LLM Fine-tuning and Optimization
9 repos
Libraries and tools for efficiently fine-tuning large language models like Gemma, DeepSeek, and ChatGPT. The cluster centers on Unsloth, a framework designed to accelerate model training and inference through optimization techniques. These repositories provide practical implementations and staging environments for adapting pre-trained models to specific tasks and domains.
Python · 8
Jupyter Notebook · 1
unsloth ·5,686
