README.md

metadata

license: other
tags:
  - yi
  - moe
license_name: yi-license
license_link: https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE
model-index:
  - name: TomGrc_FusionNet_34Bx2_MoE_v0.1_full_linear_DPO
    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: 74.06
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/TomGrc_FusionNet_34Bx2_MoE_v0.1_full_linear_DPO
          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: 86.67
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/TomGrc_FusionNet_34Bx2_MoE_v0.1_full_linear_DPO
          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: 76.69
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/TomGrc_FusionNet_34Bx2_MoE_v0.1_full_linear_DPO
          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: 71.32
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/TomGrc_FusionNet_34Bx2_MoE_v0.1_full_linear_DPO
          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: 83.43
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/TomGrc_FusionNet_34Bx2_MoE_v0.1_full_linear_DPO
          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: 72.93
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/TomGrc_FusionNet_34Bx2_MoE_v0.1_full_linear_DPO
          name: Open LLM Leaderboard

this is another DPO all-linear-parameter-fine-tuned MoE model for TomGrc/FusionNet_34Bx2_MoE_v0.1

it's trained on a H100 for one hour

DPO Trainer
TRL supports the DPO Trainer for training language models from preference data, as described in the paper Direct Preference Optimization: Your Language Model is Secretly a Reward Model by Rafailov et al., 2023. 

Metrics not test!

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	77.52
AI2 Reasoning Challenge (25-Shot)	74.06
HellaSwag (10-Shot)	86.67
MMLU (5-Shot)	76.69
TruthfulQA (0-shot)	71.32
Winogrande (5-shot)	83.43
GSM8k (5-shot)	72.93