README.md

---
language:
- en
license: creativeml-openrail-m
tags:
- text generation
- conversational
inference: false
model-index:
- name: pygmalion-6b
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: IFEval (0-Shot)
      type: HuggingFaceH4/ifeval
      args:
        num_few_shot: 0
    metrics:
    - type: inst_level_strict_acc and prompt_level_strict_acc
      value: 20.91
      name: strict accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PygmalionAI/pygmalion-6b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: BBH (3-Shot)
      type: BBH
      args:
        num_few_shot: 3
    metrics:
    - type: acc_norm
      value: 5.09
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PygmalionAI/pygmalion-6b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MATH Lvl 5 (4-Shot)
      type: hendrycks/competition_math
      args:
        num_few_shot: 4
    metrics:
    - type: exact_match
      value: 0.83
      name: exact match
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PygmalionAI/pygmalion-6b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GPQA (0-shot)
      type: Idavidrein/gpqa
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 0.0
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PygmalionAI/pygmalion-6b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MuSR (0-shot)
      type: TAUR-Lab/MuSR
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 3.71
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PygmalionAI/pygmalion-6b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU-PRO (5-shot)
      type: TIGER-Lab/MMLU-Pro
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 2.04
      name: accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PygmalionAI/pygmalion-6b
      name: Open LLM Leaderboard
---

# Pygmalion 6B

## Model description

Pymalion 6B is a proof-of-concept dialogue model based on EleutherAI's [GPT-J-6B](https://huggingface.co/EleutherAI/gpt-j-6B).

**Warning:** This model is **NOT** suitable for use by minors. It **will** output X-rated content under certain circumstances.

## Training data

The fine-tuning dataset consisted of 56MB of dialogue data gathered from multiple sources, which includes both real _and_ partially machine-generated conversations.

## Training procedure

Model weights were initialized from the `uft-6b` ConvoGPT model made available in [this commit](https://huggingface.co/hakurei/convogpt/tree/41b67bfddb6cd97070ffddf708e9720c9cb8d224/6b-uft).

The model was then further fine-tuned on ~48.5 million tokens for ~5k steps on 4 NVIDIA A40s using DeepSpeed.

## Intended use

### The easy way

We provide a notebook with a Gradio UI for playing around with the model without having to manually format inputs. This notebook can be found [here](https://github.com/PygmalionAI/gradio-ui/blob/master/notebooks/GPU.ipynb).

### The manual way

The model can be used as a regular text generation model, but it'll perform best if the input prompt adheres to the following format:

```
[CHARACTER]'s Persona: [A few sentences about the character you want the model to play]
<START>
[DIALOGUE HISTORY]
You: [Your input message here]
[CHARACTER]:
```

Where `[CHARACTER]` is, as you can probably guess, the name of the character you want the model to portray, `<START>` should be used verbatim as a delimiter token to separate persona and scenario data from the dialogue, and `[DIALOGUE HISTORY]` is chat history so the model can have some conversational context to draw from. Ideally it'll be pairs of messages like:

```
[CHARACTER]: [some dialogue here]
You: [your response to the dialogue above]
```

Apart from chat history, you can also just add example conversations in `[DIALOGUE HISTORY]` to show how the character should speak - ideally at the beginning, so it doesn't get confused as to what's conversation history vs. character definition.

## Known issues

We haven't played around with the model enough to enumerate them. Feel free to give us some feedback!

# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/PygmalionAI__pygmalion-6b-details)

|      Metric       |Value|
|-------------------|----:|
|Avg.               | 5.43|
|IFEval (0-Shot)    |20.91|
|BBH (3-Shot)       | 5.09|
|MATH Lvl 5 (4-Shot)| 0.83|
|GPQA (0-shot)      | 0.00|
|MuSR (0-shot)      | 3.71|
|MMLU-PRO (5-shot)  | 2.04|