required by instructions in few datasets, which leads to suboptimal results. \*: C-Eval results are evaluated on the validation datasets Base model performance Yi-34B and Yi-34B-200K The Yi-34B and Yi-34B-200K models stand out as the top performers among open-source models, especially excelling in MMLU, CMMLU, common-sense reasoning, reading comprehension, and more. Base model performance Evaluation methods. Disparity in results**: while benchmarking open-source models, a disparity has been noted between results from our pipeline and those reported by public sources like OpenCompass. Investigation findings**: a deeper investigation reveals that variations in prompts, post-processing strategies, and sampling techniques across models may lead to significant outcome differences. Uniform benchmarking process**: our methodology aligns with the original benchmarksconsistent prompts and post-processing strategies are used, and greedy decoding is applied during evaluations without any post-processing for the generated content. Efforts to retrieve unreported scores**: for scores that were not reported by the original authors (including scores reported with different settings), we try to get results with our pipeline. Extensive model evaluation**: to evaluate the models capability extensively, we adopted the methodology outlined in Llama2. Specifically, we included PIQA, SIQA, HellaSwag, WinoGrande, ARC, OBQA, and CSQA to assess common sense reasoning. SquAD, QuAC, and BoolQ were incorporated to evaluate reading comprehension. Special configurations**: CSQA was exclusively tested using a 7-shot setup, while all other tests were conducted with a 0-shot configuration. Additionally, we introduced GSM8K (8-shot@1), MATH (4-shot@1), HumanEval (0-shot@1), and MBPP (3-shot@1) under the category "Math & Code". Falcon-180B caveat**: Falcon-180B was not tested on QuAC and OBQA due to technical constraints. Its performance score is an average from other tasks, and considering the generally lower scores of these two tasks, Falcon-180B's capabilities are likely not underestimated. Yi-9B Yi-9B is almost the best among a range of similar-sized open-source models (including Mistral-7B, SOLAR-10.7B, Gemma-7B, DeepSeek-Coder-7B-Base-v1.5 and more), particularly excelling in code, math, common-sense reasoning, and reading comprehension. Yi-9B benchmark - details In terms of overall ability (Mean-All), Yi-9B performs the best among similarly sized open-source models, surpassing DeepSeek-Coder, DeepSeek-Math, Mistral-7B, SOLAR-10.7B, and Gemma-7B. Yi-9B benchmark - overall In terms of coding ability (Mean-Code), Yi-9B's performance is second only to DeepSeek-Coder-7B, surpassing Yi-34B, SOLAR-10.7B, Mistral-7B, and Gemma-7B. Yi-9B benchmark - code In terms of math ability (Mean-Math), Yi-9B's performance is second only to DeepSeek-Math-7B, surpassing SOLAR-10.7B, Mistral-7B, and Gemma-7B. Yi-9B benchmark - math In terms of common sense and reasoning ability (Mean-Text), Yi-9B's performance is on par with Mistral-7B, SOLAR-10.7B, and Gemma-7B. Yi-9B benchmark - text \ [Back to top \] Who can use Yi? Everyone! The Yi series models are free for personal usage, academic purposes, and commercial use. All usage must adhere to the Yi Series Models Community License Agreement 2.1 For free commercial use, you only need to complete this form to get a Yi Model Commercial License. \ [Back to top \] Misc. Acknowledgments A heartfelt thank you to each of you who have made contributions to the Yi community! You have helped Yi not just a project, but a vibrant, growing home for innovation. yi contributors \ [Back to top \] Disclaimer We use data compliance checking algorithms during the training process, to ensure the compliance of the trained model to the best of our ability. Due to complex data and the diversity of language model usage scenarios, we cannot guarantee that the model will generate correct, and reasonable output in all scenarios. Please be aware that there is still a risk of the model producing problematic outputs. We will not be responsible for any risks and issues resulting from misuse, misguidance, illegal usage, and related misinformation, as well as any associated data security concerns. \ [Back to top \] License The source code in this repo is licensed under the Apache 2.0 license. The Yi series models are fully open for academic research and free for commercial use, with automatic permission granted upon application. All usage must adhere to the Yi Series Models Community License Agreement 2.1. For free commercial use, you only need to send an email to get official commercial permission. \ [Back to top \]
Updated 5/28/2024
yi-34b-chat
253
The yi-34b-chat model is a large language model trained from scratch by developers at 01.AI. The Yi series models are the next generation of open-source large language models that show promise in language understanding, commonsense reasoning, and reading comprehension. For example, the Yi-34B-Chat model landed in second place (following GPT-4 Turbo) on the AlpacaEval Leaderboard, outperforming other LLMs like GPT-4, Mixtral, and Claude. Similar models in the Yi series include the yi-6b and yi-34b models, which are also large language models trained by 01.AI. Other related models include the multilingual-e5-large text embedding model, the nous-hermes-2-yi-34b-gguf fine-tuned Yi-34B model, and the llava-13b visual instruction tuning model. Model Inputs and Outputs The yi-34b-chat model takes in a user prompt as input and generates a corresponding response. The input prompt can be a question, a statement, or any other text that the user wants the model to address. Inputs Prompt**: The text that the user wants the model to respond to. Temperature**: A value that controls the randomness of the model's output. Lower temperatures result in more focused and deterministic responses, while higher temperatures lead to more diverse and creative outputs. Top K**: The number of highest probability tokens to consider for generating the output. If > 0, only the top k tokens with the highest probability are kept (top-k filtering). Top P**: A probability threshold for generating the output. If = top_p are kept (nucleus filtering). Max New Tokens**: The maximum number of tokens the model should generate as output. Prompt Template**: A template used to format the input prompt, with the actual prompt inserted using the {prompt} placeholder. Repetition Penalty**: A value that penalizes the model for repeating the same tokens in the output. Outputs The model generates a response text based on the provided input. The output can be a single sentence, a paragraph, or multiple paragraphs, depending on the complexity of the input prompt. Capabilities The yi-34b-chat model demonstrates impressive capabilities in areas such as language understanding, commonsense reasoning, and reading comprehension. It has been shown to outperform other large language models in various benchmarks, including the AlpacaEval Leaderboard. What Can I Use It For? The yi-34b-chat model can be used for a wide range of applications, including: Conversational AI**: The model can be used to build chatbots and virtual assistants that can engage in natural language conversations. Content Generation**: The model can be used to generate text content, such as articles, stories, or product descriptions. Question Answering**: The model can be used to answer a variety of questions, drawing upon its strong language understanding and reasoning capabilities. Summarization**: The model can be used to summarize long passages of text, capturing the key points and main ideas. Code Generation**: The model can be used to assist developers by generating code snippets or even entire programs based on natural language prompts. Things to Try One interesting aspect of the yi-34b-chat model is its ability to generate diverse and creative responses. By adjusting the temperature and other parameters, you can explore the model's versatility and see how it responds to different types of prompts. You can also try fine-tuning the model on your own dataset to customize its capabilities for your specific use case. Another interesting aspect is the model's strong performance in commonsense reasoning and reading comprehension tasks. You can experiment with prompts that require the model to draw inferences, solve problems, or demonstrate its understanding of complex concepts. Overall, the yi-34b-chat model offers a powerful and flexible platform for exploring the capabilities of large language models and developing innovative applications.
Updated 6/29/2024
🛠️
Yi-VL-34B
243
The Yi-VL-34B model is the open-source, multimodal version of the Yi Large Language Model (LLM) series developed by the team at 01.AI. This model demonstrates exceptional performance, ranking first among all existing open-source models in the latest benchmarks including MMMU in English and CMMMU in Chinese. It is the first open-source 34B vision language model worldwide. The Yi-VL series includes several model versions, such as the Yi-VL-34B and Yi-VL-6B. These models are capable of multi-round text-image conversations, allowing users to engage in visual question answering with a single image. Additionally, the Yi-VL models support bilingual text in both English and Chinese. Model inputs and outputs Inputs Text prompts Images Outputs Text responses based on the provided inputs Capabilities The Yi-VL-34B model can handle multi-round text-image conversations, allowing users to engage in visual question answering with a single image. The model also supports bilingual text in both English and Chinese, making it a versatile tool for cross-language communication. What can I use it for? The Yi-VL-34B model can be used in a variety of applications that require multimodal understanding and generation, such as visual question answering, image captioning, and language-guided image editing. Potential use cases include building interactive chatbots, developing AI-powered virtual assistants, and creating educational or entertainment applications that seamlessly integrate text and visual content. Things to try Experiment with the Yi-VL-34B model's capabilities by engaging in multi-round conversations about images, asking questions about the content, and exploring its ability to understand and respond to both text and visual inputs. Additionally, try using the model's bilingual support to converse with users in different languages and facilitate cross-cultural communication.
Updated 5/28/2024
🚀
Yi-9B
178
specify theme context for images Building the Next Generation of Open-Source and Bilingual LLMs Hugging Face ModelScope WiseModel Ask questions or discuss ideas on GitHub Join us on Discord or WeChat Check out Yi Tech Report Grow at Yi Learning Hub Table of Contents What is Yi? Introduction Models Chat models Base models Model info News How to use Yi? Quick start Choose your path pip docker llama.cpp conda-lock Web demo Fine-tuning Quantization Deployment FAQ Learning hub Why Yi? Ecosystem Upstream Downstream Serving Quantization Fine-tuning API Benchmarks Base model performance Chat model performance Tech report Citation Who can use Yi? Misc. Acknowledgements Disclaimer License What is Yi? Introduction The Yi series models are the next generation of open-source large language models trained from scratch by 01.AI. Targeted as a bilingual language model and trained on 3T multilingual corpus, the Yi series models become one of the strongest LLM worldwide, showing promise in language understanding, commonsense reasoning, reading comprehension, and more. For example, Yi-34B-Chat model landed in second place (following GPT-4 Turbo), outperforming other LLMs (such as GPT-4, Mixtral, Claude) on the AlpacaEval Leaderboard (based on data available up to January 2024). Yi-34B model ranked first among all existing open-source models (such as Falcon-180B, Llama-70B, Claude) in both English and Chinese on various benchmarks, including Hugging Face Open LLM Leaderboard (pre-trained) and C-Eval (based on data available up to November 2023). (Credits to Llama) Thanks to the Transformer and Llama open-source communities, as they reduce the efforts required to build from scratch and enable the utilization of the same tools within the AI ecosystem. If you're interested in Yi's adoption of Llama architecture and license usage policy, see Yi's relation with Llama. > TL;DR > > The Yi series models adopt the same model architecture as Llama but are NOT derivatives of Llama. Both Yi and Llama are based on the Transformer structure, which has been the standard architecture for large language models since 2018. Grounded in the Transformer architecture, Llama has become a new cornerstone for the majority of state-of-the-art open-source models due to its excellent stability, reliable convergence, and robust compatibility. This positions Llama as the recognized foundational framework for models including Yi. Thanks to the Transformer and Llama architectures, other models can leverage their power, reducing the effort required to build from scratch and enabling the utilization of the same tools within their ecosystems. However, the Yi series models are NOT derivatives of Llama, as they do not use Llama's weights. As Llama's structure is employed by the majority of open-source models, the key factors of determining model performance are training datasets, training pipelines, and training infrastructure. Developing in a unique and proprietary way, Yi has independently created its own high-quality training datasets, efficient training pipelines, and robust training infrastructure entirely from the ground up. This effort has led to excellent performance with Yi series models ranking just behind GPT4 and surpassing Llama on the Alpaca Leaderboard in Dec 2023. \ [Back to top \] News 2024-03-16: The Yi-9B-200K is open-sourced and available to the public. 2024-03-08: Yi Tech Report is published! 2024-03-07: The long text capability of the Yi-34B-200K has been enhanced. In the "Needle-in-a-Haystack" test, the Yi-34B-200K's performance is improved by 10.5%, rising from 89.3% to an impressive 99.8%. We continue to pre-train the model on 5B tokens long-context data mixture and demonstrate a near-all-green performance. 2024-03-06: The Yi-9B is open-sourced and available to the public. Yi-9B stands out as the top performer among a range of similar-sized open-source models (including Mistral-7B, SOLAR-10.7B, Gemma-7B, DeepSeek-Coder-7B-Base-v1.5 and more), particularly excelling in code, math, common-sense reasoning, and reading comprehension. 2024-01-23: The Yi-VL models, Yi-VL-34B and Yi-VL-6B, are open-sourced and available to the public. Yi-VL-34B has ranked first among all existing open-source models in the latest benchmarks, including MMMU and CMMMU (based on data available up to January 2024). 2023-11-23: Chat models are open-sourced and available to the public. This release contains two chat models based on previously released base models, two 8-bit models quantized by GPTQ, and two 4-bit models quantized by AWQ. Yi-34B-Chat Yi-34B-Chat-4bits Yi-34B-Chat-8bits Yi-6B-Chat Yi-6B-Chat-4bits Yi-6B-Chat-8bits You can try some of them interactively at: Hugging Face Replicate 2023-11-23: The Yi Series Models Community License Agreement is updated to v2.1. 2023-11-08: Invited test of Yi-34B chat model. Application form: English Chinese 2023-11-05: The base models, Yi-6B-200K and Yi-34B-200K, are open-sourced and available to the public. This release contains two base models with the same parameter sizes as the previous release, except that the context window is extended to 200K. 2023-11-02: The base models, Yi-6B and Yi-34B, are open-sourced and available to the public. The first public release contains two bilingual (English/Chinese) base models with the parameter sizes of 6B and 34B. Both of them are trained with 4K sequence length and can be extended to 32K during inference time. \ [Back to top \] Models Yi models come in multiple sizes and cater to different use cases. You can also fine-tune Yi models to meet your specific requirements. If you want to deploy Yi models, make sure you meet the software and hardware requirements. Chat models Model Download Yi-34B-Chat Hugging Face ModelScope Yi-34B-Chat-4bits Hugging Face ModelScope Yi-34B-Chat-8bits Hugging Face ModelScope Yi-6B-Chat Hugging Face ModelScope Yi-6B-Chat-4bits Hugging Face ModelScope Yi-6B-Chat-8bits Hugging Face ModelScope \- 4-bit series models are quantized by AWQ. \- 8-bit series models are quantized by GPTQ \- All quantized models have a low barrier to use since they can be deployed on consumer-grade GPUs (e.g., 3090, 4090). Base models Model Download Yi-34B Hugging Face ModelScope Yi-34B-200K Hugging Face ModelScope Yi-9B Hugging Face ModelScope Yi-9B-200K Hugging Face ModelScope Yi-6B Hugging Face ModelScope Yi-6B-200K Hugging Face ModelScope \- 200k is roughly equivalent to 400,000 Chinese characters. \- If you want to use the previous version of the Yi-34B-200K (released on Nov 5, 2023), run git checkout 069cd341d60f4ce4b07ec394e82b79e94f656cf to download the weight. Model info For chat and base models Model Intro Default context window Pretrained tokens Training Data Date 6B series models They are suitable for personal and academic use. 4K 3T Up to June 2023 9B series models It is the best at coding and math in the Yi series models. Yi-9B is continuously trained based on Yi-6B, using 0.8T tokens. 34B series models They are suitable for personal, academic, and commercial (particularly for small and medium-sized enterprises) purposes. It's a cost-effective solution that's affordable and equipped with emergent ability. 3T For chat models For chat model limitations, see the explanations below. The released chat model has undergone exclusive training using Supervised Fine-Tuning (SFT). Compared to other standard chat models, our model produces more diverse responses, making it suitable for various downstream tasks, such as creative scenarios. Furthermore, this diversity is expected to enhance the likelihood of generating higher quality responses, which will be advantageous for subsequent Reinforcement Learning (RL) training. However, this higher diversity might amplify certain existing issues, including: Hallucination: This refers to the model generating factually incorrect or nonsensical information. With the model's responses being more varied, there's a higher chance of hallucination that are not based on accurate data or logical reasoning. Non-determinism in re-generation: When attempting to regenerate or sample responses, inconsistencies in the outcomes may occur. The increased diversity can lead to varying results even under similar input conditions. Cumulative Error: This occurs when errors in the model's responses compound over time. As the model generates more diverse responses, the likelihood of small inaccuracies building up into larger errors increases, especially in complex tasks like extended reasoning, mathematical problem-solving, etc. To achieve more coherent and consistent responses, it is advisable to adjust generation configuration parameters such as temperature, top\_p, or top\_k. These adjustments can help in the balance between creativity and coherence in the model's outputs. \ [Back to top \] How to use Yi? Quick start Choose your path pip docker conda-lock llama.cpp Web demo Fine-tuning Quantization Deployment FAQ Learning hub Quick start Getting up and running with Yi models is simple with multiple choices available. Choose your path Select one of the following paths to begin your journey with Yi! Quick start - Choose your path Deploy Yi locally If you prefer to deploy Yi models locally, and you have sufficient resources (for example, NVIDIA A800 80GB), you can choose one of the following methods: pip Docker conda-lock and you have limited resources (for example, a MacBook Pro), you can use llama.cpp. Not to deploy Yi locally If you prefer not to deploy Yi models locally, you can explore Yi's capabilities using any of the following options. Run Yi with APIs If you want to explore more features of Yi, you can adopt one of these methods: Yi APIs (Yi official) Early access has been granted to some applicants. Stay tuned for the next round of access! Yi APIs (Replicate) Run Yi in playground If you want to chat with Yi with more customizable options (e.g., system prompt, temperature, repetition penalty, etc.), you can try one of the following options: Yi-34B-Chat-Playground (Yi official) Access is available through a whitelist. Welcome to apply (fill out a form in English or Chinese). Yi-34B-Chat-Playground (Replicate) Chat with Yi If you want to chat with Yi, you can use one of these online services, which offer a similar user experience: Yi-34B-Chat (Yi official on Hugging Face) No registration is required. Yi-34B-Chat (Yi official beta) Access is available through a whitelist. Welcome to apply (fill out a form in English or Chinese). \ [Back to top \] Quick start - pip This tutorial guides you through every step of running Yi-34B-Chat locally on an A800 (80G) and then performing inference. Step 0: Prerequisites Make sure Python 3.10 or a later version is installed. If you want to run other Yi models, see software and hardware requirements. Step 1: Prepare your environment To set up the environment and install the required packages, execute the following command. git clone https://github.com/01-ai/Yi.git cd yi pip install -r requirements.txt Step 2: Download the Yi model You can download the weights and tokenizer of Yi models from the following sources: Hugging Face ModelScope WiseModel Step 3: Perform inference You can perform inference with Yi chat or base models as below. Perform inference with Yi chat model Create a file named quick_start.py and copy the following content to it. from transformers import AutoModelForCausalLM, AutoTokenizer model_path = '' tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False) Since transformers 4.35.0, the GPT-Q/AWQ model can be loaded using AutoModelForCausalLM. model = AutoModelForCausalLM.from_pretrained( model_path, device_map="auto", torch_dtype='auto' ).eval() Prompt content: "hi" messages = [ {"role": "user", "content": "hi"} ] input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt') output_ids = model.generate(input_ids.to('cuda')) response = tokenizer.decode(output_ids0:], skip_special_tokens=True) Model response: "Hello! How can I assist you today?" print(response) Run quick_start.py. python quick_start.py Then you can see an output similar to the one below. Hello! How can I assist you today? Perform inference with Yi base model Yi-34B The steps are similar to pip - Perform inference with Yi chat model. You can use the existing file text_generation.py. python demo/text_generation.py --model Then you can see an output similar to the one below. Output. Prompt: Let me tell you an interesting story about cat Tom and mouse Jerry, Generation: Let me tell you an interesting story about cat Tom and mouse Jerry, which happened in my childhood. My father had a big house with two cats living inside it to kill mice. One day when I was playing at home alone, I found one of the tomcats lying on his back near our kitchen door, looking very much like he wanted something from us but couldnt get up because there were too many people around him! He kept trying for several minutes before finally giving up... Yi-9B Input from transformers import AutoModelForCausalLM, AutoTokenizer MODEL_DIR = "01-ai/Yi-9B" model = AutoModelForCausalLM.from_pretrained(MODEL_DIR, torch_dtype="auto") tokenizer = AutoTokenizer.from_pretrained(MODEL_DIR, use_fast=False) input_text = "# write the quick sort algorithm" inputs = tokenizer(input_text, return_tensors="pt").to(model.device) outputs = model.generate(**inputs, max_length=256) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) Output \\\`bash write the quick sort algorithm def quick\_sort(arr): if len(arr) pivot\] return quick\_sort(left) + middle + quick\_sort(right) test the quick sort algorithm print(quick\_sort(\[3, 6, 8, 10, 1, 2, 1\])) [ Back to top ] Quick start - Docker Run Yi-34B-chat locally with Docker: a step-by-step guide. This tutorial guides you through every step of running Yi-34B-Chat on an A800 GPU or 4*4090 locally and then performing inference. Step 0: Prerequisites Make sure you've installed Docker and nvidia-container-toolkit. Step 1: Start Docker docker run -it --gpus all \ -v <your-model-path>: /models ghcr.io/01-ai/yi:latest Alternatively, you can pull the Yi Docker image from registry.lingyiwanwu.com/ci/01-ai/yi:latest. Step 2: Perform inference You can perform inference with Yi chat or base models as below. Perform inference with Yi chat model The steps are similar to pip - Perform inference with Yi chat model. Note that the only difference is to set model_path = '<your-model-mount-path>' instead of model_path = '<your-model-path>'. Perform inference with Yi base model The steps are similar to pip - Perform inference with Yi base model. Note that the only difference is to set --model <your-model-mount-path>' instead of model <your-model-path>. Quick start - conda-lock You can use conda-lock to generate fully reproducible lock files for conda environments. You can refer to conda-lock.yml for the exact versions of the dependencies. Additionally, you can utilize micromamba for installing these dependencies. To install the dependencies, follow these steps: Install micromamba by following the instructions available here. Execute micromamba install -y -n yi -f conda-lock.yml to create a conda environment named yi and install the necessary dependencies. Quick start - llama.cpp The following tutorial will guide you through every step of running a quantized model (Yi-chat-6B-2bits) locally and then performing inference. Run Yi-chat-6B-2bits locally with llama.cpp: a step-by-step guide. This tutorial guides you through every step of running a quantized model (Yi-chat-6B-2bits) locally and then performing inference. Step 0: Prerequisites Step 1: Download llama.cpp Step 2: Download Yi model Step 3: Perform inference Step 0: Prerequisites This tutorial assumes you use a MacBook Pro with 16GB of memory and an Apple M2 Pro chip. Make sure git-lfs is installed on your machine. Step 1: Download llama.cpp To clone the llama.cpp repository, run the following command. git clone [email protected]:ggerganov/llama.cpp.git Step 2: Download Yi model 2.1 To clone XeIaso/yi-chat-6B-GGUF with just pointers, run the following command. GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/XeIaso/yi-chat-6B-GGUF 2.2 To download a quantized Yi model (yi-chat-6b.Q2\_K.gguf), run the following command. git-lfs pull --include yi-chat-6b.Q2_K.gguf Step 3: Perform inference To perform inference with the Yi model, you can use one of the following methods. Method 1: Perform inference in terminal Method 2: Perform inference in web Method 1: Perform inference in terminal To compile llama.cpp using 4 threads and then conduct inference, navigate to the llama.cpp directory, and run the following command. Tips * Replace /Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.gguf with the actual path of your model. * By default, the model operates in completion mode. * For additional output customization options (for example, system prompt, temperature, repetition penalty, etc.), run ./main -h to check detailed descriptions and usage. make -j4 && ./main -m /Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.gguf -p "How do you feed your pet fox? Please answer this question in 6 simple steps:\nStep 1:" -n 384 -e ... How do you feed your pet fox? Please answer this question in 6 simple steps: Step 1: Select the appropriate food for your pet fox. You should choose high-quality, balanced prey items that are suitable for their unique dietary needs. These could include live or frozen mice, rats, pigeons, or other small mammals, as well as fresh fruits and vegetables. Step 2: Feed your pet fox once or twice a day, depending on the species and its individual preferences. Always ensure that they have access to fresh water throughout the day. Step 3: Provide an appropriate environment for your pet fox. Ensure it has a comfortable place to rest, plenty of space to move around, and opportunities to play and exercise. Step 4: Socialize your pet with other animals if possible. Interactions with other creatures can help them develop social skills and prevent boredom or stress. Step 5: Regularly check for signs of illness or discomfort in your fox. Be prepared to provide veterinary care as needed, especially for common issues such as parasites, dental health problems, or infections. Step 6: Educate yourself about the needs of your pet fox and be aware of any potential risks or concerns that could affect their well-being. Regularly consult with a veterinarian to ensure you are providing the best care. ... Now you have successfully asked a question to the Yi model and got an answer! Method 2: Perform inference in web To initialize a lightweight and swift chatbot, run the following command. cd llama.cpp ./server --ctx-size 2048 --host 0.0.0.0 --n-gpu-layers 64 --model /Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.gguf Then you can get an output like this: ... llama_new_context_with_model: n_ctx = 2048 llama_new_context_with_model: freq_base = 5000000.0 llama_new_context_with_model: freq_scale = 1 ggml_metal_init: allocating ggml_metal_init: found device: Apple M2 Pro ggml_metal_init: picking default device: Apple M2 Pro ggml_metal_init: ggml.metallib not found, loading from source ggml_metal_init: GGML_METAL_PATH_RESOURCES = nil ggml_metal_init: loading '/Users/yu/llama.cpp/ggml-metal.metal' ggml_metal_init: GPU name: Apple M2 Pro ggml_metal_init: GPU family: MTLGPUFamilyApple8 (1008) ggml_metal_init: hasUnifiedMemory = true ggml_metal_init: recommendedMaxWorkingSetSize = 11453.25 MB ggml_metal_init: maxTransferRate = built-in GPU ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 128.00 MiB, ( 2629.44 / 10922.67) llama_new_context_with_model: KV self size = 128.00 MiB, K (f16): 64.00 MiB, V (f16): 64.00 MiB ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 0.02 MiB, ( 2629.45 / 10922.67) llama_build_graph: non-view tensors processed: 676/676 llama_new_context_with_model: compute buffer total size = 159.19 MiB ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 156.02 MiB, ( 2785.45 / 10922.67) Available slots: -> Slot 0 - max context: 2048 llama server listening at http://0.0.0.0:8080 To access the chatbot interface, open your web browser and enter http://0.0.0.0:8080 into the address bar. Yi model chatbot interface - llama.cpp Enter a question, such as "How do you feed your pet fox? Please answer this question in 6 simple steps" into the prompt window, and you will receive a corresponding answer. Ask a question to Yi model - llama.cpp \ [Back to top \] Web demo You can build a web UI demo for Yi chat models (note that Yi base models are not supported in this senario). Step 1: Prepare your environment. Step 2: Download the Yi model. Step 3. To start a web service locally, run the following command. python demo/web_demo.py -c You can access the web UI by entering the address provided in the console into your browser. Quick start - web demo \ [Back to top \] Fine-tuning bash finetune/scripts/run_sft_Yi_6b.sh Once finished, you can compare the finetuned model and the base model with the following command: bash finetune/scripts/run_eval.sh For advanced usage (like fine-tuning based on your custom data), see the explanations below. Finetune code for Yi 6B and 34B Preparation From Image By default, we use a small dataset from BAAI/COIG to finetune the base model. You can also prepare your customized dataset in the following jsonl format: { "prompt": "Human: Who are you? Assistant:", "chosen": "I'm Yi." } And then mount them in the container to replace the default ones: docker run -it \ -v /path/to/save/finetuned/model/:/finetuned-model \ -v /path/to/train.jsonl:/yi/finetune/data/train.json \ -v /path/to/eval.jsonl:/yi/finetune/data/eval.json \ ghcr.io/01-ai/yi:latest \ bash finetune/scripts/run_sft_Yi_6b.sh From Local Server Make sure you have conda. If not, use mkdir -p ~/miniconda3 wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O ~/miniconda3/miniconda.sh bash /miniconda3/miniconda.sh -b -u -p /miniconda3 rm -rf ~/miniconda3/miniconda.sh ~/miniconda3/bin/conda init bash source ~/.bashrc Then, create a conda env: conda create -n dev_env python=3.10 -y conda activate dev_env pip install torch==2.0.1 deepspeed==0.10 tensorboard transformers datasets sentencepiece accelerate ray==2.7 Hardware Setup For the Yi-6B model, a node with 4 GPUs, each with GPU memory larger than 60GB, is recommended. For the Yi-34B model, because the usage of the zero-offload technique consumes a lot of CPU memory, please be careful to limit the number of GPUs in the 34B finetune training. Please use CUDA\_VISIBLE\_DEVICES to limit the number of GPUs (as shown in scripts/run\_sft\_Yi\_34b.sh). A typical hardware setup for finetuning the 34B model is a node with 8 GPUs (limited to 4 in running by CUDA\_VISIBLE\_DEVICES=0,1,2,3), each with GPU memory larger than 80GB, and total CPU memory larger than 900GB. Quick Start Download a LLM-base model to MODEL\_PATH (6B and 34B). A typical folder of models is like: |-- $MODEL_PATH | |-- config.json | |-- pytorch_model-00001-of-00002.bin | |-- pytorch_model-00002-of-00002.bin | |-- pytorch_model.bin.index.json | |-- tokenizer_config.json | |-- tokenizer.model | |-- ... Download a dataset from huggingface to local storage DATA\_PATH, e.g. Dahoas/rm-static. |-- $DATA_PATH | |-- data | | |-- train-00000-of-00001-2a1df75c6bce91ab.parquet | | |-- test-00000-of-00001-8c7c51afc6d45980.parquet | |-- dataset_infos.json | |-- README.md finetune/yi_example_dataset has example datasets, which are modified from BAAI/COIG |-- $DATA_PATH |--data |-- train.jsonl |-- eval.jsonl cd into the scripts folder, copy and paste the script, and run. For example: cd finetune/scripts bash run_sft_Yi_6b.sh For the Yi-6B base model, setting training\_debug\_steps=20 and num\_train\_epochs=4 can output a chat model, which takes about 20 minutes. For the Yi-34B base model, it takes a relatively long time for initialization. Please be patient. Evaluation cd finetune/scripts bash run_eval.sh Then you'll see the answer from both the base model and the finetuned model. \ [Back to top \] Quantization GPT-Q python quantization/gptq/quant_autogptq.py \ --model /base_model \ --output_dir /quantized_model \ --trust_remote_code Once finished, you can then evaluate the resulting model as follows: python quantization/gptq/eval_quantized_model.py \ --model /quantized_model \ --trust_remote_code For details, see the explanations below. GPT-Q quantization GPT-Q is a PTQ (Post-Training Quantization) method. It saves memory and provides potential speedups while retaining the accuracy of the model. Yi models can be GPT-Q quantized without a lot of efforts. We provide a step-by-step tutorial below. To run GPT-Q, we will use AutoGPTQ and exllama. And the huggingface transformers has integrated optimum and auto-gptq to perform GPTQ quantization on language models. Do Quantization The quant_autogptq.py script is provided for you to perform GPT-Q quantization: python quant_autogptq.py --model /base_model \ --output_dir /quantized_model --bits 4 --group_size 128 --trust_remote_code Run Quantized Model You can run a quantized model using the eval_quantized_model.py: python eval_quantized_model.py --model /quantized_model --trust_remote_code AWQ python quantization/awq/quant_autoawq.py \ --model /base_model \ --output_dir /quantized_model \ --trust_remote_code Once finished, you can then evaluate the resulting model as follows: python quantization/awq/eval_quantized_model.py \ --model /quantized_model \ --trust_remote_code For details, see the explanations below. AWQ quantization AWQ is a PTQ (Post-Training Quantization) method. It's an efficient and accurate low-bit weight quantization (INT3/4) for LLMs. Yi models can be AWQ quantized without a lot of efforts. We provide a step-by-step tutorial below. To run AWQ, we will use AutoAWQ. Do Quantization The quant_autoawq.py script is provided for you to perform AWQ quantization: python quant_autoawq.py --model /base_model \ --output_dir /quantized_model --bits 4 --group_size 128 --trust_remote_code Run Quantized Model You can run a quantized model using the eval_quantized_model.py: python eval_quantized_model.py --model /quantized_model --trust_remote_code \ [Back to top \] Deployment If you want to deploy Yi models, make sure you meet the software and hardware requirements. Software requirements Before using Yi quantized models, make sure you've installed the correct software listed below. Model Software Yi 4-bit quantized models AWQ and CUDA Yi 8-bit quantized models GPTQ and CUDA Hardware requirements Before deploying Yi in your environment, make sure your hardware meets the following requirements. Chat models Model Minimum VRAM Recommended GPU Example Yi-6B-Chat 15 GB 1 x RTX 3090 (24 GB) 1 x RTX 4090 (24 GB) 1 x A10 (24 GB) 1 x A30 (24 GB) Yi-6B-Chat-4bits 4 GB 1 x RTX 3060 (12 GB) 1 x RTX 4060 (8 GB) Yi-6B-Chat-8bits 8 GB 1 x RTX 3070 (8 GB) 1 x RTX 4060 (8 GB) Yi-34B-Chat 72 GB 4 x RTX 4090 (24 GB) 1 x A800 (80GB) Yi-34B-Chat-4bits 20 GB 1 x RTX 3090 (24 GB) 1 x RTX 4090 (24 GB) 1 x A10 (24 GB) 1 x A30 (24 GB) 1 x A100 (40 GB) Yi-34B-Chat-8bits 38 GB 2 x RTX 3090 (24 GB) 2 x RTX 4090 (24 GB) 1 x A800 (40 GB) Below are detailed minimum VRAM requirements under different batch use cases. Model batch=1 batch=4 batch=16 batch=32 Yi-6B-Chat 12 GB 13 GB 15 GB 18 GB Yi-6B-Chat-4bits 4 GB 5 GB 7 GB 10 GB Yi-6B-Chat-8bits 7 GB 8 GB 10 GB 14 GB Yi-34B-Chat 65 GB 68 GB 76 GB \> 80 GB Yi-34B-Chat-4bits 19 GB 20 GB 30 GB 40 GB Yi-34B-Chat-8bits 35 GB 37 GB 46 GB 58 GB Base models Model Minimum VRAM Recommended GPU Example Yi-6B 15 GB 1 x RTX 3090 (24 GB) 1 x RTX 4090 (24 GB) 1 x A10 (24 GB) 1 x A30 (24 GB) Yi-6B-200K 50 GB 1 x A800 (80 GB) Yi-9B 20 GB 1 x RTX 4090 (24 GB) Yi-34B 72 GB 4 x RTX 4090 (24 GB) 1 x A800 (80 GB) Yi-34B-200K 200 GB 4 x A800 (80 GB) \ [Back to top \] FAQ If you have any questions while using the Yi series models, the answers provided below could serve as a helpful reference for you. Fine-tuning Base model or Chat model - which to fine-tune?** The choice of pre-trained language model for fine-tuning hinges on the computational resources you have at your disposal and the particular demands of your task. If you are working with a substantial volume of fine-tuning data (say, over 10,000 samples), the Base model could be your go-to choice. On the other hand, if your fine-tuning data is not quite as extensive, opting for the Chat model might be a more fitting choice. It is generally advisable to fine-tune both the Base and Chat models, compare their performance, and then pick the model that best aligns with your specific requirements. Yi-34B versus Yi-34B-Chat for full-scale fine-tuning - what is the difference?** The key distinction between full-scale fine-tuning on \Yi-34B\and \Yi-34B-Chat\ comes down to the fine-tuning approach and outcomes. - Yi-34B-Chat employs a Special Fine-Tuning (SFT) method, resulting in responses that mirror human conversation style more closely. - The Base model's fine-tuning is more versatile, with a relatively high performance potential. - If you are confident in the quality of your data, fine-tuning with \Yi-34B\ could be your go-to. - If you are aiming for model-generated responses that better mimic human conversational style, or if you have doubts about your data quality, \Yi-34B-Chat\ might be your best bet. Quantization Quantized model versus original model - what is the performance gap?** The performance variance is largely contingent on the quantization method employed and the specific use cases of these models. For instance, when it comes to models provided by the AWQ official, from a Benchmark standpoint, quantization might result in a minor performance drop of a few percentage points. Subjectively speaking, in situations like logical reasoning, even a 1% performance shift could impact the accuracy of the output results. General Where can I source fine-tuning question answering datasets?** You can find fine-tuning question answering datasets on platforms like Hugging Face, with datasets like m-a-p/COIG-CQIA readily available. Additionally, Github offers fine-tuning frameworks, such as hiyouga/LLaMA-Factory, which integrates pre-made datasets. What is the GPU memory requirement for fine-tuning Yi-34B FP16?** The GPU memory needed for fine-tuning 34B FP16 hinges on the specific fine-tuning method employed. For full parameter fine-tuning, you'll need 8 GPUs each with 80 GB; however, more economical solutions like Lora require less. For more details, check out \hiyouga/LLaMA-Factory\. Also, consider using BF16 instead of FP16 for fine-tuning to optimize performance. Are there any third-party platforms that support chat functionality for the Yi-34b-200k model?** If you're looking for third-party Chats, options include \fireworks.ai\. Learning hub If you want to learn Yi, you can find a wealth of helpful educational resources here. Welcome to the Yi learning hub! Whether you're a seasoned developer or a newcomer, you can find a wealth of helpful educational resources to enhance your understanding and skills with Yi models, including insightful blog posts, comprehensive video tutorials, hands-on guides, and more. The content you find here has been generously contributed by knowledgeable Yi experts and passionate enthusiasts. We extend our heartfelt gratitude for your invaluable contributions! At the same time, we also warmly invite you to join our collaborative effort by contributing to Yi. If you have already made contributions to Yi, please don't hesitate to showcase your remarkable work in the table below. With all these resources at your fingertips, you're ready to start your exciting journey with Yi. Happy learning! Tutorials English tutorials Type Deliverable Date Author Video Run dolphin-2.2-yi-34b on IoT Devices 2023-11-30 Second State Blog Running Yi-34B-Chat locally using LlamaEdge 2023-11-30 Second State Video Install Yi 34B Locally - Chinese English Bilingual LLM 2023-11-05 Fahd Mirza Video Dolphin Yi 34b - Brand New Foundational Model TESTED 2023-11-27 Matthew Berman Chinese tutorials Type Deliverable Date Author GitHub project 2024-04-25 Blog yi-vl-plusAnki 2024-04-24 GitHub project yi-34b-chat-200k 2024-04-24 Blog Yi-VL 2024-02-02 Blog 34B Llama.cpp & 21G 2023-11-26 Blog Yi-34B 2023-12-10 Blog CPU 2023-12-12 Blog 3 Yi-6B Agent Llama Factory 2024-01-22 Blog Yi-VL& 2024-01-26 ModelScope Video 24G vllm Yi-34B 2023-12-28 Video Yi-VL-34B - A40 2023-01-28 Why Yi? Ecosystem Upstream Downstream Serving Quantization Fine-tuning API Benchmarks Chat model performance Base model performance Yi-34B and Yi-34B-200K Yi-9B Ecosystem Yi has a comprehensive ecosystem, offering a range of tools, services, and models to enrich your experiences and maximize productivity. Upstream Downstream Serving Quantization Fine-tuning API Upstream The Yi series models follow the same model architecture as Llama. By choosing Yi, you can leverage existing tools, libraries, and resources within the Llama ecosystem, eliminating the need to create new tools and enhancing development efficiency. For example, the Yi series models are saved in the format of the Llama model. You can directly use LlamaForCausalLM and LlamaTokenizer to load the model. For more information, see Use the chat model. from transformers import AutoModelForCausalLM, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("01-ai/Yi-34b", use_fast=False) model = AutoModelForCausalLM.from_pretrained("01-ai/Yi-34b", device_map="auto") \ [Back to top \] Downstream Tip * Feel free to create a PR and share the fantastic work you've built using the Yi series models. * To help others quickly understand your work, it is recommended to use the format of : + . Serving If you want to get up with Yi in a few minutes, you can use the following services built upon Yi. Yi-34B-Chat: you can chat with Yi using one of the following platforms: Yi-34B-Chat | Hugging Face Yi-34B-Chat | Yi Platform: Note that currently it's available through a whitelist. Welcome to apply (fill out a form in English or Chinese) and experience it firsthand! Yi-6B-Chat (Replicate): you can use this model with more options by setting additional parameters and calling APIs. ScaleLLM: you can use this service to run Yi models locally with added flexibility and customization. Quantization If you have limited computational capabilities, you can use Yi's quantized models as follows. These quantized models have reduced precision but offer increased efficiency, such as faster inference speed and smaller RAM usage. TheBloke/Yi-34B-GPTQ TheBloke/Yi-34B-GGUF TheBloke/Yi-34B-AWQ Fine-tuning If you're seeking to explore the diverse capabilities within Yi's thriving family, you can delve into Yi's fine-tuned models as below. TheBloke Models: this site hosts numerous fine-tuned models derived from various LLMs including Yi. This is not an exhaustive list for Yi, but to name a few sorted on downloads: TheBloke/dolphin-2\_2-yi-34b-AWQ TheBloke/Yi-34B-Chat-AWQ TheBloke/Yi-34B-Chat-GPTQ SUSTech/SUS-Chat-34B: this model ranked first among all models below 70B and outperformed the twice larger deepseek-llm-67b-chat. You can check the result on the Open LLM Leaderboard. OrionStarAI/OrionStar-Yi-34B-Chat-Llama: this model excelled beyond other models (such as GPT-4, Qwen-14B-Chat, Baichuan2-13B-Chat) in C-Eval and CMMLU evaluations on the OpenCompass LLM Leaderboard. NousResearch/Nous-Capybara-34B: this model is trained with 200K context length and 3 epochs on the Capybara dataset. API amazing-openai-api: this tool converts Yi model APIs into the OpenAI API format out of the box. LlamaEdge: this tool builds an OpenAI-compatible API server for Yi-34B-Chat using a portable Wasm (WebAssembly) file, powered by Rust. \ [Back to top \] Tech report For detailed capabilities of the Yi series model, see Yi: Open Foundation Models by 01.AI. Citation @misc{ai2024yi, title={Yi: Open Foundation Models by 01.AI}, author={01. AI and : and Alex Young and Bei Chen and Chao Li and Chengen Huang and Ge Zhang and Guanwei Zhang and Heng Li and Jiangcheng Zhu and Jianqun Chen and Jing Chang and Kaidong Yu and Peng Liu and Qiang Liu and Shawn Yue and Senbin Yang and Shiming Yang and Tao Yu and Wen Xie and Wenhao Huang and Xiaohui Hu and Xiaoyi Ren and Xinyao Niu and Pengcheng Nie and Yuchi Xu and Yudong Liu and Yue Wang and Yuxuan Cai and Zhenyu Gu and Zhiyuan Liu and Zonghong Dai}, year={2024}, eprint={2403.04652}, archivePrefix={arXiv}, primaryClass={cs.CL} } Benchmarks Chat model performance Base model performance Chat model performance Yi-34B-Chat model demonstrates exceptional performance, ranking first among all existing open-source models in the benchmarks including MMLU, CMMLU, BBH, GSM8k, and more. Chat model performance Evaluation methods and challenges. Evaluation methods**: we evaluated various benchmarks using both zero-shot and few-shot methods, except for TruthfulQA. Zero-shot vs. few-shot**: in chat models, the zero-shot approach is more commonly employed. Evaluation strategy**: our evaluation strategy involves generating responses while following instructions explicitly or implicitly (such as using few-shot examples). We then isolate relevant answers from the generated text. Challenges faced**: some models are not well-suited to produce output in the specific format required by instructions in few datasets, which leads to suboptimal results. \*: C-Eval results are evaluated on the validation datasets Base model performance Yi-34B and Yi-34B-200K The Yi-34B and Yi-34B-200K models stand out as the top performers among open-source models, especially excelling in MMLU, CMMLU, common-sense reasoning, reading comprehension, and more. Base model performance Evaluation methods. Disparity in results**: while benchmarking open-source models, a disparity has been noted between results from our pipeline and those reported by public sources like OpenCompass. Investigation findings**: a deeper investigation reveals that variations in prompts, post-processing strategies, and sampling techniques across models may lead to significant outcome differences. Uniform benchmarking process**: our methodology aligns with the original benchmarksconsistent prompts and post-processing strategies are used, and greedy decoding is applied during evaluations without any post-processing for the generated content. Efforts to retrieve unreported scores**: for scores that were not reported by the original authors (including scores reported with different settings), we try to get results with our pipeline. Extensive model evaluation**: to evaluate the models capability extensively, we adopted the methodology outlined in Llama2. Specifically, we included PIQA, SIQA, HellaSwag, WinoGrande, ARC, OBQA, and CSQA to assess common sense reasoning. SquAD, QuAC, and BoolQ were incorporated to evaluate reading comprehension. Special configurations**: CSQA was exclusively tested using a 7-shot setup, while all other tests were conducted with a 0-shot configuration. Additionally, we introduced GSM8K (8-shot@1), MATH (4-shot@1), HumanEval (0-shot@1), and MBPP (3-shot@1) under the category "Math & Code". Falcon-180B caveat**: Falcon-180B was not tested on QuAC and OBQA due to technical constraints. Its performance score is an average from other tasks, and considering the generally lower scores of these two tasks, Falcon-180B's capabilities are likely not underestimated. Yi-9B Yi-9B is almost the best among a range of similar-sized open-source models (including Mistral-7B, SOLAR-10.7B, Gemma-7B, DeepSeek-Coder-7B-Base-v1.5 and more), particularly excelling in code, math, common-sense reasoning, and reading comprehension. Yi-9B benchmark - details In terms of overall ability (Mean-All), Yi-9B performs the best among similarly sized open-source models, surpassing DeepSeek-Coder, DeepSeek-Math, Mistral-7B, SOLAR-10.7B, and Gemma-7B. Yi-9B benchmark - overall In terms of coding ability (Mean-Code), Yi-9B's performance is second only to DeepSeek-Coder-7B, surpassing Yi-34B, SOLAR-10.7B, Mistral-7B, and Gemma-7B. Yi-9B benchmark - code In terms of math ability (Mean-Math), Yi-9B's performance is second only to DeepSeek-Math-7B, surpassing SOLAR-10.7B, Mistral-7B, and Gemma-7B. Yi-9B benchmark - math In terms of common sense and reasoning ability (Mean-Text), Yi-9B's performance is on par with Mistral-7B, SOLAR-10.7B, and Gemma-7B. Yi-9B benchmark - text \ [Back to top \] Who can use Yi? Everyone! The Yi series models are free for personal usage, academic purposes, and commercial use. All usage must adhere to the Yi Series Models Community License Agreement 2.1 For free commercial use, you only need to complete this form to get a Yi Model Commercial License. \ [Back to top \] Misc. Acknowledgments A heartfelt thank you to each of you who have made contributions to the Yi community! You have helped Yi not just a project, but a vibrant, growing home for innovation. yi contributors \ [Back to top \] Disclaimer We use data compliance checking algorithms during the training process, to ensure the compliance of the trained model to the best of our ability. Due to complex data and the diversity of language model usage scenarios, we cannot guarantee that the model will generate correct, and reasonable output in all scenarios. Please be aware that there is still a risk of the model producing problematic outputs. We will not be responsible for any risks and issues resulting from misuse, misguidance, illegal usage, and related misinformation, as well as any associated data security concerns. \ [Back to top \] License The source code in this repo is licensed under the Apache 2.0 license. The Yi series models are fully open for academic research and free for commercial use, with automatic permission granted upon application. All usage must adhere to the Yi Series Models Community License Agreement 2.1. For free commercial use, you only need to send an email to get official commercial permission. \ [Back to top \]
Updated 5/28/2024
📶
Yi-6B-200K
173
specify theme context for images Building the Next Generation of Open-Source and Bilingual LLMs Hugging Face ModelScope WiseModel Ask questions or discuss ideas on GitHub Join us on Discord or WeChat Check out Yi Tech Report Grow at Yi Learning Hub Table of Contents What is Yi? Introduction Models Chat models Base models Model info News How to use Yi? Quick start Choose your path pip docker llama.cpp conda-lock Web demo Fine-tuning Quantization Deployment FAQ Learning hub Why Yi? Ecosystem Upstream Downstream Serving Quantization Fine-tuning API Benchmarks Base model performance Chat model performance Tech report Citation Who can use Yi? Misc. Acknowledgements Disclaimer License What is Yi? Introduction The Yi series models are the next generation of open-source large language models trained from scratch by 01.AI. Targeted as a bilingual language model and trained on 3T multilingual corpus, the Yi series models become one of the strongest LLM worldwide, showing promise in language understanding, commonsense reasoning, reading comprehension, and more. For example, Yi-34B-Chat model landed in second place (following GPT-4 Turbo), outperforming other LLMs (such as GPT-4, Mixtral, Claude) on the AlpacaEval Leaderboard (based on data available up to January 2024). Yi-34B model ranked first among all existing open-source models (such as Falcon-180B, Llama-70B, Claude) in both English and Chinese on various benchmarks, including Hugging Face Open LLM Leaderboard (pre-trained) and C-Eval (based on data available up to November 2023). (Credits to Llama) Thanks to the Transformer and Llama open-source communities, as they reduce the efforts required to build from scratch and enable the utilization of the same tools within the AI ecosystem. If you're interested in Yi's adoption of Llama architecture and license usage policy, see Yi's relation with Llama. > TL;DR > > The Yi series models adopt the same model architecture as Llama but are NOT derivatives of Llama. Both Yi and Llama are based on the Transformer structure, which has been the standard architecture for large language models since 2018. Grounded in the Transformer architecture, Llama has become a new cornerstone for the majority of state-of-the-art open-source models due to its excellent stability, reliable convergence, and robust compatibility. This positions Llama as the recognized foundational framework for models including Yi. Thanks to the Transformer and Llama architectures, other models can leverage their power, reducing the effort required to build from scratch and enabling the utilization of the same tools within their ecosystems. However, the Yi series models are NOT derivatives of Llama, as they do not use Llama's weights. As Llama's structure is employed by the majority of open-source models, the key factors of determining model performance are training datasets, training pipelines, and training infrastructure. Developing in a unique and proprietary way, Yi has independently created its own high-quality training datasets, efficient training pipelines, and robust training infrastructure entirely from the ground up. This effort has led to excellent performance with Yi series models ranking just behind GPT4 and surpassing Llama on the Alpaca Leaderboard in Dec 2023. \ [Back to top \] News 2024-03-16: The Yi-9B-200K is open-sourced and available to the public. 2024-03-08: Yi Tech Report is published! 2024-03-07: The long text capability of the Yi-34B-200K has been enhanced. In the "Needle-in-a-Haystack" test, the Yi-34B-200K's performance is improved by 10.5%, rising from 89.3% to an impressive 99.8%. We continue to pre-train the model on 5B tokens long-context data mixture and demonstrate a near-all-green performance. 2024-03-06: The Yi-9B is open-sourced and available to the public. Yi-9B stands out as the top performer among a range of similar-sized open-source models (including Mistral-7B, SOLAR-10.7B, Gemma-7B, DeepSeek-Coder-7B-Base-v1.5 and more), particularly excelling in code, math, common-sense reasoning, and reading comprehension. 2024-01-23: The Yi-VL models, Yi-VL-34B and Yi-VL-6B, are open-sourced and available to the public. Yi-VL-34B has ranked first among all existing open-source models in the latest benchmarks, including MMMU and CMMMU (based on data available up to January 2024). 2023-11-23: Chat models are open-sourced and available to the public. This release contains two chat models based on previously released base models, two 8-bit models quantized by GPTQ, and two 4-bit models quantized by AWQ. Yi-34B-Chat Yi-34B-Chat-4bits Yi-34B-Chat-8bits Yi-6B-Chat Yi-6B-Chat-4bits Yi-6B-Chat-8bits You can try some of them interactively at: Hugging Face Replicate 2023-11-23: The Yi Series Models Community License Agreement is updated to v2.1. 2023-11-08: Invited test of Yi-34B chat model. Application form: English Chinese 2023-11-05: The base models, Yi-6B-200K and Yi-34B-200K, are open-sourced and available to the public. This release contains two base models with the same parameter sizes as the previous release, except that the context window is extended to 200K. 2023-11-02: The base models, Yi-6B and Yi-34B, are open-sourced and available to the public. The first public release contains two bilingual (English/Chinese) base models with the parameter sizes of 6B and 34B. Both of them are trained with 4K sequence length and can be extended to 32K during inference time. \ [Back to top \] Models Yi models come in multiple sizes and cater to different use cases. You can also fine-tune Yi models to meet your specific requirements. If you want to deploy Yi models, make sure you meet the software and hardware requirements. Chat models Model Download Yi-34B-Chat Hugging Face ModelScope Yi-34B-Chat-4bits Hugging Face ModelScope Yi-34B-Chat-8bits Hugging Face ModelScope Yi-6B-Chat Hugging Face ModelScope Yi-6B-Chat-4bits Hugging Face ModelScope Yi-6B-Chat-8bits Hugging Face ModelScope \- 4-bit series models are quantized by AWQ. \- 8-bit series models are quantized by GPTQ \- All quantized models have a low barrier to use since they can be deployed on consumer-grade GPUs (e.g., 3090, 4090). Base models Model Download Yi-34B Hugging Face ModelScope Yi-34B-200K Hugging Face ModelScope Yi-9B Hugging Face ModelScope Yi-9B-200K Hugging Face ModelScope Yi-6B Hugging Face ModelScope Yi-6B-200K Hugging Face ModelScope \- 200k is roughly equivalent to 400,000 Chinese characters. \- If you want to use the previous version of the Yi-34B-200K (released on Nov 5, 2023), run git checkout 069cd341d60f4ce4b07ec394e82b79e94f656cf to download the weight. Model info For chat and base models Model Intro Default context window Pretrained tokens Training Data Date 6B series models They are suitable for personal and academic use. 4K 3T Up to June 2023 9B series models It is the best at coding and math in the Yi series models. Yi-9B is continuously trained based on Yi-6B, using 0.8T tokens. 34B series models They are suitable for personal, academic, and commercial (particularly for small and medium-sized enterprises) purposes. It's a cost-effective solution that's affordable and equipped with emergent ability. 3T For chat models For chat model limitations, see the explanations below. The released chat model has undergone exclusive training using Supervised Fine-Tuning (SFT). Compared to other standard chat models, our model produces more diverse responses, making it suitable for various downstream tasks, such as creative scenarios. Furthermore, this diversity is expected to enhance the likelihood of generating higher quality responses, which will be advantageous for subsequent Reinforcement Learning (RL) training. However, this higher diversity might amplify certain existing issues, including: Hallucination: This refers to the model generating factually incorrect or nonsensical information. With the model's responses being more varied, there's a higher chance of hallucination that are not based on accurate data or logical reasoning. Non-determinism in re-generation: When attempting to regenerate or sample responses, inconsistencies in the outcomes may occur. The increased diversity can lead to varying results even under similar input conditions. Cumulative Error: This occurs when errors in the model's responses compound over time. As the model generates more diverse responses, the likelihood of small inaccuracies building up into larger errors increases, especially in complex tasks like extended reasoning, mathematical problem-solving, etc. To achieve more coherent and consistent responses, it is advisable to adjust generation configuration parameters such as temperature, top\_p, or top\_k. These adjustments can help in the balance between creativity and coherence in the model's outputs. \ [Back to top \] How to use Yi? Quick start Choose your path pip docker conda-lock llama.cpp Web demo Fine-tuning Quantization Deployment FAQ Learning hub Quick start Getting up and running with Yi models is simple with multiple choices available. Choose your path Select one of the following paths to begin your journey with Yi! Quick start - Choose your path Deploy Yi locally If you prefer to deploy Yi models locally, and you have sufficient resources (for example, NVIDIA A800 80GB), you can choose one of the following methods: pip Docker conda-lock and you have limited resources (for example, a MacBook Pro), you can use llama.cpp. Not to deploy Yi locally If you prefer not to deploy Yi models locally, you can explore Yi's capabilities using any of the following options. Run Yi with APIs If you want to explore more features of Yi, you can adopt one of these methods: Yi APIs (Yi official) Early access has been granted to some applicants. Stay tuned for the next round of access! Yi APIs (Replicate) Run Yi in playground If you want to chat with Yi with more customizable options (e.g., system prompt, temperature, repetition penalty, etc.), you can try one of the following options: Yi-34B-Chat-Playground (Yi official) Access is available through a whitelist. Welcome to apply (fill out a form in English or Chinese). Yi-34B-Chat-Playground (Replicate) Chat with Yi If you want to chat with Yi, you can use one of these online services, which offer a similar user experience: Yi-34B-Chat (Yi official on Hugging Face) No registration is required. Yi-34B-Chat (Yi official beta) Access is available through a whitelist. Welcome to apply (fill out a form in English or Chinese). \ [Back to top \] Quick start - pip This tutorial guides you through every step of running Yi-34B-Chat locally on an A800 (80G) and then performing inference. Step 0: Prerequisites Make sure Python 3.10 or a later version is installed. If you want to run other Yi models, see software and hardware requirements. Step 1: Prepare your environment To set up the environment and install the required packages, execute the following command. git clone https://github.com/01-ai/Yi.git cd yi pip install -r requirements.txt Step 2: Download the Yi model You can download the weights and tokenizer of Yi models from the following sources: Hugging Face ModelScope WiseModel Step 3: Perform inference You can perform inference with Yi chat or base models as below. Perform inference with Yi chat model Create a file named quick_start.py and copy the following content to it. from transformers import AutoModelForCausalLM, AutoTokenizer model_path = '' tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False) Since transformers 4.35.0, the GPT-Q/AWQ model can be loaded using AutoModelForCausalLM. model = AutoModelForCausalLM.from_pretrained( model_path, device_map="auto", torch_dtype='auto' ).eval() Prompt content: "hi" messages = [ {"role": "user", "content": "hi"} ] input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt') output_ids = model.generate(input_ids.to('cuda')) response = tokenizer.decode(output_ids0:], skip_special_tokens=True) Model response: "Hello! How can I assist you today?" print(response) Run quick_start.py. python quick_start.py Then you can see an output similar to the one below. Hello! How can I assist you today? Perform inference with Yi base model Yi-34B The steps are similar to pip - Perform inference with Yi chat model. You can use the existing file text_generation.py. python demo/text_generation.py --model Then you can see an output similar to the one below. Output. Prompt: Let me tell you an interesting story about cat Tom and mouse Jerry, Generation: Let me tell you an interesting story about cat Tom and mouse Jerry, which happened in my childhood. My father had a big house with two cats living inside it to kill mice. One day when I was playing at home alone, I found one of the tomcats lying on his back near our kitchen door, looking very much like he wanted something from us but couldnt get up because there were too many people around him! He kept trying for several minutes before finally giving up... Yi-9B Input from transformers import AutoModelForCausalLM, AutoTokenizer MODEL_DIR = "01-ai/Yi-9B" model = AutoModelForCausalLM.from_pretrained(MODEL_DIR, torch_dtype="auto") tokenizer = AutoTokenizer.from_pretrained(MODEL_DIR, use_fast=False) input_text = "# write the quick sort algorithm" inputs = tokenizer(input_text, return_tensors="pt").to(model.device) outputs = model.generate(**inputs, max_length=256) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) Output \\\`bash write the quick sort algorithm def quick\_sort(arr): if len(arr) pivot\] return quick\_sort(left) + middle + quick\_sort(right) test the quick sort algorithm print(quick\_sort(\[3, 6, 8, 10, 1, 2, 1\])) [ Back to top ] Quick start - Docker Run Yi-34B-chat locally with Docker: a step-by-step guide. This tutorial guides you through every step of running Yi-34B-Chat on an A800 GPU or 4*4090 locally and then performing inference. Step 0: Prerequisites Make sure you've installed Docker and nvidia-container-toolkit. Step 1: Start Docker docker run -it --gpus all \ -v <your-model-path>: /models ghcr.io/01-ai/yi:latest Alternatively, you can pull the Yi Docker image from registry.lingyiwanwu.com/ci/01-ai/yi:latest. Step 2: Perform inference You can perform inference with Yi chat or base models as below. Perform inference with Yi chat model The steps are similar to pip - Perform inference with Yi chat model. Note that the only difference is to set model_path = '<your-model-mount-path>' instead of model_path = '<your-model-path>'. Perform inference with Yi base model The steps are similar to pip - Perform inference with Yi base model. Note that the only difference is to set --model <your-model-mount-path>' instead of model <your-model-path>. Quick start - conda-lock You can use conda-lock to generate fully reproducible lock files for conda environments. You can refer to conda-lock.yml for the exact versions of the dependencies. Additionally, you can utilize micromamba for installing these dependencies. To install the dependencies, follow these steps: Install micromamba by following the instructions available here. Execute micromamba install -y -n yi -f conda-lock.yml to create a conda environment named yi and install the necessary dependencies. Quick start - llama.cpp The following tutorial will guide you through every step of running a quantized model (Yi-chat-6B-2bits) locally and then performing inference. Run Yi-chat-6B-2bits locally with llama.cpp: a step-by-step guide. This tutorial guides you through every step of running a quantized model (Yi-chat-6B-2bits) locally and then performing inference. Step 0: Prerequisites Step 1: Download llama.cpp Step 2: Download Yi model Step 3: Perform inference Step 0: Prerequisites This tutorial assumes you use a MacBook Pro with 16GB of memory and an Apple M2 Pro chip. Make sure git-lfs is installed on your machine. Step 1: Download llama.cpp To clone the llama.cpp repository, run the following command. git clone [email protected]:ggerganov/llama.cpp.git Step 2: Download Yi model 2.1 To clone XeIaso/yi-chat-6B-GGUF with just pointers, run the following command. GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/XeIaso/yi-chat-6B-GGUF 2.2 To download a quantized Yi model (yi-chat-6b.Q2\_K.gguf), run the following command. git-lfs pull --include yi-chat-6b.Q2_K.gguf Step 3: Perform inference To perform inference with the Yi model, you can use one of the following methods. Method 1: Perform inference in terminal Method 2: Perform inference in web Method 1: Perform inference in terminal To compile llama.cpp using 4 threads and then conduct inference, navigate to the llama.cpp directory, and run the following command. Tips * Replace /Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.gguf with the actual path of your model. * By default, the model operates in completion mode. * For additional output customization options (for example, system prompt, temperature, repetition penalty, etc.), run ./main -h to check detailed descriptions and usage. make -j4 && ./main -m /Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.gguf -p "How do you feed your pet fox? Please answer this question in 6 simple steps:\nStep 1:" -n 384 -e ... How do you feed your pet fox? Please answer this question in 6 simple steps: Step 1: Select the appropriate food for your pet fox. You should choose high-quality, balanced prey items that are suitable for their unique dietary needs. These could include live or frozen mice, rats, pigeons, or other small mammals, as well as fresh fruits and vegetables. Step 2: Feed your pet fox once or twice a day, depending on the species and its individual preferences. Always ensure that they have access to fresh water throughout the day. Step 3: Provide an appropriate environment for your pet fox. Ensure it has a comfortable place to rest, plenty of space to move around, and opportunities to play and exercise. Step 4: Socialize your pet with other animals if possible. Interactions with other creatures can help them develop social skills and prevent boredom or stress. Step 5: Regularly check for signs of illness or discomfort in your fox. Be prepared to provide veterinary care as needed, especially for common issues such as parasites, dental health problems, or infections. Step 6: Educate yourself about the needs of your pet fox and be aware of any potential risks or concerns that could affect their well-being. Regularly consult with a veterinarian to ensure you are providing the best care. ... Now you have successfully asked a question to the Yi model and got an answer! Method 2: Perform inference in web To initialize a lightweight and swift chatbot, run the following command. cd llama.cpp ./server --ctx-size 2048 --host 0.0.0.0 --n-gpu-layers 64 --model /Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.gguf Then you can get an output like this: ... llama_new_context_with_model: n_ctx = 2048 llama_new_context_with_model: freq_base = 5000000.0 llama_new_context_with_model: freq_scale = 1 ggml_metal_init: allocating ggml_metal_init: found device: Apple M2 Pro ggml_metal_init: picking default device: Apple M2 Pro ggml_metal_init: ggml.metallib not found, loading from source ggml_metal_init: GGML_METAL_PATH_RESOURCES = nil ggml_metal_init: loading '/Users/yu/llama.cpp/ggml-metal.metal' ggml_metal_init: GPU name: Apple M2 Pro ggml_metal_init: GPU family: MTLGPUFamilyApple8 (1008) ggml_metal_init: hasUnifiedMemory = true ggml_metal_init: recommendedMaxWorkingSetSize = 11453.25 MB ggml_metal_init: maxTransferRate = built-in GPU ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 128.00 MiB, ( 2629.44 / 10922.67) llama_new_context_with_model: KV self size = 128.00 MiB, K (f16): 64.00 MiB, V (f16): 64.00 MiB ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 0.02 MiB, ( 2629.45 / 10922.67) llama_build_graph: non-view tensors processed: 676/676 llama_new_context_with_model: compute buffer total size = 159.19 MiB ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 156.02 MiB, ( 2785.45 / 10922.67) Available slots: -> Slot 0 - max context: 2048 llama server listening at http://0.0.0.0:8080 To access the chatbot interface, open your web browser and enter http://0.0.0.0:8080 into the address bar. Yi model chatbot interface - llama.cpp Enter a question, such as "How do you feed your pet fox? Please answer this question in 6 simple steps" into the prompt window, and you will receive a corresponding answer. Ask a question to Yi model - llama.cpp \ [Back to top \] Web demo You can build a web UI demo for Yi chat models (note that Yi base models are not supported in this senario). Step 1: Prepare your environment. Step 2: Download the Yi model. Step 3. To start a web service locally, run the following command. python demo/web_demo.py -c You can access the web UI by entering the address provided in the console into your browser. Quick start - web demo \ [Back to top \] Fine-tuning bash finetune/scripts/run_sft_Yi_6b.sh Once finished, you can compare the finetuned model and the base model with the following command: bash finetune/scripts/run_eval.sh For advanced usage (like fine-tuning based on your custom data), see the explanations below. Finetune code for Yi 6B and 34B Preparation From Image By default, we use a small dataset from BAAI/COIG to finetune the base model. You can also prepare your customized dataset in the following jsonl format: { "prompt": "Human: Who are you? Assistant:", "chosen": "I'm Yi." } And then mount them in the container to replace the default ones: docker run -it \ -v /path/to/save/finetuned/model/:/finetuned-model \ -v /path/to/train.jsonl:/yi/finetune/data/train.json \ -v /path/to/eval.jsonl:/yi/finetune/data/eval.json \ ghcr.io/01-ai/yi:latest \ bash finetune/scripts/run_sft_Yi_6b.sh From Local Server Make sure you have conda. If not, use mkdir -p ~/miniconda3 wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O ~/miniconda3/miniconda.sh bash /miniconda3/miniconda.sh -b -u -p /miniconda3 rm -rf ~/miniconda3/miniconda.sh ~/miniconda3/bin/conda init bash source ~/.bashrc Then, create a conda env: conda create -n dev_env python=3.10 -y conda activate dev_env pip install torch==2.0.1 deepspeed==0.10 tensorboard transformers datasets sentencepiece accelerate ray==2.7 Hardware Setup For the Yi-6B model, a node with 4 GPUs, each with GPU memory larger than 60GB, is recommended. For the Yi-34B model, because the usage of the zero-offload technique consumes a lot of CPU memory, please be careful to limit the number of GPUs in the 34B finetune training. Please use CUDA\_VISIBLE\_DEVICES to limit the number of GPUs (as shown in scripts/run\_sft\_Yi\_34b.sh). A typical hardware setup for finetuning the 34B model is a node with 8 GPUs (limited to 4 in running by CUDA\_VISIBLE\_DEVICES=0,1,2,3), each with GPU memory larger than 80GB, and total CPU memory larger than 900GB. Quick Start Download a LLM-base model to MODEL\_PATH (6B and 34B). A typical folder of models is like: |-- $MODEL_PATH | |-- config.json | |-- pytorch_model-00001-of-00002.bin | |-- pytorch_model-00002-of-00002.bin | |-- pytorch_model.bin.index.json | |-- tokenizer_config.json | |-- tokenizer.model | |-- ... Download a dataset from huggingface to local storage DATA\_PATH, e.g. Dahoas/rm-static. |-- $DATA_PATH | |-- data | | |-- train-00000-of-00001-2a1df75c6bce91ab.parquet | | |-- test-00000-of-00001-8c7c51afc6d45980.parquet | |-- dataset_infos.json | |-- README.md finetune/yi_example_dataset has example datasets, which are modified from BAAI/COIG |-- $DATA_PATH |--data |-- train.jsonl |-- eval.jsonl cd into the scripts folder, copy and paste the script, and run. For example: cd finetune/scripts bash run_sft_Yi_6b.sh For the Yi-6B base model, setting training\_debug\_steps=20 and num\_train\_epochs=4 can output a chat model, which takes about 20 minutes. For the Yi-34B base model, it takes a relatively long time for initialization. Please be patient. Evaluation cd finetune/scripts bash run_eval.sh Then you'll see the answer from both the base model and the finetuned model. \ [Back to top \] Quantization GPT-Q python quantization/gptq/quant_autogptq.py \ --model /base_model \ --output_dir /quantized_model \ --trust_remote_code Once finished, you can then evaluate the resulting model as follows: python quantization/gptq/eval_quantized_model.py \ --model /quantized_model \ --trust_remote_code For details, see the explanations below. GPT-Q quantization GPT-Q is a PTQ (Post-Training Quantization) method. It saves memory and provides potential speedups while retaining the accuracy of the model. Yi models can be GPT-Q quantized without a lot of efforts. We provide a step-by-step tutorial below. To run GPT-Q, we will use AutoGPTQ and exllama. And the huggingface transformers has integrated optimum and auto-gptq to perform GPTQ quantization on language models. Do Quantization The quant_autogptq.py script is provided for you to perform GPT-Q quantization: python quant_autogptq.py --model /base_model \ --output_dir /quantized_model --bits 4 --group_size 128 --trust_remote_code Run Quantized Model You can run a quantized model using the eval_quantized_model.py: python eval_quantized_model.py --model /quantized_model --trust_remote_code AWQ python quantization/awq/quant_autoawq.py \ --model /base_model \ --output_dir /quantized_model \ --trust_remote_code Once finished, you can then evaluate the resulting model as follows: python quantization/awq/eval_quantized_model.py \ --model /quantized_model \ --trust_remote_code For details, see the explanations below. AWQ quantization AWQ is a PTQ (Post-Training Quantization) method. It's an efficient and accurate low-bit weight quantization (INT3/4) for LLMs. Yi models can be AWQ quantized without a lot of efforts. We provide a step-by-step tutorial below. To run AWQ, we will use AutoAWQ. Do Quantization The quant_autoawq.py script is provided for you to perform AWQ quantization: python quant_autoawq.py --model /base_model \ --output_dir /quantized_model --bits 4 --group_size 128 --trust_remote_code Run Quantized Model You can run a quantized model using the eval_quantized_model.py: python eval_quantized_model.py --model /quantized_model --trust_remote_code \ [Back to top \] Deployment If you want to deploy Yi models, make sure you meet the software and hardware requirements. Software requirements Before using Yi quantized models, make sure you've installed the correct software listed below. Model Software Yi 4-bit quantized models AWQ and CUDA Yi 8-bit quantized models GPTQ and CUDA Hardware requirements Before deploying Yi in your environment, make sure your hardware meets the following requirements. Chat models Model Minimum VRAM Recommended GPU Example Yi-6B-Chat 15 GB 1 x RTX 3090 (24 GB) 1 x RTX 4090 (24 GB) 1 x A10 (24 GB) 1 x A30 (24 GB) Yi-6B-Chat-4bits 4 GB 1 x RTX 3060 (12 GB) 1 x RTX 4060 (8 GB) Yi-6B-Chat-8bits 8 GB 1 x RTX 3070 (8 GB) 1 x RTX 4060 (8 GB) Yi-34B-Chat 72 GB 4 x RTX 4090 (24 GB) 1 x A800 (80GB) Yi-34B-Chat-4bits 20 GB 1 x RTX 3090 (24 GB) 1 x RTX 4090 (24 GB) 1 x A10 (24 GB) 1 x A30 (24 GB) 1 x A100 (40 GB) Yi-34B-Chat-8bits 38 GB 2 x RTX 3090 (24 GB) 2 x RTX 4090 (24 GB) 1 x A800 (40 GB) Below are detailed minimum VRAM requirements under different batch use cases. Model batch=1 batch=4 batch=16 batch=32 Yi-6B-Chat 12 GB 13 GB 15 GB 18 GB Yi-6B-Chat-4bits 4 GB 5 GB 7 GB 10 GB Yi-6B-Chat-8bits 7 GB 8 GB 10 GB 14 GB Yi-34B-Chat 65 GB 68 GB 76 GB \> 80 GB Yi-34B-Chat-4bits 19 GB 20 GB 30 GB 40 GB Yi-34B-Chat-8bits 35 GB 37 GB 46 GB 58 GB Base models Model Minimum VRAM Recommended GPU Example Yi-6B 15 GB 1 x RTX 3090 (24 GB) 1 x RTX 4090 (24 GB) 1 x A10 (24 GB) 1 x A30 (24 GB) Yi-6B-200K 50 GB 1 x A800 (80 GB) Yi-9B 20 GB 1 x RTX 4090 (24 GB) Yi-34B 72 GB 4 x RTX 4090 (24 GB) 1 x A800 (80 GB) Yi-34B-200K 200 GB 4 x A800 (80 GB) \ [Back to top \] FAQ If you have any questions while using the Yi series models, the answers provided below could serve as a helpful reference for you. Fine-tuning Base model or Chat model - which to fine-tune?** The choice of pre-trained language model for fine-tuning hinges on the computational resources you have at your disposal and the particular demands of your task. If you are working with a substantial volume of fine-tuning data (say, over 10,000 samples), the Base model could be your go-to choice. On the other hand, if your fine-tuning data is not quite as extensive, opting for the Chat model might be a more fitting choice. It is generally advisable to fine-tune both the Base and Chat models, compare their performance, and then pick the model that best aligns with your specific requirements. Yi-34B versus Yi-34B-Chat for full-scale fine-tuning - what is the difference?** The key distinction between full-scale fine-tuning on \Yi-34B\and \Yi-34B-Chat\ comes down to the fine-tuning approach and outcomes. - Yi-34B-Chat employs a Special Fine-Tuning (SFT) method, resulting in responses that mirror human conversation style more closely. - The Base model's fine-tuning is more versatile, with a relatively high performance potential. - If you are confident in the quality of your data, fine-tuning with \Yi-34B\ could be your go-to. - If you are aiming for model-generated responses that better mimic human conversational style, or if you have doubts about your data quality, \Yi-34B-Chat\ might be your best bet. Quantization Quantized model versus original model - what is the performance gap?** The performance variance is largely contingent on the quantization method employed and the specific use cases of these models. For instance, when it comes to models provided by the AWQ official, from a Benchmark standpoint, quantization might result in a minor performance drop of a few percentage points. Subjectively speaking, in situations like logical reasoning, even a 1% performance shift could impact the accuracy of the output results. General Where can I source fine-tuning question answering datasets?** You can find fine-tuning question answering datasets on platforms like Hugging Face, with datasets like m-a-p/COIG-CQIA readily available. Additionally, Github offers fine-tuning frameworks, such as hiyouga/LLaMA-Factory, which integrates pre-made datasets. What is the GPU memory requirement for fine-tuning Yi-34B FP16?** The GPU memory needed for fine-tuning 34B FP16 hinges on the specific fine-tuning method employed. For full parameter fine-tuning, you'll need 8 GPUs each with 80 GB; however, more economical solutions like Lora require less. For more details, check out \hiyouga/LLaMA-Factory\. Also, consider using BF16 instead of FP16 for fine-tuning to optimize performance. Are there any third-party platforms that support chat functionality for the Yi-34b-200k model?** If you're looking for third-party Chats, options include \fireworks.ai\. Learning hub If you want to learn Yi, you can find a wealth of helpful educational resources here. Welcome to the Yi learning hub! Whether you're a seasoned developer or a newcomer, you can find a wealth of helpful educational resources to enhance your understanding and skills with Yi models, including insightful blog posts, comprehensive video tutorials, hands-on guides, and more. The content you find here has been generously contributed by knowledgeable Yi experts and passionate enthusiasts. We extend our heartfelt gratitude for your invaluable contributions! At the same time, we also warmly invite you to join our collaborative effort by contributing to Yi. If you have already made contributions to Yi, please don't hesitate to showcase your remarkable work in the table below. With all these resources at your fingertips, you're ready to start your exciting journey with Yi. Happy learning! Tutorials English tutorials Type Deliverable Date Author Video Run dolphin-2.2-yi-34b on IoT Devices 2023-11-30 Second State Blog Running Yi-34B-Chat locally using LlamaEdge 2023-11-30 Second State Video Install Yi 34B Locally - Chinese English Bilingual LLM 2023-11-05 Fahd Mirza Video Dolphin Yi 34b - Brand New Foundational Model TESTED 2023-11-27 Matthew Berman Chinese tutorials Type Deliverable Date Author GitHub project 2024-04-25 Blog yi-vl-plusAnki 2024-04-24 GitHub project yi-34b-chat-200k 2024-04-24 Blog Yi-VL 2024-02-02 Blog 34B Llama.cpp & 21G 2023-11-26 Blog Yi-34B 2023-12-10 Blog CPU 2023-12-12 Blog 3 Yi-6B Agent Llama Factory 2024-01-22 Blog Yi-VL& 2024-01-26 ModelScope Video 24G vllm Yi-34B 2023-12-28 Video Yi-VL-34B - A40 2023-01-28 Why Yi? Ecosystem Upstream Downstream Serving Quantization Fine-tuning API Benchmarks Chat model performance Base model performance Yi-34B and Yi-34B-200K Yi-9B Ecosystem Yi has a comprehensive ecosystem, offering a range of tools, services, and models to enrich your experiences and maximize productivity. Upstream Downstream Serving Quantization Fine-tuning API Upstream The Yi series models follow the same model architecture as Llama. By choosing Yi, you can leverage existing tools, libraries, and resources within the Llama ecosystem, eliminating the need to create new tools and enhancing development efficiency. For example, the Yi series models are saved in the format of the Llama model. You can directly use LlamaForCausalLM and LlamaTokenizer to load the model. For more information, see Use the chat model. from transformers import AutoModelForCausalLM, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("01-ai/Yi-34b", use_fast=False) model = AutoModelForCausalLM.from_pretrained("01-ai/Yi-34b", device_map="auto") \ [Back to top \] Downstream Tip * Feel free to create a PR and share the fantastic work you've built using the Yi series models. * To help others quickly understand your work, it is recommended to use the format of : + . Serving If you want to get up with Yi in a few minutes, you can use the following services built upon Yi. Yi-34B-Chat: you can chat with Yi using one of the following platforms: Yi-34B-Chat | Hugging Face Yi-34B-Chat | Yi Platform: Note that currently it's available through a whitelist. Welcome to apply (fill out a form in English or Chinese) and experience it firsthand! Yi-6B-Chat (Replicate): you can use this model with more options by setting additional parameters and calling APIs. ScaleLLM: you can use this service to run Yi models locally with added flexibility and customization. Quantization If you have limited computational capabilities, you can use Yi's quantized models as follows. These quantized models have reduced precision but offer increased efficiency, such as faster inference speed and smaller RAM usage. TheBloke/Yi-34B-GPTQ TheBloke/Yi-34B-GGUF TheBloke/Yi-34B-AWQ Fine-tuning If you're seeking to explore the diverse capabilities within Yi's thriving family, you can delve into Yi's fine-tuned models as below. TheBloke Models: this site hosts numerous fine-tuned models derived from various LLMs including Yi. This is not an exhaustive list for Yi, but to name a few sorted on downloads: TheBloke/dolphin-2\_2-yi-34b-AWQ TheBloke/Yi-34B-Chat-AWQ TheBloke/Yi-34B-Chat-GPTQ SUSTech/SUS-Chat-34B: this model ranked first among all models below 70B and outperformed the twice larger deepseek-llm-67b-chat. You can check the result on the Open LLM Leaderboard. OrionStarAI/OrionStar-Yi-34B-Chat-Llama: this model excelled beyond other models (such as GPT-4, Qwen-14B-Chat, Baichuan2-13B-Chat) in C-Eval and CMMLU evaluations on the OpenCompass LLM Leaderboard. NousResearch/Nous-Capybara-34B: this model is trained with 200K context length and 3 epochs on the Capybara dataset. API amazing-openai-api: this tool converts Yi model APIs into the OpenAI API format out of the box. LlamaEdge: this tool builds an OpenAI-compatible API server for Yi-34B-Chat using a portable Wasm (WebAssembly) file, powered by Rust. \ [Back to top \] Tech report For detailed capabilities of the Yi series model, see Yi: Open Foundation Models by 01.AI. Citation @misc{ai2024yi, title={Yi: Open Foundation Models by 01.AI}, author={01. AI and : and Alex Young and Bei Chen and Chao Li and Chengen Huang and Ge Zhang and Guanwei Zhang and Heng Li and Jiangcheng Zhu and Jianqun Chen and Jing Chang and Kaidong Yu and Peng Liu and Qiang Liu and Shawn Yue and Senbin Yang and Shiming Yang and Tao Yu and Wen Xie and Wenhao Huang and Xiaohui Hu and Xiaoyi Ren and Xinyao Niu and Pengcheng Nie and Yuchi Xu and Yudong Liu and Yue Wang and Yuxuan Cai and Zhenyu Gu and Zhiyuan Liu and Zonghong Dai}, year={2024}, eprint={2403.04652}, archivePrefix={arXiv}, primaryClass={cs.CL} } Benchmarks Chat model performance Base model performance Chat model performance Yi-34B-Chat model demonstrates exceptional performance, ranking first among all existing open-source models in the benchmarks including MMLU, CMMLU, BBH, GSM8k, and more. Chat model performance Evaluation methods and challenges. Evaluation methods**: we evaluated various benchmarks using both zero-shot and few-shot methods, except for TruthfulQA. Zero-shot vs. few-shot**: in chat models, the zero-shot approach is more commonly employed. Evaluation strategy**: our evaluation strategy involves generating responses while following instructions explicitly or implicitly (such as using few-shot examples). We then isolate relevant answers from the generated text. Challenges faced**: some models are not well-suited to produce output in the specific format required by instructions in few datasets, which leads to suboptimal results. \*: C-Eval results are evaluated on the validation datasets Base model performance Yi-34B and Yi-34B-200K The Yi-34B and Yi-34B-200K models stand out as the top performers among open-source models, especially excelling in MMLU, CMMLU, common-sense reasoning, reading comprehension, and more. Base model performance Evaluation methods. Disparity in results**: while benchmarking open-source models, a disparity has been noted between results from our pipeline and those reported by public sources like OpenCompass. Investigation findings**: a deeper investigation reveals that variations in prompts, post-processing strategies, and sampling techniques across models may lead to significant outcome differences. Uniform benchmarking process**: our methodology aligns with the original benchmarksconsistent prompts and post-processing strategies are used, and greedy decoding is applied during evaluations without any post-processing for the generated content. Efforts to retrieve unreported scores**: for scores that were not reported by the original authors (including scores reported with different settings), we try to get results with our pipeline. Extensive model evaluation**: to evaluate the models capability extensively, we adopted the methodology outlined in Llama2. Specifically, we included PIQA, SIQA, HellaSwag, WinoGrande, ARC, OBQA, and CSQA to assess common sense reasoning. SquAD, QuAC, and BoolQ were incorporated to evaluate reading comprehension. Special configurations**: CSQA was exclusively tested using a 7-shot setup, while all other tests were conducted with a 0-shot configuration. Additionally, we introduced GSM8K (8-shot@1), MATH (4-shot@1), HumanEval (0-shot@1), and MBPP (3-shot@1) under the category "Math & Code". Falcon-180B caveat**: Falcon-180B was not tested on QuAC and OBQA due to technical constraints. Its performance score is an average from other tasks, and considering the generally lower scores of these two tasks, Falcon-180B's capabilities are likely not underestimated. Yi-9B Yi-9B is almost the best among a range of similar-sized open-source models (including Mistral-7B, SOLAR-10.7B, Gemma-7B, DeepSeek-Coder-7B-Base-v1.5 and more), particularly excelling in code, math, common-sense reasoning, and reading comprehension. Yi-9B benchmark - details In terms of overall ability (Mean-All), Yi-9B performs the best among similarly sized open-source models, surpassing DeepSeek-Coder, DeepSeek-Math, Mistral-7B, SOLAR-10.7B, and Gemma-7B. Yi-9B benchmark - overall In terms of coding ability (Mean-Code), Yi-9B's performance is second only to DeepSeek-Coder-7B, surpassing Yi-34B, SOLAR-10.7B, Mistral-7B, and Gemma-7B. Yi-9B benchmark - code In terms of math ability (Mean-Math), Yi-9B's performance is second only to DeepSeek-Math-7B, surpassing SOLAR-10.7B, Mistral-7B, and Gemma-7B. Yi-9B benchmark - math In terms of common sense and reasoning ability (Mean-Text), Yi-9B's performance is on par with Mistral-7B, SOLAR-10.7B, and Gemma-7B. Yi-9B benchmark - text \ [Back to top \] Who can use Yi? Everyone! The Yi series models are free for personal usage, academic purposes, and commercial use. All usage must adhere to the Yi Series Models Community License Agreement 2.1 For free commercial use, you only need to complete this form to get a Yi Model Commercial License. \ [Back to top \] Misc. Acknowledgments A heartfelt thank you to each of you who have made contributions to the Yi community! You have helped Yi not just a project, but a vibrant, growing home for innovation. yi contributors \ [Back to top \] Disclaimer We use data compliance checking algorithms during the training process, to ensure the compliance of the trained model to the best of our ability. Due to complex data and the diversity of language model usage scenarios, we cannot guarantee that the model will generate correct, and reasonable output in all scenarios. Please be aware that there is still a risk of the model producing problematic outputs. We will not be responsible for any risks and issues resulting from misuse, misguidance, illegal usage, and related misinformation, as well as any associated data security concerns. \ [Back to top \] License The source code in this repo is licensed under the Apache 2.0 license. The Yi series models are fully open for academic research and free for commercial use, with automatic permission granted upon application. All usage must adhere to the Yi Series Models Community License Agreement 2.1. For free commercial use, you only need to send an email to get official commercial permission. \ [Back to top \]
Updated 5/28/2024
🏋️
Yi-1.5-34B-Chat
168
Yi-1.5-34B-Chat is an upgraded version of the Yi language model, developed by the team at 01.AI. Compared to the original Yi model, Yi-1.5-34B-Chat has been continuously pre-trained on a high-quality corpus of 500B tokens and fine-tuned on 3M diverse samples. This allows it to deliver stronger performance in areas like coding, math, reasoning, and instruction-following, while still maintaining excellent capabilities in language understanding, commonsense reasoning, and reading comprehension. The model is available in several different sizes, including Yi-1.5-9B-Chat and Yi-1.5-6B-Chat, catering to different use cases and hardware constraints. Model inputs and outputs The Yi-1.5-34B-Chat model can accept a wide range of natural language inputs, including text prompts, instructions, and questions. It can then generate coherent and contextually appropriate responses, making it a powerful tool for conversational AI applications. The model's large scale and diverse training data allow it to engage in thoughtful discussions, provide detailed explanations, and even tackle complex tasks like coding and mathematical problem-solving. Inputs Natural language text prompts Conversational queries and instructions Requests for analysis, explanation, or task completion Outputs Coherent and contextually relevant responses Detailed explanations and task completions Creative and innovative solutions to open-ended problems Capabilities The Yi-1.5-34B-Chat model demonstrates impressive capabilities across a variety of domains. It excels at language understanding, commonsense reasoning, and reading comprehension, allowing it to engage in natural, context-aware conversations. The model also shines in areas like coding, math, and reasoning, where it can provide insightful solutions and explanations. Additionally, the model's strong instruction-following capability makes it well-suited for tasks that require following complex guidelines or steps. What can I use it for? The Yi-1.5-34B-Chat model has a wide range of potential applications, from conversational AI assistants and chatbots to educational tools and creative writing aids. Developers could leverage the model's language understanding and generation capabilities to build virtual assistants that can engage in natural, context-sensitive dialogues. Educators could use the model to create interactive learning experiences, providing personalized explanations and feedback to students. Businesses could explore using the model for customer service, content generation, or even internal task automation. Things to try One interesting aspect of the Yi-1.5-34B-Chat model is its ability to engage in open-ended, contextual reasoning. Users can provide the model with complex prompts or instructions and observe how it formulates thoughtful, creative responses. For example, you could ask the model to solve a challenging math problem, provide a detailed analysis of a historical event, or generate a unique story based on a given premise. The model's versatility and problem-solving skills make it a valuable tool for exploring the boundaries of conversational AI and language understanding.
Updated 6/11/2024
yi-6b
158
The yi-6b models are large language models trained from scratch by developers at 01.AI. They are targeted as bilingual language models trained on a 3T multilingual corpus, aiming to be one of the strongest LLMs worldwide. The Yi series models show promise in language understanding, commonsense reasoning, reading comprehension, and more. For example, the Yi-34B-Chat model ranked second (following GPT-4 Turbo) on the AlpacaEval Leaderboard, outperforming other LLMs like GPT-4, Mixtral, and Claude. The Yi series models adopt the Transformer architecture like the Llama models, reducing the effort required to build from scratch and enabling the utilization of the same tools within the AI ecosystem. However, the Yi series models are not derivatives of Llama, as they do not use Llama's weights. Instead, they have independently created their own high-quality training datasets, efficient training pipelines, and robust training infrastructure entirely from the ground up. Model inputs and outputs The yi-6b models are designed to handle a wide range of natural language tasks, from text generation to question answering. They take a text prompt as input and generate a response as output. Inputs Prompt**: The text that serves as the starting point for the model's generation. Outputs Generated text**: The model's response to the input prompt, which can be of varying length depending on the use case. Capabilities The yi-6b models demonstrate strong performance across a variety of benchmarks, including language understanding, commonsense reasoning, and reading comprehension. They are particularly adept at tasks that require coherent and contextual responses, such as open-ended conversations, summarization, and question answering. What can I use it for? The yi-6b models can be used for a wide range of applications, including: Content generation**: Generating engaging and coherent text for tasks like creative writing, article generation, and dialogue systems. Question answering**: Answering questions on a variety of topics, drawing upon their broad knowledge base. Summarization**: Concisely summarizing long-form text, such as articles or reports. Language understanding**: Performing tasks that require deep language comprehension, like sentiment analysis, text classification, and natural language inference. Things to try One interesting aspect of the yi-6b models is their ability to engage in open-ended conversations. You can try providing the models with a variety of prompts and see how they respond, exploring their conversational capabilities and ability to maintain context. Additionally, you can experiment with fine-tuning the models on specific datasets or tasks to further enhance their performance in areas of interest to you.
Updated 6/29/2024