Inference code for Mistral and Mixtral hacked up into original Llama implementation

Inference code for LLaMA models

QLoRA with Enhanced Multi GPU Support

Modified Stanford-Alpaca Trainer for Training Replit's Code Model

QLoRA: Efficient Finetuning of Quantized LLMs

Code for the paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers" with GPT-J implementation.

Locally run an Instruction-Tuned Chat-Style LLM

Ansible Microsoft Azure Modules