README.md

---
language:
- en
license: llama2
tags:
- text generation
- instruct
datasets:
- PygmalionAI/PIPPA
- Open-Orca/OpenOrca
- Norquinal/claude_multiround_chat_30k
- jondurbin/airoboros-gpt4-1.4.1
- databricks/databricks-dolly-15k
pipeline_tag: text-generation
inference: false
model-index:
- name: pygmalion-2-13b
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: AI2 Reasoning Challenge (25-Shot)
      type: ai2_arc
      config: ARC-Challenge
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: acc_norm
      value: 60.32
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PygmalionAI/pygmalion-2-13b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: HellaSwag (10-Shot)
      type: hellaswag
      split: validation
      args:
        num_few_shot: 10
    metrics:
    - type: acc_norm
      value: 82.37
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PygmalionAI/pygmalion-2-13b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU (5-Shot)
      type: cais/mmlu
      config: all
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 56.02
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PygmalionAI/pygmalion-2-13b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: TruthfulQA (0-shot)
      type: truthful_qa
      config: multiple_choice
      split: validation
      args:
        num_few_shot: 0
    metrics:
    - type: mc2
      value: 42.22
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PygmalionAI/pygmalion-2-13b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Winogrande (5-shot)
      type: winogrande
      config: winogrande_xl
      split: validation
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 78.06
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PygmalionAI/pygmalion-2-13b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GSM8k (5-shot)
      type: gsm8k
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 11.75
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PygmalionAI/pygmalion-2-13b
      name: Open LLM Leaderboard
---
<h1 style="text-align: center">Pygmalion-2 13B</h1>
<h2 style="text-align: center">An instruction-tuned Llama-2 biased towards fiction writing and conversation.</h2>

## Model Details

The long-awaited release of our new models based on Llama-2 is finally here. Pygmalion-2 13B (formerly known as Metharme) is based on
[Llama-2 13B](https://huggingface.co/meta-llama/llama-2-13b-hf) released by Meta AI. 

The Metharme models were an experiment to try and get a model that is usable for conversation, roleplaying and storywriting, 
but which can be guided using natural language like other instruct models. After much deliberation, we reached the conclusion
that the Metharme prompting format is superior (and easier to use) compared to the classic Pygmalion. 

This model was trained by doing supervised fine-tuning over a mixture of regular instruction data alongside roleplay, fictional stories
and conversations with synthetically generated instructions attached.

This model is freely available for both commercial and non-commercial use, as per the Llama-2 license.


## Prompting

The model has been trained on prompts using three different roles, which are denoted by the following tokens: `<|system|>`, `<|user|>` and `<|model|>`.

The `<|system|>` prompt can be used to inject out-of-channel information behind the scenes, while the `<|user|>` prompt should be used to indicate user input.
The `<|model|>` token should then be used to indicate that the model should generate a response. These tokens can happen multiple times and be chained up to
form a conversation history.

### Prompting example

The system prompt has been designed to allow the model to "enter" various modes and dictate the reply length. Here's an example:

```
<|system|>Enter RP mode. Pretend to be {{char}} whose persona follows:
{{persona}}

You shall reply to the user while staying in character, and generate long responses.
```

## Dataset
The dataset used to fine-tune this model includes our own [PIPPA](https://huggingface.co/datasets/PygmalionAI/PIPPA), along with several other instruction
datasets, and datasets acquired from various RP forums.

## Limitations and biases

The intended use-case for this model is fictional writing for entertainment purposes. Any other sort of usage is out of scope.

As such, it was **not** fine-tuned to be safe and harmless: the base model _and_ this fine-tune have been trained on data known to contain profanity and texts that are lewd or otherwise offensive. It may produce socially unacceptable or undesirable text, even if the prompt itself does not include anything explicitly offensive. Outputs might often be factually wrong or misleading.

## Acknowledgements
We would like to thank [SpicyChat](https://spicychat.ai/) for sponsoring the training for this model.

[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)

# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_PygmalionAI__pygmalion-2-13b)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |55.12|
|AI2 Reasoning Challenge (25-Shot)|60.32|
|HellaSwag (10-Shot)              |82.37|
|MMLU (5-Shot)                    |56.02|
|TruthfulQA (0-shot)              |42.22|
|Winogrande (5-shot)              |78.06|
|GSM8k (5-shot)                   |11.75|