Blur-7b-slerp-v1.41 / README.md
limin(gate)
Adding Evaluation Results (#1)
50720e9 verified
metadata
license: apache-2.0
tags:
  - merge
  - mergekit
  - lazymergekit
  - bardsai/jaskier-7b-dpo-v5.6
  - liminerity/merge
model-index:
  - name: Blur-7b-slerp-v1.41
    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: 72.78
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/Blur-7b-slerp-v1.41
          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: 88.65
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/Blur-7b-slerp-v1.41
          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: 64.84
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/Blur-7b-slerp-v1.41
          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: 74.23
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/Blur-7b-slerp-v1.41
          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: 83.9
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/Blur-7b-slerp-v1.41
          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: 71.49
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=liminerity/Blur-7b-slerp-v1.41
          name: Open LLM Leaderboard

Blur-7b-slerp-v1.41

Blur-7b-slerp-v1.41 is a merge of the following models using mergekit:

🧩 Configuration

slices:
  - sources:
      - model: bardsai/jaskier-7b-dpo-v5.6
        layer_range: [0, 32]
      - model: liminerity/merge
        layer_range: [0, 32]
merge_method: slerp
base_model: bardsai/jaskier-7b-dpo-v5.6
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: 0.5
dtype: float16
#im pretty sure this will be bricked so

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 75.98
AI2 Reasoning Challenge (25-Shot) 72.78
HellaSwag (10-Shot) 88.65
MMLU (5-Shot) 64.84
TruthfulQA (0-shot) 74.23
Winogrande (5-shot) 83.90
GSM8k (5-shot) 71.49