README.md

metadata

license: apache-2.0
model-index:
  - name: Nous-Hermes-2-MoE-2x34B
    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: 66.64
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/Nous-Hermes-2-MoE-2x34B
          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: 85.73
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/Nous-Hermes-2-MoE-2x34B
          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: 76.49
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/Nous-Hermes-2-MoE-2x34B
          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: 58.08
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/Nous-Hermes-2-MoE-2x34B
          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: 83.35
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/Nous-Hermes-2-MoE-2x34B
          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: 69.52
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/Nous-Hermes-2-MoE-2x34B
          name: Open LLM Leaderboard

This is an experimental model to make an MoE of Nous Hermes 2 Yi 34B as Mixture of Expert.

The base model is Yi-34B.

All credits belong to NousResearch for fine tuned Yi model, 01-AI for Yi model, and Charles O. Goddard for the 'mergekit'.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	73.30
AI2 Reasoning Challenge (25-Shot)	66.64
HellaSwag (10-Shot)	85.73
MMLU (5-Shot)	76.49
TruthfulQA (0-shot)	58.08
Winogrande (5-shot)	83.35
GSM8k (5-shot)	69.52