README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - merge
  - dpo
  - conversation
  - text-generation-inference
  - Kukedlc/NeuTrixOmniBe-7B-model-remix
datasets:
  - argilla/OpenHermes2.5-dpo-binarized-alpha
pipeline_tag: text-generation
model-index:
  - name: dpo-binarized-NeutrixOmnibe-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: 72.78
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/dpo-binarized-NeutrixOmnibe-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: 89.05
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/dpo-binarized-NeutrixOmnibe-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: 64.6
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/dpo-binarized-NeutrixOmnibe-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: 76.9
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/dpo-binarized-NeutrixOmnibe-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: 85.08
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/dpo-binarized-NeutrixOmnibe-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: 69.45
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/dpo-binarized-NeutrixOmnibe-7B
          name: Open LLM Leaderboard

DPO Finetuned Kukedlc/NeuTrixOmniBe-7B-model-remix 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.

GGUF: https://huggingface.co/eren23/dpo-binarized-NeutrixOmnibe-7B-GGUF

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	76.31
AI2 Reasoning Challenge (25-Shot)	72.78
HellaSwag (10-Shot)	89.05
MMLU (5-Shot)	64.60
TruthfulQA (0-shot)	76.90
Winogrande (5-shot)	85.08
GSM8k (5-shot)	69.45