metadata

language:
  - en
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - trl
  - sft
base_model: unsloth/llama-3.2-3b-instruct-bnb-4bit
datasets:
  - theprint/VanRossum-GPT
model-index:
  - name: Llama-3.2-3B-VanRossum
    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: 47.83
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/Llama-3.2-3B-VanRossum
          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: 19.37
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/Llama-3.2-3B-VanRossum
          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: 9.37
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/Llama-3.2-3B-VanRossum
          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: 2.35
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/Llama-3.2-3B-VanRossum
          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: 6.55
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/Llama-3.2-3B-VanRossum
          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: 19.67
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/Llama-3.2-3B-VanRossum
          name: Open LLM Leaderboard

Homage to Python

This model has been trained for 1 epoch on the VanRossum dataset.

The VanRossum dataset is all Python! I used DataMix to combine a handful of highly rated Python-centric datasets, to get a sampling of each and create something new.

This data set has 80,000 entries and is named after Guido Van Rossum, the man who invented Python back in 1991.

See the VanRossum Collection on HF for all things related to this dataset.

Alpaca / GPT

There are 2 versions of this dataset available on Huggingface.

Uploaded model

Developed by: theprint
License: apache-2.0
Finetuned from model : unsloth/llama-3.2-3b-instruct-bnb-4bit

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	17.52
IFEval (0-Shot)	47.83
BBH (3-Shot)	19.37
MATH Lvl 5 (4-Shot)	9.37
GPQA (0-shot)	2.35
MuSR (0-shot)	6.55
MMLU-PRO (5-shot)	19.67