README.md

metadata

license: llama3.1
library_name: transformers
base_model:
  - nbeerbower/Llama3.1-Gutenberg-Doppel-70B
datasets:
  - flammenai/Date-DPO-NoAsterisks
  - jondurbin/truthy-dpo-v0.1
model-index:
  - name: Llama3.1-Flammades-70B
    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: 70.58
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/Llama3.1-Flammades-70B
          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: 52.55
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/Llama3.1-Flammades-70B
          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: 13.37
            name: exact match
        source:
          url: >-
            https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/Llama3.1-Flammades-70B
          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: 13.87
            name: acc_norm
        source:
          url: >-
            https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/Llama3.1-Flammades-70B
          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: 22.35
            name: acc_norm
        source:
          url: >-
            https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/Llama3.1-Flammades-70B
          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: 41.69
            name: accuracy
        source:
          url: >-
            https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/Llama3.1-Flammades-70B
          name: Open LLM Leaderboard

Llama3.1-Flammades-70B

nbeerbower/Llama3.1-Gutenberg-Doppel-70B finetuned on flammenai/Date-DPO-NoAsterisks and jondurbin/truthy-dpo-v0.1.

Method

ORPO tuned with 2x H100 for 3 epochs.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	35.74
IFEval (0-Shot)	70.58
BBH (3-Shot)	52.55
MATH Lvl 5 (4-Shot)	13.37
GPQA (0-shot)	13.87
MuSR (0-shot)	22.35
MMLU-PRO (5-shot)	41.69