Maylin-7b / README.md
leaderboard-pr-bot's picture
Adding Evaluation Results
0db3061 verified
|
raw
history blame
3.98 kB
metadata
license: cc-by-4.0
tags:
  - mistral
  - merge
pipeline_tag: text-generation
model-index:
  - name: Maylin-7b
    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: 66.81
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/Maylin-7b
          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: 86.4
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/Maylin-7b
          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: 64.73
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/Maylin-7b
          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: 60.24
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/Maylin-7b
          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: 79.64
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/Maylin-7b
          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: 63.76
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/Maylin-7b
          name: Open LLM Leaderboard

Model Card for Maylin-7b

DARE merge intended to help the Argetsu model be more coherent and less horny.

.yaml file for mergekit

models:
  - model: mistralai/Mistral-7B-v0.1
    # no parameters necessary for base model
  - model: SanjiWatsuki/Sonya-7B #200
    parameters:
      weight: 0.45
      density: 0.75
  - model: Azazelle/Argetsu #175
    parameters:
      weight: 0.39
      density: 0.70
  - model: Azazelle/Tippy-Toppy-7b #100
    parameters:
      weight: 0.22
      density: 0.52
merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
  int8_mask: true
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 70.26
AI2 Reasoning Challenge (25-Shot) 66.81
HellaSwag (10-Shot) 86.40
MMLU (5-Shot) 64.73
TruthfulQA (0-shot) 60.24
Winogrande (5-shot) 79.64
GSM8k (5-shot) 63.76