Stars
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Examples and guides for using the OpenAI API
🔊 Text-Prompted Generative Audio Model
《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程
Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable…
A guidance language for controlling large language models.
Anthropic's educational courses
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
Get started with building Fullstack Agents using Gemini 2.5 and LangGraph
A collection of various deep learning architectures, models, and tips
This repository contains the source code for the paper First Order Motion Model for Image Animation
Official inference library for Mistral models
🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022
Reference PyTorch implementation and models for DINOv3
FaceChain is a deep-learning toolchain for generating your Digital-Twin.
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
Inpaint anything using Segment Anything and inpainting models.
The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.
Accepted as [NeurIPS 2024] Spotlight Presentation Paper
CoTracker is a model for tracking any point (pixel) on a video.
JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.
An Open Source text-to-speech system built by inverting Whisper.
《Pytorch实用教程》（第二版）无论是零基础入门，还是CV、NLP、LLM项目应用，或是进阶工程化部署落地，在这里都有。相信在本书的帮助下，读者将能够轻松掌握 PyTorch 的使用，成为一名优秀的深度学习工程师。
Neo4j graph construction from unstructured data using LLMs
Segment Anything in High Quality [NeurIPS 2023]
Everything you need to know to build your own RAG application
中文nlp解决方案(大模型、数据、模型、训练、推理)
Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.
骆驼(Luotuo): Open Sourced Chinese Language Models. Developed by 陈启源 @ 华中师范大学 & 李鲁鲁 @ 商汤科技 & 冷子昂 @ 商汤科技