Yuna-7b-Merge / README.md
leaderboard-pr-bot's picture
Adding Evaluation Results
a9630ea verified
|
raw
history blame
4.01 kB
metadata
license: cc-by-4.0
tags:
  - mistral
  - merge
pipeline_tag: text-generation
model-index:
  - name: Yuna-7b-Merge
    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: 67.49
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/Yuna-7b-Merge
          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: 86.84
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/Yuna-7b-Merge
          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: 64.86
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/Yuna-7b-Merge
          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: 61.2
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/Yuna-7b-Merge
          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: 80.74
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/Yuna-7b-Merge
          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: 67.63
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/Yuna-7b-Merge
          name: Open LLM Leaderboard

Model Card for Argetsu

Experimental DARE (no idea if this is decent).

.yaml file for mergekit

models:
  - model: Dans-DiscountModels/Dans-07YahooAnswers-7b
    # no parameters necessary for base model
  - model: Azazelle/Maylin-7b #200
    parameters:
      weight: 0.45
      density: 0.75
  - model: Azazelle/smol_bruin-7b #175
    parameters:
      weight: 0.39
      density: 0.70
  - model: SanjiWatsuki/Kunoichi-7B #100
    parameters:
      weight: 0.22
      density: 0.52
merge_method: dare_ties
base_model: Dans-DiscountModels/Dans-07YahooAnswers-7b
parameters:
  int8_mask: true
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 71.46
AI2 Reasoning Challenge (25-Shot) 67.49
HellaSwag (10-Shot) 86.84
MMLU (5-Shot) 64.86
TruthfulQA (0-shot) 61.20
Winogrande (5-shot) 80.74
GSM8k (5-shot) 67.63