README.md

metadata

license: llama3
library_name: transformers
base_model:
  - mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated
datasets:
  - flammenai/casual-conversation-DPO
model-index:
  - name: llama3.1-cc-8B
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: IFEval (0-Shot)
          type: HuggingFaceH4/ifeval
          args:
            num_few_shot: 0
        metrics:
          - type: inst_level_strict_acc and prompt_level_strict_acc
            value: 50.68
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/llama3.1-cc-8B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: BBH (3-Shot)
          type: BBH
          args:
            num_few_shot: 3
        metrics:
          - type: acc_norm
            value: 26.48
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/llama3.1-cc-8B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MATH Lvl 5 (4-Shot)
          type: hendrycks/competition_math
          args:
            num_few_shot: 4
        metrics:
          - type: exact_match
            value: 6.34
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/llama3.1-cc-8B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GPQA (0-shot)
          type: Idavidrein/gpqa
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 4.7
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/llama3.1-cc-8B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MuSR (0-shot)
          type: TAUR-Lab/MuSR
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 6.5
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/llama3.1-cc-8B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU-PRO (5-shot)
          type: TIGER-Lab/MMLU-Pro
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 26.08
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/llama3.1-cc-8B
          name: Open LLM Leaderboard

llama3.1-cc-8B

mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated finetuned on flammenai/casual-conversation-DPO.

This is an experimental finetune that formats the conversation data sequentially with the Llama 3 template.

Method

Finetuned using an A100 on Google Colab for 3 epochs.

Fine-tune Llama 3 with ORPO

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	20.13
IFEval (0-Shot)	50.68
BBH (3-Shot)	26.48
MATH Lvl 5 (4-Shot)	6.34
GPQA (0-shot)	4.70
MuSR (0-shot)	6.50
MMLU-PRO (5-shot)	26.08