leaderboard-pr-bot's picture
Adding Evaluation Results
8dd8087 verified
|
raw
history blame
4.21 kB
metadata
language:
  - en
  - ko
license: mit
datasets: We-Want-GPU/Yi-Ko-DPO-Orca-DPO-Pairs
pipeline_tag: text-generation
model-index:
  - name: FusionNet_7Bx2_MoE_Ko_DPO_Adapter_Attach
    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: 73.89
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=dddsaty/FusionNet_7Bx2_MoE_Ko_DPO_Adapter_Attach
          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=dddsaty/FusionNet_7Bx2_MoE_Ko_DPO_Adapter_Attach
          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: 65.03
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=dddsaty/FusionNet_7Bx2_MoE_Ko_DPO_Adapter_Attach
          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: 71.24
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=dddsaty/FusionNet_7Bx2_MoE_Ko_DPO_Adapter_Attach
          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: 87.61
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=dddsaty/FusionNet_7Bx2_MoE_Ko_DPO_Adapter_Attach
          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: 69.83
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=dddsaty/FusionNet_7Bx2_MoE_Ko_DPO_Adapter_Attach
          name: Open LLM Leaderboard

Explanation

  • With the base model, attached the DPO applied Adapter

Base Model

Adapter Base Model

Adapter Corpus

Score

Average ARC HellaSwag MMLU TruthfulQA Winogrande GSM8K
76.09 73.89 88.94 65.03 71.24 87.61 69.83

Log

  • 2024.02.13: Initial version Upload

LICENSE

  • MIT

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 76.09
AI2 Reasoning Challenge (25-Shot) 73.89
HellaSwag (10-Shot) 88.94
MMLU (5-Shot) 65.03
TruthfulQA (0-shot) 71.24
Winogrande (5-shot) 87.61
GSM8k (5-shot) 69.83