README.md

metadata

license: apache-2.0
tags:
  - merge
  - mergekit
  - lazymergekit
  - FelixChao/WestSeverus-7B-DPO-v2
  - macadeliccc/WestLake-7B-v2-laser-truthy-dpo
model-index:
  - name: blockchainlabs_test3_seminar
    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: 72.18
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alnrg2arg/blockchainlabs_test3_seminar
          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: 88.94
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alnrg2arg/blockchainlabs_test3_seminar
          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: 64.63
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alnrg2arg/blockchainlabs_test3_seminar
          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: 72.47
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alnrg2arg/blockchainlabs_test3_seminar
          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: 85.64
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alnrg2arg/blockchainlabs_test3_seminar
          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: 70.36
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alnrg2arg/blockchainlabs_test3_seminar
          name: Open LLM Leaderboard

blockchainlabs_test3_seminar

blockchainlabs_test3_seminar is a merge of the following models using mergekit:

• FelixChao/WestSeverus-7B-DPO-v2
• macadeliccc/WestLake-7B-v2-laser-truthy-dpo

🧩 Configuration

slices:
  - sources:
      - model: FelixChao/WestSeverus-7B-DPO-v2
        layer_range: [0, 32]
      - model: macadeliccc/WestLake-7B-v2-laser-truthy-dpo
        layer_range: [0, 32]
merge_method: slerp
base_model: FelixChao/WestSeverus-7B-DPO-v2 
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: #bfloat16 #bfloat16이 float16보다 학습할때 더 빠릅니다.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	75.70
AI2 Reasoning Challenge (25-Shot)	72.18
HellaSwag (10-Shot)	88.94
MMLU (5-Shot)	64.63
TruthfulQA (0-shot)	72.47
Winogrande (5-shot)	85.64
GSM8k (5-shot)	70.36