spow12_-_ChatWaifu_22B_v2.0_preview-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

ChatWaifu_22B_v2.0_preview - GGUF

• Model creator: https://huggingface.co/spow12/
• Original model: https://huggingface.co/spow12/ChatWaifu_22B_v2.0_preview/

Original model description:

language:

• en
• ja license: cc-by-nc-4.0 library_name: transformers tags:
• nsfw
• Visual novel
• roleplay
• mergekit
• merge base_model:
• mistralai/Mistral-Small-Instruct-2409 datasets:
• roleplay4fun/aesir-v1.1
• kalomaze/Opus_Instruct_3k
• Gryphe/Sonnet3.5-SlimOrcaDedupCleaned
• Aratako/Synthetic-Japanese-Roleplay-gpt-4o-mini-39.6k-formatted
• Aratako/Synthetic-Japanese-Roleplay-NSFW-Claude-3.5s-15.3k-formatted
• SkunkworksAI/reasoning-0.01 pipeline_tag: text-generation model-index:
• name: ChatWaifu_22B_v2.0_preview 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: 67.45 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=spow12/ChatWaifu_22B_v2.0_preview 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: 45.49 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=spow12/ChatWaifu_22B_v2.0_preview 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: 16.31 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=spow12/ChatWaifu_22B_v2.0_preview 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: 8.72 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=spow12/ChatWaifu_22B_v2.0_preview 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: 3.53 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=spow12/ChatWaifu_22B_v2.0_preview 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: 33.2 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=spow12/ChatWaifu_22B_v2.0_preview name: Open LLM Leaderboard

---

Model Card for Model ID

Merged model using mergekit

This model aimed to act like visual novel character.

Merge Format

models:
  - model: mistralai/Mistral-Small-Instruct-2409_SFT
    layer_range: [0, 56]
  - model: mistralai/Mistral-Small-Instruct-2409
    layer_range: [0, 56]
merge_method: slerp
base_model: mistralai/Mistral-Small-Instruct-2409_SFT
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5 # fallback for rest of tensors
dtype: bfloat16

WaifuModel Collections

• TTS
• Chat
• ASR

Unified demo

WaifuAssistant

Update 2.0

• 2024.09.23 Update 22B, Ver 2.0

Model Details

Model Description

• Developed by: spow12(yw_nam)
• Shared by : spow12(yw_nam)
• Model type: CausalLM
• Language(s) (NLP): japanese. English
• Finetuned from model : mistralai/Mistral-Small-Instruct-2409

Currently, chatbot has below personality.

But you can chat your own Character with persona text.

Feel free to test.

Your feedback will be helpful for improving model.

Dataset

Riddle Joker(Prviate)

Café Stella and the Reaper's Butterflies(Private)

Senren＊Banka(Private)

roleplay4fun/aesir-v1.1

kalomaze/Opus_Instruct_3k

Gryphe/Sonnet3.5-SlimOrcaDedupCleaned

Aratako/Synthetic-JP-EN-Coding-Dataset-567k (only using 50000 sample)

Aratako/Synthetic-Japanese-Roleplay-gpt-4o-mini-39.6k-formatted

Aratako/Synthetic-Japanese-Roleplay-NSFW-Claude-3.5s-15.3k-formatted

SkunkworksAI/reasoning-0.01

Feature

• Fluent Chat performance
• Reduce repetition problem when generate with many turn(over 20~30)
• Zero Shot character persona using description of character.
• 128k context window
• Memory ability that does not forget even after long-context generation

Demo

You can use Demo in google colab.

Check Here

Bias, Risks, and Limitations

This model can generate NSFW content.

Use & Credit

This model is currently available for non-commercial & Research purpose only.

Also, since I'm not detailed in licensing, I hope you use this model responsibly.

By sharing this model, I hope to contribute to the research efforts of our community (the open-source community and Waifu Lovers).

Citation

@misc {ChatWaifu_22B_v2.0
    author       = { YoungWoo Nam },
    title        = { ChatWaifu_22B_v2.0_preview },
    year         = 2024,
    url          = { https://huggingface.co/spow12/ChatWaifu_22B_v2.0_preview },
    publisher    = { Hugging Face }
}

Open LLM Leaderboard Evaluation Results

Detailed results can be found here