Large Language Model Fine-tuning & Inference
15 repos
Text generation and deployment infrastructure built around PyTorch, with particular focus on adapter-based fine-tuning and inference optimization for models in the Llama family. The cluster centers on practical tools for adapting and serving large language models at various scales, emphasizing compatibility with standard text-generation endpoints. While most repos appear to be model weights or configurations rather than foundational libraries, the shared technical stack and deployment patterns reflect a coherent engineering practice around efficient LLM adaptation and inference.
Python · 2
pytorch ·301
llama ·300
endpoints_compatible ·300
text-generation ·300
text-generation-inference ·300
transformers ·300
safetensors ·300
