Yibuddy-35B / README.md
allknowingroger's picture
Adding Evaluation Results (#1)
fe9638b verified
metadata
license: apache-2.0
library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - 01-ai/Yi-1.5-34B-Chat
  - BattlescarZa/medibuddy-llm-34B
model-index:
  - name: Yibuddy-35B
    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: 42.35
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allknowingroger/Yibuddy-35B
          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: 42.81
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allknowingroger/Yibuddy-35B
          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: 12.24
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allknowingroger/Yibuddy-35B
          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: 14.09
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allknowingroger/Yibuddy-35B
          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: 15.97
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allknowingroger/Yibuddy-35B
          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: 38.77
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allknowingroger/Yibuddy-35B
          name: Open LLM Leaderboard

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

slices:
- sources:
  - model: 01-ai/Yi-1.5-34B-Chat
    layer_range:
    - 0
    - 60
  - model: BattlescarZa/medibuddy-llm-34B
    layer_range:
    - 0
    - 60
merge_method: slerp
base_model: 01-ai/Yi-1.5-34B-Chat
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: 0.38
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 27.70
IFEval (0-Shot) 42.35
BBH (3-Shot) 42.81
MATH Lvl 5 (4-Shot) 12.24
GPQA (0-shot) 14.09
MuSR (0-shot) 15.97
MMLU-PRO (5-shot) 38.77