theprint/phi-3-mini-4k-python

1---2language:3- en4license: apache-2.05tags:6- text-generation-inference7- transformers8- unsloth9- mistral10- trl11- sft12base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit13datasets:14- iamtarun/python_code_instructions_18k_alpaca15- ajibawa-2023/Python-Code-23k-ShareGPT16pipeline_tag: text-generation17model-index:18- name: phi-3-mini-4k-python19  results:20  - task:21      type: text-generation22      name: Text Generation23    dataset:24      name: IFEval (0-Shot)25      type: HuggingFaceH4/ifeval26      args:27        num_few_shot: 028    metrics:29    - type: inst_level_strict_acc and prompt_level_strict_acc30      value: 24.0931      name: strict accuracy32    source:33      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/phi-3-mini-4k-python34      name: Open LLM Leaderboard35  - task:36      type: text-generation37      name: Text Generation38    dataset:39      name: BBH (3-Shot)40      type: BBH41      args:42        num_few_shot: 343    metrics:44    - type: acc_norm45      value: 28.4546      name: normalized accuracy47    source:48      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/phi-3-mini-4k-python49      name: Open LLM Leaderboard50  - task:51      type: text-generation52      name: Text Generation53    dataset:54      name: MATH Lvl 5 (4-Shot)55      type: hendrycks/competition_math56      args:57        num_few_shot: 458    metrics:59    - type: exact_match60      value: 8.4661      name: exact match62    source:63      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/phi-3-mini-4k-python64      name: Open LLM Leaderboard65  - task:66      type: text-generation67      name: Text Generation68    dataset:69      name: GPQA (0-shot)70      type: Idavidrein/gpqa71      args:72        num_few_shot: 073    metrics:74    - type: acc_norm75      value: 5.4876      name: acc_norm77    source:78      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/phi-3-mini-4k-python79      name: Open LLM Leaderboard80  - task:81      type: text-generation82      name: Text Generation83    dataset:84      name: MuSR (0-shot)85      type: TAUR-Lab/MuSR86      args:87        num_few_shot: 088    metrics:89    - type: acc_norm90      value: 9.2291      name: acc_norm92    source:93      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/phi-3-mini-4k-python94      name: Open LLM Leaderboard95  - task:96      type: text-generation97      name: Text Generation98    dataset:99      name: MMLU-PRO (5-shot)100      type: TIGER-Lab/MMLU-Pro101      config: main102      split: test103      args:104        num_few_shot: 5105    metrics:106    - type: acc107      value: 28.63108      name: accuracy109    source:110      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/phi-3-mini-4k-python111      name: Open LLM Leaderboard112---113 114# Uploaded  model115 116- **Developed by:** theprint117- **License:** apache-2.0118- **Finetuned from model :** unsloth/Phi-3-mini-4k-instruct-bnb-4bit119 120This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.121 122[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)123# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)124Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_theprint__phi-3-mini-4k-python)125 126|      Metric       |Value|127|-------------------|----:|128|Avg.               |17.39|129|IFEval (0-Shot)    |24.09|130|BBH (3-Shot)       |28.45|131|MATH Lvl 5 (4-Shot)| 8.46|132|GPQA (0-shot)      | 5.48|133|MuSR (0-shot)      | 9.22|134|MMLU-PRO (5-shot)  |28.63|135 136