README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - mistral
  - trl
  - sft
base_model: BarraHome/Mistroll-7B-v2.2
model-index:
  - name: fiona-7B-v0.2
    results:
      - task:
          type: text-generation
        metrics:
          - name: Average
            type: Average
            value: 69.5
        source:
          name: Open LLM Leaderboard
          url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
      - task:
          type: text-generation
        metrics:
          - name: AI2 Reasoning Challenge
            type: AI2 Reasoning Challenge
            value: 65.1
        source:
          name: Open LLM Leaderboard
          url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
      - task:
          type: text-generation
        metrics:
          - name: HellaSwag
            type: HellaSwag
            value: 85.49
        source:
          name: Open LLM Leaderboard
          url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
      - task:
          type: text-generation
        metrics:
          - name: MMLU
            type: MMLU
            value: 62.78
        source:
          name: Open LLM Leaderboard
          url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
      - task:
          type: text-generation
        metrics:
          - name: TruthfulQA
            type: TruthfulQA
            value: 56.53
        source:
          name: Open LLM Leaderboard
          url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
      - task:
          type: text-generation
        metrics:
          - name: Winogrande
            type: Winogrande
            value: 78.77
        source:
          name: Open LLM Leaderboard
          url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
      - task:
          type: text-generation
        metrics:
          - name: GSM8K
            type: GSM8K
            value: 68.31
        source:
          name: Open LLM Leaderboard
          url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
datasets:
  - niizam/fiona-sft

Uploaded model

• Developed by: niizam
• License: apache-2.0
• Finetuned from model : BarraHome/Mistroll-7B-v2.2

This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.