MythoMax-L2-13b
Maintainer: Gryphe
234
⛏️
| Property | Value |
|---|---|
| Run this model | Run on HuggingFace |
| API spec | View on HuggingFace |
| Github link | No Github link provided |
| Paper link | No paper link provided |
Create account to get full access
Model overview
The MythoMax-L2-13b is an AI model created by Gryphe, an improved and potentially perfected variant of Gryphe's previous MythoMix model. It combines Gryphe's MythoLogic-L2 and Huginn models using a highly experimental tensor type merge technique. This results in a model that excels at both roleplaying and storywriting tasks.
Model inputs and outputs
The MythoMax-L2-13b model primarily accepts Alpaca-style prompts for optimal performance. These prompts include an instruction for the model, and can optionally include a suggestion for the model to roleplay as a character and respond accordingly.
Inputs
- Prompt: A text instruction for the model to follow, such as "Write a story about llamas" or "Roleplay as a wise old wizard and respond to my greeting."
Outputs
- Generated text: The model's response to the given prompt, which can range from short informative responses to longer, more detailed roleplaying replies.
Capabilities
The MythoMax-L2-13b model is capable of both informative and creative text generation. It can provide factual information, but also excel at roleplaying and storytelling tasks. Due to its unique merging process, the model maintains a high level of coherency across its responses.
What can I use it for?
The MythoMax-L2-13b model is well-suited for a variety of creative writing and roleplaying applications. It could be used to generate character dialogues, short stories, or even extended narratives. The model's capabilities make it a useful tool for writers, game developers, and others looking to explore the intersection of AI and creative expression.
Things to try
One interesting aspect of the MythoMax-L2-13b model is its ability to seamlessly transition between informative and roleplaying responses. Try providing the model with a prompt that starts with a factual question, but then invites it to respond in character. See how the model maintains coherency as it shifts into a roleplaying mode.
You could also experiment with the model's storytelling abilities by providing it with a scenario or prompt and asking it to continue the narrative, building on its previous responses. The model's unique merging process allows it to maintain a strong narrative flow.
This summary was produced with help from an AI and may contain inaccuracies - check out the links to read the original source documents!
Related Models
🤔
MythoMax-L2-13B-GGML
81
MythoMax-L2-13B-GGML is an AI model created by the AI researcher Gryphe, and further optimized and quantized by TheBloke. It is an improved variant of Gryphe's MythoLogic-L2 and Huginn models, combining their robust understanding and extensive writing capabilities. The model uses a unique tensor merge technique to blend these capabilities, resulting in strong performance on both roleplaying and storywriting tasks. TheBloke has provided quantized versions of the model in GGML format, which can be used for efficient CPU and GPU inference. These include 4-bit, 5-bit and 8-bit quantized models as well as GPTQ models for GPU acceleration. There are also GGUF models available, which provide improved compatibility with the latest version of llama.cpp. Model inputs and outputs Inputs Text**: The model takes text as input, which it uses to generate further text outputs. Outputs Text**: The model generates natural language text outputs, which can be used for a variety of purposes such as creative writing, roleplay, and language tasks. Capabilities The MythoMax-L2-13B-GGML model excels at both roleplaying and storywriting due to its unique tensor merge technique, which combines the strengths of the MythoLogic-L2 and Huginn models. It is able to generate coherent and engaging text across a range of styles and genres. What can I use it for? The MythoMax-L2-13B-GGML model can be used for a variety of text generation tasks, such as: Creative writing and storytelling Roleplaying and interactive fiction Language modeling and downstream NLP applications The quantized versions provided by TheBloke allow for efficient inference on both CPU and GPU, making the model accessible to a wide range of users and use cases. Things to try One interesting aspect of the MythoMax-L2-13B-GGML model is its ability to generate long, coherent responses. This can be particularly useful for roleplaying and interactive fiction scenarios, where the model can maintain a consistent narrative and character over an extended exchange. Researchers and developers may also want to explore fine-tuning the model on domain-specific data to further improve its performance on specialized tasks. The Gryphe's original unquantised fp16 model could be a good starting point for further training and customization.
Updated Invalid Date
🔍
MythoMax-L2-13B-GPTQ
161
Gryphe's MythoMax L2 13B is a large language model created by Gryphe and supported by a grant from andreessen horowitz (a16z). It is similar in size and capabilities to other prominent open-source models like the Llama 2 7B Chat and Falcon 180B Chat, but with a focus on mythological and fantastical content. Model inputs and outputs MythoMax-L2-13B-GPTQ is a text-to-text generative model, meaning it takes text prompts as input and generates new text as output. The model was trained on a large dataset of online text, with a focus on mythological and fantasy-related content. Inputs Text prompts**: The model takes freeform natural language text as input, which it then uses to generate new text in response. Outputs Generated text**: The model outputs new text that continues or expands upon the provided input prompt. The output can range from a single sentence to multiple paragraphs, depending on the prompt and the model's parameters. Capabilities The MythoMax-L2-13B-GPTQ model is capable of generating engaging, coherent text on a wide variety of fantasy and mythological topics. It can be used to produce creative stories, worldbuilding details, character dialogue, and more. The model's knowledge spans mythological creatures, legends, magical systems, and other fantastical concepts. What can I use it for? The MythoMax-L2-13B-GPTQ model is well-suited for all kinds of fantasy and science-fiction writing projects. Writers and worldbuilders can use it to generate ideas, expand on existing stories, or flesh out the details of imaginary realms. It could also be leveraged for interactive storytelling applications, roleplaying games, or even AI-generated fanfiction. Things to try Try prompting the model with the beginning of a fantastical story or worldbuilding prompt, and see how it continues the narrative. You can also experiment with more specific requests, like asking it to describe a particular mythological creature or magical ritual. The model's responses may surprise you with their creativity and attention to detail.
Updated Invalid Date
📈
mythalion-13b
133
The mythalion-13b model is a merge of the Pygmalion-2 13B and MythoMax L2 13B models, created in collaboration between PygmalionAI and Gryphe. According to the maintainers, this model seems to outperform MythoMax in roleplay and conversation tasks. Model inputs and outputs Inputs The model can be prompted using both the Alpaca and Pygmalion/Metharme formatting, which utilize special tokens like `, , and ` to indicate different roles and conversation flow. Outputs The model generates long-form text responses that aim to stay in character and continue the narrative, making it suitable for fictional writing and roleplaying. Capabilities The mythalion-13b model is focused on generating engaging, character-driven text for creative writing and roleplay scenarios. It has been trained on a mixture of instruction data, fictional stories, and conversational data to develop its capabilities in these areas. What can I use it for? The mythalion-13b model is well-suited for projects involving fictional writing, interactive storytelling, and character-driven roleplaying. This could include applications like interactive fiction, creative writing assistants, and open-ended chat bots. However, the maintainers note that the model was not fine-tuned to be safe or harmless, so it may generate content that is socially unacceptable or factually incorrect. Things to try One interesting aspect of the mythalion-13b model is its use of the Pygmalion/Metharme prompting format, which allows the user to set the character persona and guide the model's responses to stay in-character. Experimenting with different character backgrounds and personas could lead to unique and engaging narrative experiences.
Updated Invalid Date
❗
MythoMax-L2-13B-GGUF
61
The MythoMax-L2-13B-GGUF is an AI language model created by TheBloke. It is a quantized version of Gryphe's MythoMax L2 13B model, which was an improved variant that merged MythoLogic-L2 and Huginn models using an experimental tensor merging technique. The quantized versions available from TheBloke provide a range of options with different bit depths and trade-offs between model size, RAM usage, and inference quality. Similar models include the MythoMax-L2-13B-GGML and MythoMax-L2-13B-GPTQ which offer different quantization formats. TheBloke has also provided quantized versions of other models like Llama-2-13B-chat-GGUF and CausalLM-14B-GGUF. Model inputs and outputs Inputs Text**: The model takes natural language text as input, which can include prompts, instructions, or conversational messages. Outputs Text**: The model generates fluent text responses, which can range from short answers to longer passages. The output is tailored to the input prompt and can cover a wide variety of topics. Capabilities The MythoMax-L2-13B-GGUF model is proficient at both roleplaying and storywriting due to its unique merging of the MythoLogic-L2 and Huginn models. It demonstrates strong language understanding and generation capabilities, allowing it to engage in coherent and contextual conversations. The model can be used for tasks such as creative writing, dialogue generation, and language understanding. What can I use it for? The MythoMax-L2-13B-GGUF model can be used for a variety of natural language processing tasks, particularly those involving creative writing and interactive dialogue. Some potential use cases include: Narrative generation**: Use the model to generate original stories, plot lines, and character dialogues. Interactive fiction**: Incorporate the model into interactive fiction or choose-your-own-adventure style experiences. Roleplaying assistant**: Leverage the model's capabilities to enable engaging roleplaying scenarios and character interactions. Conversational AI**: Utilize the model's language understanding and generation abilities to power chatbots or virtual assistants. Things to try One interesting aspect of the MythoMax-L2-13B-GGUF model is its blend of capabilities from the MythoLogic-L2 and Huginn models. You could explore the model's performance on tasks that require both robust language understanding and creative writing, such as generating coherent and engaging fictional narratives in response to open-ended prompts. Additionally, you could experiment with using the model as a roleplaying assistant, providing it with character profiles and scenario details to see how it responds and develops the interaction.
Updated Invalid Date