README.md

metadata

language:
  - en
  - de
  - fr
  - it
  - es
license: apache-2.0
library_name: adapter-transformers
datasets:
  - Open-Orca/SlimOrca
  - argilla/distilabel-intel-orca-dpo-pairs
pipeline_tag: text-generation
model-index:
  - name: Mixtral-8x7b-DPO-v0.2
    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: 70.39
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Swisslex/Mixtral-8x7b-DPO-v0.2
          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: 87.73
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Swisslex/Mixtral-8x7b-DPO-v0.2
          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: 71.03
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Swisslex/Mixtral-8x7b-DPO-v0.2
          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: 58.69
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Swisslex/Mixtral-8x7b-DPO-v0.2
          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: 82.56
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Swisslex/Mixtral-8x7b-DPO-v0.2
          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: 57.54
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Swisslex/Mixtral-8x7b-DPO-v0.2
          name: Open LLM Leaderboard

Model Card for Model Swisslex/Mixtral-8x7b-DPO-v0.2

Model Details

Model Description

Finetuned version of mistralai/Mixtral-8x7B-v0.2 using SFT and DPO.

• Developed by: Swisslex
• Language(s) (NLP): English, German, French, Italian, Spanish
• License: apache-2.0
• Finetuned from model [optional]: mistralai/Mixtral-8x7B-v0.2

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	71.32
AI2 Reasoning Challenge (25-Shot)	70.39
HellaSwag (10-Shot)	87.73
MMLU (5-Shot)	71.03
TruthfulQA (0-shot)	58.69
Winogrande (5-shot)	82.56
GSM8k (5-shot)	57.54