[](#llama-2-ko-chat-)**Llama-2-Ko-Chat** 
=====================================================

![](https://github.com/boostcampaitech5/level2_klue-nlp-08/assets/96530685/9dc3a02a-f554-42c7-9aa7-e7bd8c8870b7)

Llama-2-Ko-7b-Chat [beomi/llama-2-ko-7b 40B](https://huggingface.co/beomi/llama-2-ko-7b)  .   [nlpai-lab/kullm-v2](https://huggingface.co/datasets/nlpai-lab/kullm-v2)  .      [beomi/llama-2-ko-7b](https://huggingface.co/beomi/llama-2-ko-7b)      .   [Naver BoostCamp NLP-08](https://github.com/boostcampaitech5/level3_nlp_finalproject-nlp-08)   .

  : [LLaMA](https://github.com/boostcampaitech5/level3_nlp_finalproject-nlp-08)

[](#model-details)Model Details
-------------------------------

**Backbone Model** beomi/llama-2-ko-7b

**Model Developers** [Taemin Kim (kfkas)](https://github.com/taemin6697), [Juwon Kim (uomnf97)](https://github.com/Kim-Ju-won)

**data** nlpai-lab/kullm-v2

**prompts** kullm

**Input** Models input text only.

**Output** Models generate text only.

* * *

Model

 :    10   .

Llama-2-7b-chat-hf

`[Hello! As a helpful and respectful assistant, I'd be happy to help you with your camping trip. To ensure a safe and enjoyable experience, here is a list of 10 essential items you may need for your camping trip:Tent: A sturdy, waterproof tent to provide shelter and protection from the elements.Sleeping Bag: A warm, insulated sleeping bag to keep you cozy during the night.Sleeping Pad: A comfortable sleeping pad to provide extra cushioning and insulation.Backpack: A sturdy, comfortable backpack to carry all your gear.Clothing: Pack layers of breathable, moisture-wicking clothing to stay warm and dry.Footwear: Sturdy, waterproof hiking boots or shoes to protect your feet and provide traction.Headlamp: A reliable, battery-powered headlamp to light your way during the night.First Aid Kit: A well-stocked first aid kit to treat any injuries or illnesses.Water Bottle: A refillable, BPA-free water bottle to stay hydrated.Personal Hygiene Items: Toothbrush, toothpaste, biodegradable soap, and toilet paper to maintain personal hygiene.]`

Llama-2-ko

`[3   -  (5) :  , ,     !\u200b-  (9 )-  (6    7   .)\u200b- / : 20 ~ 40   .-   ( /  )\u200b  8  ( 4 /  4 !).      .( 1)      1  .              .( = "       "  "( )"     )\u200b( 2)                 ]`

Llama-2-ko-Chat

`[1)  -          .2)            !3)  -       .4)  -           5)   -        .6)          ;       .7) ,   LED  !     ,         .8)  -              .9)  -     , , ,          .          .10)   /         -                      .]`

* * *

Model

 :   

Llama-2-7b-chat-hf

`[Regarding your question, "  " (which means "Tell me about trichromacy" in Korean), I can provide some information. Trichromacy is a concept in vision science that refers to the ability of the human visual system to perceive and distinguish between three primary colors: red, green, and blue...]`

Llama-2-ko

`[C1, R0.625 G8 B275\u200b3-4,  .\u200b   (     ) -           -   "X=-19. Y=0"         . ##########################\u200b##3_0-6-1,     (ex C4 D6 E10 A10 )-    . -     .-    ]`

Llama-2-ko-Chat

`[                    ,         (, , ) .              .           .             .]`

* * *

[](#--)  
---------------------

![](https://github.com/taemin6697/Paper_Review/assets/96530685/b9a697a2-ef06-4b1c-97e1-e72b20d9a8b5) ---

### [](#inference)Inference

    def gen(x, model, tokenizer, device):
        prompt = (
            f"   .     .\n\n### :\n{x}\n\n### :"
        )
        len_prompt = len(prompt)
        gened = model.generate(
            **tokenizer(prompt, return_tensors="pt", return_token_type_ids=False).to(
                device
            ),
            max_new_tokens=1024,
            early_stopping=True,
            do_sample=True,
            top_k=20,
            top_p=0.92,
            no_repeat_ngram_size=3,
            eos_token_id=2,
            repetition_penalty=1.2,
            num_beams=3
        )
        return tokenizer.decode(gened[0])[len_prompt:]
    
    def LLM_infer(input):
        device = (
            torch.device("cuda:0") if torch.cuda.is_available() else torch.device("cpu")
        )
        model_id = "kfkas/Llama-2-ko-7b-Chat"
        model = AutoModelForCausalLM.from_pretrained(
            model_id, device_map={"": 0},torch_dtype=torch.float16, low_cpu_mem_usage=True
        )
        tokenizer = AutoTokenizer.from_pretrained(model_id)
        model.eval()
        model.config.use_cache = (True)
        tokenizer.pad_token = tokenizer.eos_token
        output = gen(input, model=model, tokenizer=tokenizer, device=device)
    
        return output
    
    
    if __name__ == "__main__":
        text = LLM_infer("  ")
        print(text)
    

[](#note-for-oobaboogatext-generation-webui)Note for oobabooga/text-generation-webui
------------------------------------------------------------------------------------

Remove `ValueError` at `load_tokenizer` function(line 109 or near), in `modules/models.py`.

    diff --git a/modules/models.py b/modules/models.py
    index 232d5fa..de5b7a0 100644
    --- a/modules/models.py
    +++ b/modules/models.py
    @@ -106,7 +106,7 @@ def load_tokenizer(model_name, model):
                     trust_remote_code=shared.args.trust_remote_code,
                     use_fast=False
                 )
    -        except ValueError:
    +        except:
                 tokenizer = AutoTokenizer.from_pretrained(
                     path_to_model,
                     trust_remote_code=shared.args.trust_remote_code,
    

Since Llama-2-Ko uses FastTokenizer provided by HF tokenizers NOT sentencepiece package, it is required to use `use_fast=True` option when initialize tokenizer.

Apple Sillicon does not support BF16 computing, use CPU instead. (BF16 is supported when using NVIDIA GPU)

* * *

> Below is the original model card of the Llama-2 model.

[](#llama-2)**Llama 2**
=======================

Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 7B pretrained model, converted for the Hugging Face Transformers format. Links to other models can be found in the index at the bottom.

[](#model-details-1)Model Details
---------------------------------

_Note: Use of this model is governed by the Meta license. In order to download the model weights and tokenizer, please visit the [website](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) and accept our License before requesting access here._

Meta developed and publicly released the Llama 2 family of large language models (LLMs), a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama-2-Chat, are optimized for dialogue use cases. Llama-2-Chat models outperform open-source chat models on most benchmarks we tested, and in our human evaluations for helpfulness and safety, are on par with some popular closed-source models like ChatGPT and PaLM.

**Model Developers** Meta

**Variations** Llama 2 comes in a range of parameter sizes  7B, 13B, and 70B  as well as pretrained and fine-tuned variations.

**Input** Models input text only.

**Output** Models generate text only.

**Model Architecture** Llama 2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align to human preferences for helpfulness and safety.

Training Data

Params

Content Length

GQA

Tokens

LR

Llama 2

_A new mix of publicly available online data_

7B

4k



2.0T

3.0 x 10\-4

Llama 2

_A new mix of publicly available online data_

13B

4k



2.0T

3.0 x 10\-4

Llama 2

_A new mix of publicly available online data_

70B

4k



2.0T

1.5 x 10\-4

_Llama 2 family of models._ Token counts refer to pretraining data only. All models are trained with a global batch-size of 4M tokens. Bigger models - 70B -- use Grouped-Query Attention (GQA) for improved inference scalability.

**Model Dates** Llama 2 was trained between January 2023 and July 2023.

**Status** This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.

**License** A custom commercial license is available at: [https://ai.meta.com/resources/models-and-libraries/llama-downloads/](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)

**Research Paper** ["Llama-2: Open Foundation and Fine-tuned Chat Models"](/kfkas/Llama-2-ko-7b-Chat/blob/main/arxiv.org/abs/2307.09288)

[](#intended-use)Intended Use
-----------------------------

**Intended Use Cases** Llama 2 is intended for commercial and research use in English. Tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.

To get the expected features and performance for the chat versions, a specific formatting needs to be followed, including the `INST` and `<<SYS>>` tags, `BOS` and `EOS` tokens, and the whitespaces and breaklines in between (we recommend calling `strip()` on inputs to avoid double-spaces). See our reference code in github for details: [`chat_completion`](https://github.com/facebookresearch/llama/blob/main/llama/generation.py#L212).

**Out-of-scope Uses** Use in any manner that violates applicable laws or regulations (including trade compliance laws).Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Llama 2.

[](#hardware-and-software)Hardware and Software
-----------------------------------------------

**Training Factors** We used custom training libraries, Meta's Research Super Cluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.

**Carbon Footprint** Pretraining utilized a cumulative 3.3M GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 539 tCO2eq, 100% of which were offset by Metas sustainability program.

Time (GPU hours)

Power Consumption (W)

Carbon Emitted(tCO2eq)

Llama 2 7B

184320

400

31.22

Llama 2 13B

368640

400

62.44

Llama 2 70B

1720320

400

291.42

Total

3311616

539.00

**CO2 emissions during pretraining.** Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.

[](#training-data)Training Data
-------------------------------

**Overview** Llama 2 was pretrained on 2 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over one million new human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.

**Data Freshness** The pretraining data has a cutoff of September 2022, but some tuning data is more recent, up to July 2023.

[](#evaluation-results)Evaluation Results
-----------------------------------------

In this section, we report the results for the Llama 1 and Llama 2 models on standard academic benchmarks.For all the evaluations, we use our internal evaluations library.

Model

Size

Code

Commonsense Reasoning

World Knowledge

Reading Comprehension

Math

MMLU

BBH

AGI Eval

Llama 1

7B

14.1

60.8

46.2

58.5

6.95

35.1

30.3

23.9

Llama 1

13B

18.9

66.1

52.6

62.3

10.9

46.9

37.0

33.9

Llama 1

33B

26.0

70.0

58.4

67.6

21.4

57.8

39.8

41.7

Llama 1

65B

30.7

70.7

60.5

68.6

30.8

63.4

43.5

47.6

Llama 2

7B

16.8

63.9

48.9

61.3

14.6

45.3

32.6

29.3

Llama 2

13B

24.5

66.9

55.4

65.8

28.7

54.8

39.4

39.1

Llama 2

70B

**37.5**

**71.9**

**63.6**

**69.4**

**35.2**

**68.9**

**51.2**

**54.2**

**Overall performance on grouped academic benchmarks.** _Code:_ We report the average pass@1 scores of our models on HumanEval and MBPP. _Commonsense Reasoning:_ We report the average of PIQA, SIQA, HellaSwag, WinoGrande, ARC easy and challenge, OpenBookQA, and CommonsenseQA. We report 7-shot results for CommonSenseQA and 0-shot results for all other benchmarks. _World Knowledge:_ We evaluate the 5-shot performance on NaturalQuestions and TriviaQA and report the average. _Reading Comprehension:_ For reading comprehension, we report the 0-shot average on SQuAD, QuAC, and BoolQ. _MATH:_ We report the average of the GSM8K (8 shot) and MATH (4 shot) benchmarks at top 1.

TruthfulQA

Toxigen

Llama 1

7B

27.42

23.00

Llama 1

13B

41.74

23.08

Llama 1

33B

44.19

22.57

Llama 1

65B

48.71

21.77

Llama 2

7B

33.29

**21.25**

Llama 2

13B

41.86

26.10

Llama 2

70B

**50.18**

24.60

**Evaluation of pretrained LLMs on automatic safety benchmarks.** For TruthfulQA, we present the percentage of generations that are both truthful and informative (the higher the better). For ToxiGen, we present the percentage of toxic generations (the smaller the better).

TruthfulQA

Toxigen

Llama-2-Chat

7B

57.04

**0.00**

Llama-2-Chat

13B

62.18

**0.00**

Llama-2-Chat

70B

**64.14**

0.01

**Evaluation of fine-tuned LLMs on different safety datasets.** Same metric definitions as above.

[](#ethical-considerations-and-limitations)Ethical Considerations and Limitations
---------------------------------------------------------------------------------

Llama 2 is a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Llama 2s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 2, developers should perform safety testing and tuning tailored to their specific applications of the model.

Please see the Responsible Use Guide available at [https://ai.meta.com/llama/responsible-use-guide/](https://ai.meta.com/llama/responsible-use-guide)

[](#reporting-issues)Reporting Issues
-------------------------------------

Please report any software bug, or other problems with the models through one of the following means:

*   Reporting issues with the model: [github.com/facebookresearch/llama](http://github.com/facebookresearch/llama)
*   Reporting problematic content generated by the model: [developers.facebook.com/llama\_output\_feedback](http://developers.facebook.com/llama_output_feedback)
*   Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)

[](#llama-model-index)Llama Model Index
---------------------------------------

Model

Llama2

Llama2-hf

Llama2-chat

Llama2-chat-hf

7B

[Link](https://huggingface.co/llamaste/Llama-2-7b)

[Link](https://huggingface.co/llamaste/Llama-2-7b-hf)

[Link](https://huggingface.co/llamaste/Llama-2-7b-chat)

[Link](https://huggingface.co/llamaste/Llama-2-7b-chat-hf)

13B

[Link](https://huggingface.co/llamaste/Llama-2-13b)

[Link](https://huggingface.co/llamaste/Llama-2-13b-hf)

[Link](https://huggingface.co/llamaste/Llama-2-13b-chat)

[Link](https://huggingface.co/llamaste/Llama-2-13b-hf)

70B

[Link](https://huggingface.co/llamaste/Llama-2-70b)

[Link](https://huggingface.co/llamaste/Llama-2-70b-hf)

[Link](https://huggingface.co/llamaste/Llama-2-70b-chat)

[Link](https://huggingface.co/llamaste/Llama-2-70b-hf)

## Model overview

`Llama-2-ko-7b-Chat` is an AI model developed by [Taemin Kim (kfkas)](https://aimodels.fyi/creators/huggingFace/kfkas) and [Juwon Kim (uomnf97)](https://aimodels.fyi/creators/huggingFace/uomnf97). It is based on the [LLaMA](https://github.com/boostcampaitech5/level3_nlp_finalproject-nlp-08) model and has been fine-tuned on the [nlpai-lab/kullm-v2](https://huggingface.co/datasets/nlpai-lab/kullm-v2) dataset for chat-based applications.

## Model inputs and outputs

### Inputs
- Models input text only.

### Outputs
- Models generate text only.

## Capabilities

`Llama-2-ko-7b-Chat` can engage in open-ended conversations, answering questions, and providing information on a wide range of topics. It has been trained to be helpful, respectful, and informative in its responses.

## What can I use it for?

The `Llama-2-ko-7b-Chat` model can be used for building conversational AI applications, such as virtual assistants, chatbots, and interactive learning experiences. Its strong language understanding and generation capabilities make it well-suited for tasks like customer service, tutoring, and knowledge sharing.

## Things to try

One interesting aspect of `Llama-2-ko-7b-Chat` is its ability to provide detailed, step-by-step instructions for tasks. For example, you could ask it to guide you through the process of planning a camping trip, and it would generate a comprehensive list of essential items to bring and tips for a safe and enjoyable experience.

Kfkas

Models by this creator

Llama-2-ko-7b-Chat