Large World Model -- Modeling Text and Video with Millions Context

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

Official release of InternLM series (InternLM, InternLM2, InternLM2.5, InternLM3).

Build ChatGPT over your data, all with natural language

An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

🎉 Repo for LaWGPT, Chinese-Llama tuned with Chinese Legal knowledge. 基于中文法律知识的大语言模型

A flexible framework of neural networks for deep learning

中文文本分类，TextCNN，TextRNN，FastText，TextRCNN，BiLSTM_Attention，DPCNN，Transformer，基于pytorch，开箱即用。

The official PyTorch implementation of Google's Gemma models

Unified embedding generation and search engine. Also available on cloud - cloud.marqo.ai

AIOS: AI Agent Operating System

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉

Time series forecasting with PyTorch

PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....

Merlion: A Machine Learning Framework for Time Series Intelligence

Papers on Computational Advertising

System for AI Education Resource.

我的自学笔记，终身更新

🚀 Efficient implementations of state-of-the-art linear attention models

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

Code and models for ICML 2024 paper, NExT-GPT: Any-to-Any Multimodal Large Language Model

Hummingbird compiles trained ML models into tensor computation for faster inference.

A simple, easy-to-hack GraphRAG implementation

Classic papers and resources on recommendation

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

【PyTorch】Easy-to-use,Modular and Extendible package of deep-learning based CTR models.

Awesome work on hand pose estimation/tracking