FineTuningLLM

Public

This repository focuses on improving Python code generation by fine-tuning Microsoft’s phi-1.5 model using the CodeParrot/APPS dataset. It uses PEFT and LoRA techniques for efficient training, resulting in better accuracy in generating code from natural language descriptions.

finetuning huggingface jupyter-notebook llm lora peft prompt-engineering python synthetic-data

Creat：2024-05-23T04:41:22

Update：2025-05-06T01:52:58

Stars

Stars Increase

Related projects

D2l Zh

book

《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。

71230

4个月前

+41today

PythonDataScienceHandbook

jupyter-notebook

Python Data Science Handbook: full text in Jupyter Notebooks

45099

4个月前

+14today

Unsloth

Hot

deepseek

Finetune Llama 3.3, DeepSeek-R1 & Reasoning LLMs 2x faster with 70% less memory! ?

43016

4个月前

+80today

Gradio

data-analysis

Build and share delightful machine learning apps, all in Python. ? Star to support our work!

39278

1年前

+29today

Trilium

electron

Build your personal knowledge base with Trilium Notes

29882

4个月前

+35today

Probabilistic Programming And Bayesian Methods For Hackers

bayesian-methods

aka "Bayesian Methods for Hackers": An introduction to Bayesian methods + probabilistic programming with a computation/understanding-first, mathematics-second point of view. All in pure Python ;)

27659

4个月前

+4today

D2l En

book

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

26458

4个月前

+19today