metadata
license: apache-2.0
tags:
  - merge
  - mergekit
  - lazymergekit
  - Qwen/Qwen1.5-72B-Chat
  - vilm/Quyen-Pro-Max-v0.1
model-index:
  - name: ECE-TW3-JRGL-V2
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: IFEval (0-Shot)
          type: HuggingFaceH4/ifeval
          args:
            num_few_shot: 0
        metrics:
          - type: inst_level_strict_acc and prompt_level_strict_acc
            value: 22.55
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=paloalma/ECE-TW3-JRGL-V2
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: BBH (3-Shot)
          type: BBH
          args:
            num_few_shot: 3
        metrics:
          - type: acc_norm
            value: 43.17
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=paloalma/ECE-TW3-JRGL-V2
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MATH Lvl 5 (4-Shot)
          type: hendrycks/competition_math
          args:
            num_few_shot: 4
        metrics:
          - type: exact_match
            value: 16.31
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=paloalma/ECE-TW3-JRGL-V2
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GPQA (0-shot)
          type: Idavidrein/gpqa
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 10.85
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=paloalma/ECE-TW3-JRGL-V2
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MuSR (0-shot)
          type: TAUR-Lab/MuSR
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 19.82
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=paloalma/ECE-TW3-JRGL-V2
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU-PRO (5-shot)
          type: TIGER-Lab/MMLU-Pro
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 39.86
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=paloalma/ECE-TW3-JRGL-V2
          name: Open LLM Leaderboard
ECE-TW3-JRGL-V2

ECE-TW3-JRGL-V2 is a merge of the following models using mergekit:
🧩 Configuration

Open LLM Leaderboard Evaluation Results

Detailed results can be found here
Metric	Value
Avg.	25.43
IFEval (0-Shot)	22.55
BBH (3-Shot)	43.17
MATH Lvl 5 (4-Shot)	16.31
GPQA (0-shot)	10.85
MuSR (0-shot)	19.82
MMLU-PRO (5-shot)	39.86