Stars
LlamaIndex is the leading framework for building LLM-powered agents over your data.
State-of-the-Art Text Embeddings
Multi-aspect knowledge distillation with Large Language Model, Preprint, 2025
The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation" and [TPAMI'23] "ViTPose++: Vision Transformer for Generic Body Pose Estimation"
USB: Universal-Scale Object Detection Benchmark (BMVC 2022)
Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)
An elegant PyTorch deep reinforcement learning library.
Massively Parallel Deep Reinforcement Learning. 🔥
Monocular Lane Detection Based on Deep Learning: A Survey
Exploring the use of bezier curves for lane detection —— A baseline model.
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
PyTorch implementations of deep reinforcement learning algorithms and environments
Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.
My blogs and code for machine learning. http://cnblogs.com/pinard
On-Policy Policy Gradient Algorithms in JAX
VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.
LLaVA-Mini is a unified large multimodal model (LMM) that can support the understanding of images, high-resolution images, and videos in an efficient manner.
A curated list of awesome model based RL resources (continually updated)
This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!
This resposity maintains a collection of important papers on knowledge distillation (awesome-knowledge-distillation)).
ZillaRU / Qwen-TPU
Forked from sophgo/Qwen-TPUSG2300X Demo for Qwen-7B-Chat
基于SG2300X的视频检索【使用自然语言搜索视频内容,定位到符合描述的具体时间段】
ZillaRU / facexlib
Forked from xinntao/facexlibFaceXlib aims at providing ready-to-use face-related functions based on current STOA open-source methods.
ZillaRU / nanoGPT
Forked from karpathy/nanoGPTThe simplest, fastest repository for training/finetuning medium-sized GPTs.
ZillaRU / sg200x-build
Forked from KennethLiu61/sg200x-buildDuo Arm核验证和流程文档review