README.md

metadata

license: mit
tags:
  - moe
  - DPO
  - RL-TUNED
model-index:
  - name: Truthful_DPO_TomGrc_FusionNet_34Bx2_MoE
    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: 72.87
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Truthful_DPO_TomGrc_FusionNet_34Bx2_MoE
          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: 86.52
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Truthful_DPO_TomGrc_FusionNet_34Bx2_MoE
          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: 76.96
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Truthful_DPO_TomGrc_FusionNet_34Bx2_MoE
          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: 73.28
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Truthful_DPO_TomGrc_FusionNet_34Bx2_MoE
          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: 83.19
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Truthful_DPO_TomGrc_FusionNet_34Bx2_MoE
          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: 70.89
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Truthful_DPO_TomGrc_FusionNet_34Bx2_MoE
          name: Open LLM Leaderboard

• DPO Trainer with dataset jondurbin/truthy-dpo-v0.1 to improve [TomGrc/FusionNet_34Bx2_MoE]

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 improved by DPO 
![Metrsc improment](34bx2-dpo.jpg)

# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_cloudyu__Truthful_DPO_TomGrc_FusionNet_34Bx2_MoE)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |77.28|
|AI2 Reasoning Challenge (25-Shot)|72.87|
|HellaSwag (10-Shot)              |86.52|
|MMLU (5-Shot)                    |76.96|
|TruthfulQA (0-shot)              |73.28|
|Winogrande (5-shot)              |83.19|
|GSM8k (5-shot)                   |70.89|