dwopdm

tianshou

An elegant PyTorch deep reinforcement learning library.

Pyramid-Flow

Code of Pyramidal Flow Matching for Efficient Video Generative Modeling

llm_illustrated

看图学大模型

ComfyUI-Zluda

The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface. Now ZLUDA enhanced for better AMD GPU performance.

OptML_course

EPFL Course - Optimization for Machine Learning - CS-439

AWT

[NeurIPS 2024] AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation

ChatGPT_Agent

A Game Demo Powered by ChatGPT Agents

Selective_Context

Compress your input to ChatGPT or other LLMs, to let them process 2x more content and save 40% memory and GPU time.

skyvern

Automate browser-based workflows with LLMs and Computer Vision

WasmEdge-WASINN-examples

crabml

a fast cross platform AI inference engine 🤖 using Rust 🦀 and WebGPU 🎮

VoCoT

VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models

felafax

Felafax is building AI infra for non-NVIDIA GPUs

thinkR

gpt-o1 like chain of thoughts with local LLMs in R

g1

g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains

torchkeras

Pytorch❤️ Keras 😋😋

transformer

transformer 源码实现

cs149-xmake

CS149 xmake version

RectifiedFlow

Official Implementation of Rectified Flow (ICLR2023 Spotlight)

Awesome-Token-Compress

A paper list of some recent works about Token Compress for Vit and VLM

self-refine

LLMs can generate feedback on their work, use it to improve the output, and repeat this process iteratively.

LongAlign

[EMNLP 2024] LongAlign: A Recipe for Long Context Alignment of LLMs

image_classification

仓库主要任务是图片分类，对训练策略做了优化，添加了数据增强，基本能还原论文精度，支持onnx的python、C++、java、javascript和ncnn的C++和java部署。

nerfstudio

A collaboration friendly studio for NeRFs

CRAFT

Code, datasets, and checkpoints for the paper "CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentation"

CleanDiffuser

CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Making

Web_to_SFT

official code for the paper "Leveraging Web-Crawled Data for High-Quality Fine-Tuning"

Multimodal-Affective-Computing-Survey

LongRecipe

LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models

dify-with-qwen-vl

视频理解：千问视频多模态模型 & Dify