#
Lists (32)
🌟 accelerate & optimize
11 repositories
anormaly detection
6 repositories
awesome-series
15 repositories
chatroom
14 repositories
create a world
7 repositories
cuda
3 repositories
datasets
28 repositories
gpt
60 repositories
jax+differentiable renderer+其他..
6 repositories
LLMs
模型，训练，部署112 repositories
LLM应用
67 repositories
loss
2 repositories
Multimodal
27 repositories
Music
2 repositories
nas + 远程
11 repositories
ner
14 repositories
paper
5 repositories
physics
3 repositories
proxy
3 repositories
py+js
2 repositories
Risk Management
6 repositories
rl
5 repositories
rust-ml
5 repositories
sentence vec
7 repositories
time series
7 repositories
transformer
8 repositories
trie
4 repositories
Vec (or not) Search
25 repositories
Vision 👁️ 👁️
39 repositories
✌️ voice
36 repositories
模型基础结构
3 repositories
系统相关
13 repositories
Starred repositories
The simplest, fastest repository for training/finetuning small-sized VLMs.
Modeling, training, eval, and inference code for OLMo
Build your personal knowledge base with TriliumNext Notes
Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents
📖 A curated list of resources dedicated to hallucination of multimodal large language models (MLLM).
Production ready LLM model compression/quantization toolkit with hw accelerated inference support for both cpu/gpu via HF, vLLM, and SGLang.
FULL v0, Cursor, Manus, Same.dev, Lovable, Devin, Replit Agent, Windsurf Agent, VSCode Agent, Dia Browser & Trae AI (And other Open Sourced) System Prompts, Tools & AI Models.
Implementing DeepSeek R1's GRPO algorithm from scratch
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
APOLLO: SGD-like Memory, AdamW-level Performance
Visualize streams of multimodal data. Free, fast, easy to use, and simple to integrate. Built in Rust.
🤱🏻 Turn any webpage into a desktop app with Rust. 🤱🏻 利用 Rust 轻松构建轻量级多端桌面应用
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & RFT & Dynamic Sampling & Async Agent RL)
A generative world for general-purpose robotics & embodied AI learning.
Python implementation of MPPI (Model Predictive Path-Integral) controller to understand the basic idea. Mandatory dependencies are numpy and matplotlib only.
Python client for Baidu Yun (Personal Cloud Storage) 百度云/百度网盘Python客户端
The official Python SDK for Model Context Protocol servers and clients
Deep research agent to help you find the best GitHub repositories 🕵️!
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
Official repository of 'Visual-RFT: Visual Reinforcement Fine-Tuning' & 'Visual-ARFT: Visual Agentic Reinforcement Fine-Tuning'’
verl: Volcano Engine Reinforcement Learning for LLMs
Solve Visual Understanding with Reinforced VLMs
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
🪄 Create rich visualizations with AI
RLHF experiments on a single A100 40G GPU. Support PPO, GRPO, REINFORCE, RAFT, RLOO, ReMax, DeepSeek R1-Zero reproducing.
Minimal reproduction of DeepSeek R1-Zero