airllm:基于内存优化技术的大语言模型推理项目

Star14

Star14

AirLLM 70B inference with single 4GB GPU

Introduction

使用单个4GB GPU进行AirLLM 70B模型的推理【此简介由AI生成】

Apache-2.0 Jupyter Notebook 292Commitschinese-llm chinese-nlp finetune generative-ai instruct-gpt instruction-set llama llm open-models open-source open-source-models qlora

Customize your domain

22922.36 K2.57 KVisit GitHub