README.md

metadata

model-index:
  - name: orthogonal-2x7B-v2-base
    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: 66.89
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=LoSboccacc/orthogonal-2x7B-v2-base
          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: 85.69
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=LoSboccacc/orthogonal-2x7B-v2-base
          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: 62.65
            name: accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=LoSboccacc/orthogonal-2x7B-v2-base
          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: 66.8
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=LoSboccacc/orthogonal-2x7B-v2-base
          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: 77.35
            name: accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=LoSboccacc/orthogonal-2x7B-v2-base
          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: 51.4
            name: accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=LoSboccacc/orthogonal-2x7B-v2-base
          name: Open LLM Leaderboard

base_model: mistralai/Mistral-7B-Instruct-v0.2 gate_mode: hidden # one of "hidden", "cheap_embed", or "random" dtype: bfloat16 # output dtype (float32, float16, or bfloat16) experts: - source_model: SanjiWatsuki/Kunoichi-DPO-v2-7B positive_prompts: - "roleplay" - source_model: mistralai/Mistral-7B-Instruct-v0.2 positive_prompts: - "chat"

chatml

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	68.47
AI2 Reasoning Challenge (25-Shot)	66.89
HellaSwag (10-Shot)	85.69
MMLU (5-Shot)	62.65
TruthfulQA (0-shot)	66.80
Winogrande (5-shot)	77.35
GSM8k (5-shot)	51.40