README.md

metadata

license: apache-2.0
tags:
  - dpo
base_model:
  - CorticalStack/neurotic-crown-clown-7b-ties
dataset:
  - CorticalStack/tak-stack-dpo
model-index:
  - name: neurotic-crown-clown-7b-tak-stack-dpo
    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: 72.44
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/neurotic-crown-clown-7b-tak-stack-dpo
          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: 88.73
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/neurotic-crown-clown-7b-tak-stack-dpo
          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: 64.56
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/neurotic-crown-clown-7b-tak-stack-dpo
          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: 78.37
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/neurotic-crown-clown-7b-tak-stack-dpo
          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: 83.82
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/neurotic-crown-clown-7b-tak-stack-dpo
          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: 70.36
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/neurotic-crown-clown-7b-tak-stack-dpo
          name: Open LLM Leaderboard

neurotic-crown-clown-7b-tak-stack-dpo

neurotic-crown-clown-7b-tak-stack-dpo is a DPO fine-tuned version of CorticalStack/neurotic-crown-clown-7b-ties using the CorticalStack/tak-stack-dpo dataset.

LoRA

• r: 32
• LoRA alpha: 32
• LoRA dropout: 0.05

Training arguments

• Batch size: 4
• Gradient accumulation steps: 4
• Optimizer: paged_adamw_32bit
• Max steps: 100
• Learning rate: 5e-05
• Learning rate scheduler type: cosine
• Beta: 0.1
• Max prompt length: 1024
• Max length: 1536

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	76.38
AI2 Reasoning Challenge (25-Shot)	72.44
HellaSwag (10-Shot)	88.73
MMLU (5-Shot)	64.56
TruthfulQA (0-shot)	78.37
Winogrande (5-shot)	83.82
GSM8k (5-shot)	70.36