README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - merge
model-index:
  - name: Marcoroni-v3-neural-chat-v3-3-Slerp
    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: 68.77
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Toten5/Marcoroni-v3-neural-chat-v3-3-Slerp
          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: 86.55
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Toten5/Marcoroni-v3-neural-chat-v3-3-Slerp
          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: 64.51
            name: accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Toten5/Marcoroni-v3-neural-chat-v3-3-Slerp
          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: 62.7
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Toten5/Marcoroni-v3-neural-chat-v3-3-Slerp
          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: 80.74
            name: accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Toten5/Marcoroni-v3-neural-chat-v3-3-Slerp
          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: 71.8
            name: accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Toten5/Marcoroni-v3-neural-chat-v3-3-Slerp
          name: Open LLM Leaderboard

Marcoroni-neural-chat-7B-v1

Model Details

This model is a merge of models AIDC-ai-business/Marcoroni-7B-v3 and Intel/neural-chat-7b-v3-3 using Slerp with mergekit tool for testing purposes. Both models are based on mistralai/Mistral-7B-v0.1.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	72.51
AI2 Reasoning Challenge (25-Shot)	68.77
HellaSwag (10-Shot)	86.55
MMLU (5-Shot)	64.51
TruthfulQA (0-shot)	62.70
Winogrande (5-shot)	80.74
GSM8k (5-shot)	71.80