README.md

metadata

language:
  - zh
  - en
license: apache-2.0
library_name: transformers
tags:
  - llm
  - long context
  - yi
  - chat
  - it
  - abliterated
base_model: 01-ai/Yi-1.5-9B-Chat
pipeline_tag: text-generation
model-index:
  - name: Yi-1.5-9B-Chat-abliterated
    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: 57.23
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=byroneverson/Yi-1.5-9B-Chat-abliterated
          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: 34.35
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=byroneverson/Yi-1.5-9B-Chat-abliterated
          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: 9.82
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=byroneverson/Yi-1.5-9B-Chat-abliterated
          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: 5.59
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=byroneverson/Yi-1.5-9B-Chat-abliterated
          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: 13.66
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=byroneverson/Yi-1.5-9B-Chat-abliterated
          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: 30.17
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=byroneverson/Yi-1.5-9B-Chat-abliterated
          name: Open LLM Leaderboard

Yi-1.5-9B-Chat-abliterated

Check out the jupyter notebook for details of how this model was abliterated from Yi-1.5-9B-Chat.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	25.14
IFEval (0-Shot)	57.23
BBH (3-Shot)	34.35
MATH Lvl 5 (4-Shot)	9.82
GPQA (0-shot)	5.59
MuSR (0-shot)	13.66
MMLU-PRO (5-shot)	30.17