Muon is an optimizer for hidden layers in neural networks

interactive visualization of 5 popular gradient descent methods with step-by-step illustration and hyperparameter tuning UI

This is the code for the SpeechTokenizer presented in the SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models. Samples are presented on

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

Fast and memory-efficient exact attention

Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.

Central place for the engineering/scaling WG: documentation, SLURM scripts and logs, compute environment and data.

Inference script for Meta's LLaMA models using Hugging Face wrapper

Quantized inference code for LLaMA models

Inference code for Llama models

Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.

SimCSE在中文上的复现，有监督+无监督

xmnlp：提供中文分词, 词性标注, 命名体识别，情感分析，文本纠错，文本转拼音，文本摘要，偏旁部首，句子表征及文本相似度计算等功能

[EMNLP 2022] An Open Toolkit for Knowledge Graph Extraction and Construction

High-Resolution Image Synthesis with Latent Diffusion Models

A latent text-to-image diffusion model

Google Research

A colab friendly toolkit to generate 3D mesh model / video / nerf instance / multiview images of colourful 3D objects by text and image prompts input, based on dreamfields.

Awesome Pretrained Chinese NLP Models，高质量中文预训练模型&大模型&多模态模型&大语言模型集合

Nearest Neighbor Search with Neighborhood Graph and Tree for High-dimensional Data

Multi Task Vision and Language

全局指针统一处理嵌套与非嵌套NER的Pytorch实现

SpanNER: Named EntityRe-/Recognition as Span Prediction

Unified Structure Generation for Universal Information Extraction

EasyTransfer is designed to make the development of transfer learning in NLP applications easier.

基于轻量级的albert实现albert+BiLstm+CRF

Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework