Xin Li's repositories
AIOS
AIOS: LLM Agent Operating System
alignment-handbook
Robust recipes to align language models with human and AI preferences
LLaMA-Factory
Easy-to-use LLM fine-tuning framework (LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, ChatGLM2)
mmpose
OpenMMLab Pose Estimation Toolbox and Benchmark.
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
examples
Example deep learning projects that use wandb's features.
exllamav2
A fast inference library for running LLMs locally on modern consumer-class GPUs
FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
fastllm
纯c++的全平台llm加速库,chatglm-6B级模型单卡可达10000+token / s,支持moss, chatglm, baichuan模型,手机端流畅运行
gpt-fast
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
Gymnasium
A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
HuixiangDou
HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance
lightllm
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
LLaMA2-Accessory
An Open-source Toolkit for LLM Development
LLMTest_NeedleInAHaystack
Doing simple retrieval from LLM models at various context lengths to measure accuracy
LMOps
General technology for enabling AI capabilities w/ LLMs and MLLMs
mmdeploy
OpenMMLab Model Deployment Framework
mmdetection
OpenMMLab Detection Toolbox and Benchmark
mmengine
OpenMMLab Foundational Library for Training Deep Learning Models
open_flamingo
An open-source framework for training large multimodal models
OpenRLHF
A Ray-based High-performance RLHF framework (Support 70B+ full tuning & LoRA & Mixtral)
ring-attention-pytorch
Explorations into Ring Attention, from Liu et al. at Berkeley AI
sd-webui-controlnet
WebUI extension for ControlNet
search_with_lepton
Building a quick conversation-based search demo with Lepton AI.
self-rag
This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.
sglang
SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.
stable-diffusion-webui
Stable Diffusion web UI
trlx
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
xtuner
XTuner is a toolkit for efficiently fine-tuning LLM
YOLOv6
YOLOv6: a single-stage object detection framework dedicated to industrial applications.