https://github.com/sccsmartcode/deep-learning-03-llm-finetuning

Scalable and modular framework for fine-tuning large language models (LLMs) using LoRA and QLoRA. Supports 4-bit/8-bit quantization, Hugging Face Transformers, and instruction-tuning workflows across various tasks and datasets. Built for reproducibility, extensibility, and efficient experimentation.
https://github.com/sccsmartcode/deep-learning-03-llm-finetuning

bitsandbytes finetuning huggingface llama2 llm peft qlora transformers

Last synced: 8 months ago
JSON representation

Scalable and modular framework for fine-tuning large language models (LLMs) using LoRA and QLoRA. Supports 4-bit/8-bit quantization, Hugging Face Transformers, and instruction-tuning workflows across various tasks and datasets. Built for reproducibility, extensibility, and efficient experimentation.

• Host: GitHub
• URL: https://github.com/sccsmartcode/deep-learning-03-llm-finetuning
• Owner: SCCSMARTCODE
• License: mit
• Created: 2025-05-17T23:36:38.000Z (9 months ago)
• Default Branch: main
• Last Pushed: 2025-05-20T22:44:21.000Z (9 months ago)
• Last Synced: 2025-06-08T15:01:51.518Z (8 months ago)
• Topics: bitsandbytes, finetuning, huggingface, llama2, llm, peft, qlora, transformers
• Language: Jupyter Notebook
• Homepage:
• Size: 66.4 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Deep-Learning-03-LLM-FineTuning

Scalable and modular framework for fine-tuning large language models (LLMs) using LoRA and QLoRA. Supports 4-bit/8-bit quantization, Hugging Face Transformers, and instruction-tuning workflows across various tasks and datasets. Built for reproducibility, extensibility, and efficient experimentation.