从 65,722 个高星开源项目里，
找到你要的下一个。

LLMs-from-scratch 是用 Jupyter Notebook 编写的 AI 工具，用于人工智能方向的建模与推理。

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

vit-pytorch 是用 Python 编写的 AI 工具，用于人工智能方向的建模与推理，主打易用。

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

邱锡鹏《神经网络与深度学习》第二版与通识版：电子书、章节目录、学习资源与勘误。

邱锡鹏《神经网络与深度学习》第二版与通识版：电子书、章节目录、学习资源与勘误。

RWKV-LM 是用 Python 编写的学习资料，用于系统学习与查阅，主打速度快、开源免费。

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at…

text_classification 是用 Python 编写的 AI 工具，用于人工智能方向的建模与推理。

all kinds of text classification models and more with deep learning

x-transformers 是用 Python 编写的 AI 工具，用于人工智能方向的建模与推理。

A concise but complete full-attention transformer with a set of promising experimental features from various papers

DALLE-pytorch 是用 Python 编写的 AI 工具，用于人工智能方向的建模与推理。

Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

Awesome-Transformer-Attention 是一个 AI 工具，用于人工智能方向的建模与推理，主打功能完整。

An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites

awesome-graph-classification 是用 Python 编写的学习资料，用于系统学习与查阅。

A collection of important graph embedding, classification and representation learning papers with implementations.

RuVector 是用 Rust 编写的 AI 工具，用于人工智能方向的建模与推理，主打高性能、实时。

RuVector provides High Performance, Real-Time decisions and agent memory , Self-Learning Ai, Vector GNN DB built in Rust.

transformer 是用 Python 编写的 AI 工具，用于人工智能方向的建模与推理。

A TensorFlow Implementation of the Transformer: Attention Is All You Need

how-to-train-your-gpt 是用 Jupyter Notebook 编写的学习资料，用于系统学习与查阅，主打现代化。

Build a modern LLM from scratch. Every line commented. Explained like we are five.

GAT 是用 Python 编写的 AI 工具，用于人工智能方向的建模与推理。

Graph Attention Networks (https://arxiv.org/abs/1710.10903)

awesome-speech-recognition-speech-synthesis-papers 是一个 AI 工具，用于人工智能方向的建模与推理。

Automatic Speech Recognition (ASR), Speaker Verification, Speech Synthesis, Text-to-Speech (TTS), Language Modelling, Singing Voice Synthesis (SVS),…

pyGAT 是用 Python 编写的 AI 工具，用于人工智能方向的建模与推理。

Pytorch implementation of the Graph Attention Network model by Veličković et. al (2017, https://arxiv.org/abs/1710.10903)

a-PyTorch-Tutorial-to-Image-Captioning 是用 Python 编写的学习资料，用于系统学习与查阅。

Show, Attend, and Tell | a PyTorch Tutorial to Image Captioning

whisper-timestamped 是用 Python 编写的学习资料，用于系统学习与查阅。

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

keras-attention 是用 Python 编写的 AI 工具，用于人工智能方向的建模与推理。

Keras Attention Layer (Luong and Bahdanau scores).

pytorch-GAT 是用 Jupyter Notebook 编写的学习资料，用于系统学习与查阅。

My implementation of the original GAT paper (Veličković et al.). I've additionally included the playground.py file for visualizing the Cora dataset,…

reformer-pytorch 是用 Python 编写的 AI 工具，用于人工智能方向的建模与推理。

Reformer, the efficient Transformer, in Pytorch

llm-internals 是一个 AI 工具，用于大模型与智能体应用开发。

Learn LLM internals step by step - from tokenization to attention to inference optimization.

alphafold2 是用 Python 编写的 AI 工具，用于人工智能方向的建模与推理。

To eventually become an unofficial Pytorch implementation / replication of Alphafold2, as details of the architecture get released

soundstorm-pytorch 是用 Python 编写的 AI 工具，用于人工智能方向的建模与推理。

Implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch

lambda-networks 是用 Python 编写的 AI 工具，用于人工智能方向的建模与推理。

Implementation of LambdaNetworks, a new approach to image recognition that reaches SOTA with less compute