Xin Li's repositories
xtuner
XTuner is a toolkit for efficiently fine-tuning LLM
mmpose
OpenMMLab Pose Estimation Toolbox and Benchmark.
exllamav2
A fast inference library for running LLMs locally on modern consumer-class GPUs
LLaMA-Factory
Easy-to-use LLM fine-tuning framework (LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, ChatGLM2)
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
gpt-fast
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
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.
sglang
SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.
ring-attention-pytorch
Explorations into Ring Attention, from Liu et al. at Berkeley AI
alignment-handbook
Robust recipes to align language models with human and AI preferences
AIOS
AIOS: LLM Agent Operating System
mmengine
OpenMMLab Foundational Library for Training Deep Learning Models
HuixiangDou
HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance
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
LLaMA2-Accessory
An Open-source Toolkit for LLM Development
Gymnasium
A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
examples
Example deep learning projects that use wandb's features.
open_flamingo
An open-source framework for training large multimodal models
sd-webui-controlnet
WebUI extension for ControlNet
stable-diffusion-webui
Stable Diffusion web UI
trlx
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
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.
mmdetection
OpenMMLab Detection Toolbox and Benchmark
FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
search_with_lepton
Building a quick conversation-based search demo with Lepton AI.
mmdeploy
OpenMMLab Model Deployment Framework
OpenRLHF
A Ray-based High-performance RLHF framework (Support 70B+ full tuning & LoRA & Mixtral)
LLMTest_NeedleInAHaystack
Doing simple retrieval from LLM models at various context lengths to measure accuracy
YOLOv6
YOLOv6: a single-stage object detection framework dedicated to industrial applications.
LMOps
General technology for enabling AI capabilities w/ LLMs and MLLMs