README.md

metadata

language:
  - en
license: cc-by-nc-4.0
model-index:
  - name: KuroMitsu-11B
    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: 70.31
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Himitsui/KuroMitsu-11B
          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: 88.07
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Himitsui/KuroMitsu-11B
          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: 66.66
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Himitsui/KuroMitsu-11B
          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: 61.36
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Himitsui/KuroMitsu-11B
          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: 84.69
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Himitsui/KuroMitsu-11B
          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: 64.37
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Himitsui/KuroMitsu-11B
          name: Open LLM Leaderboard

Included in this repo is the full model for KuroMitsu-11B

(☯‿├┬┴┬┴┬┴┬┴┤(･_├┬┴┬┴┬┴┬┴┤･ω･)ﾉ

Hiya! This is my 11B Solar Finetune.

Included in the dataset I used to train are hateful and toxic entries. Along with rows of chat, roleplay and instruct entries. The goal was to make a roleplaying model that is uncensored. (・_・ヾ)

The prompt format Vicuna or Alpaca works well with this model.

I hope this model may be useful to you 💜

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	72.58
AI2 Reasoning Challenge (25-Shot)	70.31
HellaSwag (10-Shot)	88.07
MMLU (5-Shot)	66.66
TruthfulQA (0-shot)	61.36
Winogrande (5-shot)	84.69
GSM8k (5-shot)	64.37