README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - conversation
  - text-generation-inference
  - CultriX/NeuralTrix-7B-dpo
  - dpo
  - merge
datasets:
  - argilla/OpenHermes2.5-dpo-binarized-alpha
pipeline_tag: text-generation
model-index:
  - name: dpo-binarized-NeuralTrix-7B
    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: 72.35
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/dpo-binarized-NeuralTrix-7B
          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: 88.89
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/dpo-binarized-NeuralTrix-7B
          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: 64.09
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/dpo-binarized-NeuralTrix-7B
          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: 79.07
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/dpo-binarized-NeuralTrix-7B
          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: 84.61
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/dpo-binarized-NeuralTrix-7B
          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: 68.01
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/dpo-binarized-NeuralTrix-7B
          name: Open LLM Leaderboard

DPO Finetuned CultriX/NeuralTrix-7B-dpo using argilla/OpenHermes2.5-dpo-binarized-alpha

argilla dpo binarized pairs is a dataset built on top of: https://huggingface.co/datasets/teknium/OpenHermes-2.5 using https://github.com/argilla-io/distilabel if interested.

Thx for the great data sources.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	76.17
AI2 Reasoning Challenge (25-Shot)	72.35
HellaSwag (10-Shot)	88.89
MMLU (5-Shot)	64.09
TruthfulQA (0-shot)	79.07
Winogrande (5-shot)	84.61
GSM8k (5-shot)	68.01