ECE-TW3-JRGL-V1 / README.md
leaderboard-pr-bot's picture
Adding Evaluation Results
3288a90 verified
|
raw
history blame
5.29 kB
metadata
license: apache-2.0
tags:
  - merge
  - mergekit
  - ShinojiResearch/Senku-70B-Full
  - 152334H/miqu-1-70b-sf
model-index:
  - name: ECE-TW3-JRGL-V1
    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: 55.35
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=paloalma/ECE-TW3-JRGL-V1
          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: 46.7
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=paloalma/ECE-TW3-JRGL-V1
          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: 11.86
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=paloalma/ECE-TW3-JRGL-V1
          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: 12.98
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=paloalma/ECE-TW3-JRGL-V1
          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: 17.46
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=paloalma/ECE-TW3-JRGL-V1
          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: 35.79
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=paloalma/ECE-TW3-JRGL-V1
          name: Open LLM Leaderboard

ECE-TW3-JRGL-V1

This model has been produced by :

Under the supervision of :

With the contribution of :

  • ECE engineering school as sponsor and financial contributor
  • RunPod as financial contributor

About ECE

ECE, a multi-program, multi-campus, and multi-sector engineering school specializing in digital engineering, trains engineers and technology experts for the 21st century, capable of meeting the challenges of the dual digital and sustainable development revolutions. French Engineering School ECE

Description

ECE-TW3-JRGL-V1 is a merge of the following models using mergekit:

slices:
  - sources:
      - model: ShinojiResearch/Senku-70B-Full
        layer_range: [0, 80]
      - model: 152334H/miqu-1-70b-sf
        layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
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

Results


@misc{paech2023eqbench, title={EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models}, author={Samuel J. Paech}, year={2023}, eprint={2312.06281}, archivePrefix={arXiv}, primaryClass={cs.CL} }

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 30.02
IFEval (0-Shot) 55.35
BBH (3-Shot) 46.70
MATH Lvl 5 (4-Shot) 11.86
GPQA (0-shot) 12.98
MuSR (0-shot) 17.46
MMLU-PRO (5-shot) 35.79