Stars
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…
Introduction to Machine Learning Systems
Multilingual Document Layout Parsing in a Single Vision-Language Model
Agentic LLM System for Practicing System Design and other technical Interviews.
Recursive-Emergence / RE
Forked from immartian/acithe original ideas from Isaac
The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.
The official repository for ERNIE 4.5 and ERNIEKit – its industrial-grade development toolkit based on PaddlePaddle.
Supercharge Your LLM with the Fastest KV Cache Layer
MiniCPM-V 4.5: A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone
Main reference implementation for NLWeb, implemented in Python.
Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling
A TTS model capable of generating ultra-realistic dialogue in one pass.
Implementation of all RL algorithms in a simpler way
Official repository for "AM-RADIO: Reduce All Domains Into One"
DSPy: The framework for programming—not prompting—language models
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget)
[CVPR 2025] Learning Flow Fields in Attention for Controllable Person Image Generation
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama mode…
OCR, layout analysis, reading order, table recognition in 90+ languages
FlashMLA: Efficient Multi-head Latent Attention Kernels
[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
Minimal reproduction of DeepSeek R1-Zero
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & TIS & vLLM & Ray & Dynamic Sampling & Async Agentic RL)