README.md

metadata

language:
  - en
license: apache-2.0
base_model: mistralai/Mistral-Nemo-Base-2407
datasets:
  - PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
model-index:
  - name: Dans-Instruct-CoreCurriculum-12b-ChatML
    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: 4.78
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Dans-DiscountModels/Dans-Instruct-CoreCurriculum-12b-ChatML
          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: 32.02
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Dans-DiscountModels/Dans-Instruct-CoreCurriculum-12b-ChatML
          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: 3.78
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Dans-DiscountModels/Dans-Instruct-CoreCurriculum-12b-ChatML
          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: 7.38
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Dans-DiscountModels/Dans-Instruct-CoreCurriculum-12b-ChatML
          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: 12.08
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Dans-DiscountModels/Dans-Instruct-CoreCurriculum-12b-ChatML
          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: 28.67
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Dans-DiscountModels/Dans-Instruct-CoreCurriculum-12b-ChatML
          name: Open LLM Leaderboard

Test model do not use. All of this text is to pad it to the limit and submit an eval on the leaderboard hope you enjoy reading it.

Trained on the PocketDoc/Dans-MemoryCore-CoreCurriculum-Small dataset using 4x H100 for 2 epochs.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	14.79
IFEval (0-Shot)	4.78
BBH (3-Shot)	32.02
MATH Lvl 5 (4-Shot)	3.78
GPQA (0-shot)	7.38
MuSR (0-shot)	12.08
MMLU-PRO (5-shot)	28.67