1 repo
Awesome GitHub RepositoriesAdapter Fine-Tuning
Methods for updating model behavior by training small, injected parameter modules instead of full model weights.
Distinguishing note: Focuses on specific rank-decomposition injection techniques rather than general parameter-efficient training.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Adapter Fine-Tuning. Refine with filters or upvote what's useful.
Awesome Adapter Fine-Tuning GitHub Repositories
Find the best repos with AI.We'll search the best matching repositories with AI.
- datawhalechina/self-llm
datawhalechina/self-llm
28,285View on GitHubThis project is an open-source educational resource providing structured, step-by-step guides for fine-tuning large language models. It focuses on adapting pre-trained transformer-based causal models to custom datasets, enabling users to transfer specific writing styles or domain knowledge into generative AI models. The repository distinguishes itself by emphasizing parameter-efficient training techniques, specifically low-rank adaptation. By providing practical implementations for updating only a small subset of model weights, it allows for the customization of massive neural networks on con
Injects trainable rank-decomposition matrices into transformer layers to update model behavior while keeping original weights frozen.
Jupyter Notebookchatglmchatglm3gemma-2b-it
