StarDust-12b-v2/README.md

---
language:
- en
license: apache-2.0
tags:
- chat
- mistral
- roleplay
- creative-writing
base_model:
- nbeerbower/mistral-nemo-bophades-12B
- anthracite-org/magnum-v2-12b
- Sao10K/MN-12B-Lyra-v3
- Gryphe/Pantheon-RP-1.6-12b-Nemo
pipeline_tag: text-generation
model-index:
- name: StarDust-12b-v2
  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: 56.29
      name: strict accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Luni/StarDust-12b-v2
      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: 34.95
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Luni/StarDust-12b-v2
      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: 5.97
      name: exact match
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Luni/StarDust-12b-v2
      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: 5.82
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Luni/StarDust-12b-v2
      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: 14.26
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Luni/StarDust-12b-v2
      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: 27.1
      name: accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Luni/StarDust-12b-v2
      name: Open LLM Leaderboard
library_name: transformers
---

![image/png](https://cdn-uploads.huggingface.co/production/uploads/6303fa71fc783bfc7443e7ae/c3ddWBoz-lINEykUDCoXy.png)

![image/png](https://cdn-uploads.huggingface.co/production/uploads/6303fa71fc783bfc7443e7ae/hOpgDxJS2sDO7HzuC9e18.png)


# StarDust-12b-v2

## Quants

- GGUF: [mradermacher/StarDust-12b-v2-GGUF](https://huggingface.co/mradermacher/StarDust-12b-v2-GGUF)
- weighted/imatrix GGUF: [mradermacher/StarDust-12b-v2-i1-GGUF](https://huggingface.co/mradermacher/StarDust-12b-v2-i1-GGUF/tree/main)
- exl2: [lucyknada/Luni_StarDust-12b-v2-exl2](https://huggingface.co/lucyknada/Luni_StarDust-12b-v2-exl2)

## Description | Usecase

- The result of this merge is in my opinion a more vibrant and less generic sonnet inspired prose, it's able to be gentle and harsh where asked.
- The v2 uses the non-kto magnum which tends to have less "claudeism" (making the story feel rather repetitive)
- Note on Non-Kto: There is a very big gap between people preferring and disliking the KTO. To make things easier, you can still use [Luni/StarDust-12b-v1](https://huggingface.co/Luni/StarDust-12b-v1) which has the KTO version.
- In early testing users have reported a much better experience in longer roleplays and a abillity to add a creative touch to the stable experience.

Just like with v1:
- This model is intended to be used as a Role-playing model.
- Its direct conversational output is... I can't even say it's luck, it's just not made for it.
- Extension to Conversational output: The Model is designed for roleplay, direct instructing or general purpose is NOT recommended.
- It can be used with simple setup to be used as an "Agent" by forcing it into an "impersonation" of a character which works very well but sometimes narratives sneak in.

## Initial Feedback

- Initial feedback has proven the model to be a solid "go-to" choice for creative storywriting
- The prose has been certified as "amazing" with many making it their default model.


## Prompting

### ChatML has proven to be the BEST choice.

Both Mistral and ChatML should work though I had better results with ChatML:
ChatML Example:
```py
"""<|im_start|>user
Hi there!<|im_end|>
<|im_start|>assistant
Nice to meet you!<|im_end|>
<|im_start|>user
Can I ask a question?<|im_end|>
<|im_start|>assistant
"""
```



## Merge Details
### Merge Method

This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [Sao10K/MN-12B-Lyra-v3](https://huggingface.co/Sao10K/MN-12B-Lyra-v3) as a base.

### Models Merged

The following models were included in the merge:
* [nbeerbower/mistral-nemo-bophades-12B](https://huggingface.co/nbeerbower/mistral-nemo-bophades-12B)
* [anthracite-org/magnum-v2-12b](https://huggingface.co/anthracite-org/magnum-v2-12b)
* [Gryphe/Pantheon-RP-1.6-12b-Nemo](https://huggingface.co/Gryphe/Pantheon-RP-1.6-12b-Nemo)
* [Sao10K/MN-12B-Lyra-v3](https://huggingface.co/Sao10K/MN-12B-Lyra-v3)

### Special Thanks

Special thanks to the SillyTilly and myself for helping me find the energy to finish this.
# [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/details_Luni__StarDust-12b-v2)

|      Metric       |Value|
|-------------------|----:|
|Avg.               |24.06|
|IFEval (0-Shot)    |56.29|
|BBH (3-Shot)       |34.95|
|MATH Lvl 5 (4-Shot)| 5.97|
|GPQA (0-shot)      | 5.82|
|MuSR (0-shot)      |14.26|
|MMLU-PRO (5-shot)  |27.10|