This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data

Official implementation of "Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling"

s1: Simple test-time scaling

The MATH Dataset (NeurIPS 2021)

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models

🚀 Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

The model, data and code for the visual GUI Agent SeeClick

The official implementation of Tensor ProducT ATTenTion Transformer (T6)

LoRA fine-tune directly on the quantized models.

[ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule

The official repository for "2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining"

Inference Speed Benchmark for Learning to (Learn at Test Time): RNNs with Expressive Hidden States

D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement [ICLR 2025 Spotlight]

[NeurIPS 2024] Classification Done Right for Vision-Language Pre-Training

Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors

一年过去了，你在华子食堂里花的钱都花在哪儿了？

A simple screen parsing tool towards pure vision based GUI agent

A collection of vision foundation models unifying understanding and generation.

DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding

A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.

GMAI-VL & GMAI-VL-5.5M: A Large Vision-Language Model and A Comprehensive Multimodal Dataset Towards General Medical AI.

The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curatio…

Next-Token Prediction is All You Need

[ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads