README.md

metadata

license: apache-2.0
tags:
  - merge
model-index:
  - name: Mistral-CatMacaroni-slerp-gradient
    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: 65.53
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=diffnamehard/Mistral-CatMacaroni-slerp-gradient
          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: 85.66
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=diffnamehard/Mistral-CatMacaroni-slerp-gradient
          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: 61.53
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=diffnamehard/Mistral-CatMacaroni-slerp-gradient
          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: 64.1
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=diffnamehard/Mistral-CatMacaroni-slerp-gradient
          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: 80.03
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=diffnamehard/Mistral-CatMacaroni-slerp-gradient
          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: 57.62
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=diffnamehard/Mistral-CatMacaroni-slerp-gradient
          name: Open LLM Leaderboard

Slerp Merge of Mistral-7B-Instruct-v0.2 and cookinai/CatMacaroni-Slerp

.yaml file for mergekit

slices:
  - sources:
      - model: Mistral-7B-Instruct-v0.2
        layer_range: [0, 32]
      - model: CatMacaroni-Slerp-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: Mistral-7B-Instruct-v0.2
parameters:
  t:
    - value: [0, 0.3, 0.5, 0.7, 1]
dtype: float16

Metric	Value
Avg.	69.08
ARC (25-shot)	65.53
HellaSwag (10-shot)	85.66
MMLU (5-shot)	61.53
TruthfulQA (0-shot)	64.1
Winogrande (5-shot)	80.03
GSM8K (5-shot)	57.62

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	69.08
AI2 Reasoning Challenge (25-Shot)	65.53
HellaSwag (10-Shot)	85.66
MMLU (5-Shot)	61.53
TruthfulQA (0-shot)	64.10
Winogrande (5-shot)	80.03
GSM8k (5-shot)	57.62