slime is an LLM post-training framework for RL Scaling.

Awesome LLM compression research papers and tools.

Go ahead and axolotl questions

QLoRA: Efficient Finetuning of Quantized LLMs

A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks …

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads