RWKV in nanoGPT style

A simple, performant and scalable JAX-based world modeling codebase

Official Code for "From Cognition to Precognition: A Future-Aware Framework for Social Navigation" (ICRA 2025)

Video+code lecture on building nanoGPT from scratch

World's Smallest Vision-Language Model

Python implementation of the Kalman-IOU Tracker

Code and model for "Peeking into the Future: Predicting Future Person Activities and Locations in Videos", Liang et al, CVPR 2019

🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

4 bits quantization of LLaMa using GPTQ

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

DAMO-YOLO: a fast and accurate object detection method with some new techs, including NAS backbones, efficient RepGFPN, ZeroHead, AlignedOTA, and distillation enhancement.

Official DeiT repository

AliTok: Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Model

Clean, accessible reproduction of DeepSeek R1-Zero

[NeurIPS'23] RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions

Fast bare-bones BPE for modern tokenizer training

Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks