README.md

---
language:
  - en
pipeline_tag: text-generation
tags:
  - unsloth
  - axolotl
---

# DreamGen Opus V1

<div style="display: flex; flex-direction: row; align-items: center;">
<img src="/dreamgen/opus-v1-34b/resolve/main/images/logo-1024.png" alt="model logo" style="
    border-radius: 12px;
    margin-right: 12px;
    margin-top: 0px;
    margin-bottom: 0px;
    max-width: 100px;
    height: auto;
"/>

Models for **(steerable) story-writing and role-playing**.
<br/>[All Opus V1 models, including quants](https://huggingface.co/collections/dreamgen/opus-v1-65d092a6f8ab7fc669111b31).

</div>

## Prompting

[Read the full Opus V1 prompting guide](https://dreamgen.com/docs/models/opus/v1) with many (interactive) examples and prompts that you can readily copy.

<details>
<summary>The models use an extended version of ChatML.</summary>

```
<|im_start|>system
(Story description in the right format here)
(Typically consists of plot description, style description and characters)<|im_end|>
<|im_start|>user
(Your instruction on how the story should continue)<|im_end|>
<|im_start|>text names= Alice
(Continuation of the story from the Alice character)<|im_end|>
<|im_start|>text
(Continuation of the story from no character in particular (pure narration))<|im_end|>
<|im_start|>user
(Your instruction on how the story should continue)<|im_end|>
<|im_start|>text names= Bob
(Continuation of the story from the Bob character)<|im_end|>
```

The Opus V1 extension is the addition of the `text` role, and the addition / modification of role names.

Pay attention to the following:

- The `text` messages can (but don't have to have) `names`, names are used to indicate the "active" character during role-play.
- There can be multiple subsequent message with a `text` role, especially if names are involved.
- There can be multiple names attached to a message.
- The format for names is `names= {{name[0]}}; {{name[1]}}`, beware of the spaces after `names=` and after the `;`. This spacing leads to most natural tokenization for the names.
</details>

While the main goal for the models is great story-writing and role-playing performance, the models are also capable of several writing related tasks as well as general assistance.

<img src="/dreamgen/opus-v1-34b/resolve/main/images/story_writing.webp" alt="story writing" style="
    padding: 12px;
    border-radius: 12px;
    border: 2px solid #f9a8d4;
    background: rgb(9, 9, 11);
"/>

Here's how you can prompt the model for the following tasks

- Steerable [Story-writing](https://dreamgen.com/docs/models/opus/v1#task-story-writing) and [Role-playing](https://dreamgen.com/docs/models/opus/v1#task-role-playing):
  - Input:
    - System prompt: You provide story / role-play description, which consists of:
      - Plot description
      - Style description
      - Characters and their descriptions
    - Conversation turns:
      - Text / message turn: This represents part of the story or role play
      - Instruction: This tells the model what should happen next
  - Output: Continuation of the story / role-play.
- [Story plot summarization](https://dreamgen.com/docs/models/opus/v1#task-plot-description)
  - Input: A story, or a few chapters of a story.
  - Output: A description of the story or chapters.
- [Story character description](https://dreamgen.com/docs/models/opus/v1#task-char-description)
  - Input: A story, or a few chapters of a story, set of characters.
  - Output: A description of the characters.
- [Story style description](https://dreamgen.com/docs/models/opus/v1#task-style-description)
  - Input: A story, or a few chapters of a story.
  - Output: A description the style of the story.
- [Story description to chapters](https://dreamgen.com/docs/models/opus/v1#task-story-description-to-chapter-descriptions)
  - Input: A brief plot description and the desired number of chapters.
  - Output: A description for each chapter.
- And more...

### Sampling params

For story-writing and role-play, I recommend "Min P" based sampling with `min_p` in the range `[0.01, 0.1]` and with `temperature` in the range `[0.5, 1.5]`, depending on your preferences. A good starting point would be `min_p=0.1; temperature=0.8`.

You may also benefit from setting presence, frequency and repetition penalties, especially at lower temperatures.

## Dataset

The fine-tuning dataset consisted of ~100M tokens of steerable story-writing, role-playing, writing-assistant and general-assistant examples. Each example was up to 31000 tokens long.

All story-writing and role-playing examples were based on human-written text.

![token count distribution](images/token_count_cum__token_bucket.png)

## Running the model

The model is should be compatible with any software that supports the base model, but beware of the prompting (see above).

### Running Locally

- [Chat template from model config](tokenizer_config.json#L51)
  - This uses "text" role instead of the typical "assistant" role, and it does not (can’t?) support names
- [LM Studio config](configs/lmstudio.json)
  - This uses "text" role role as well

### Running on DreamGen.com (free)

You can try the model for free on [dreamgen.com](https://dreamgen.com) — note that an account is required.

## Community

Join the DreamGen community on [**Discord**](https://dreamgen.com/discord) to get early access to new models.

## License

- This model is intended for personal use only, other use is not permitted.