README.md

metadata

language:
  - fr
  - it
  - de
  - es
  - en
license: apache-2.0
tags:
  - moe
model-index:
  - name: Mixtral-8x7B-Instruct-v0.1-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: 69.8
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral-8x7B-Instruct-v0.1-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: 87.83
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral-8x7B-Instruct-v0.1-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: 71.05
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral-8x7B-Instruct-v0.1-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: 69.18
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral-8x7B-Instruct-v0.1-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: 81.37
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral-8x7B-Instruct-v0.1-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: 61.41
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO
          name: Open LLM Leaderboard

Model Card for cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO

• try to improve mistralai/Mixtral-8x7B-Instruct-v0.1 by DPO training

• DPO Trainer

Metrics improved by Truthful DPO traingin after 100 steps

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	73.44
AI2 Reasoning Challenge (25-Shot)	69.80
HellaSwag (10-Shot)	87.83
MMLU (5-Shot)	71.05
TruthfulQA (0-shot)	69.18
Winogrande (5-shot)	81.37
GSM8k (5-shot)	61.41