A pure-python PDF library capable of splitting, merging, cropping, and transforming the pages of PDF files

🚀 DeepSeek-V3 R1大模型逆向API【特长：良心厂商】（官方贼便宜，建议直接走官方），支持高速流式输出、多轮对话，联网搜索，R1深度思考，零配置部署，多路token支持，仅供测试，如需商用请前往官方开放平台。

PyTorch implementation of FractalGen https://arxiv.org/abs/2502.17437

DeepSeek Coder: Let the Code Write Itself

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

[CVPR 2025] 🔥 Official impl. of "TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation".

[ICLR 2025][arXiv:2406.07548] Image and Video Tokenization with Binary Spherical Quantization

Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.

Code for the paper: Why Transformers Need Adam: A Hessian Perspective

A simple and efficient tool to parallelize Pandas operations on all available CPUs

Implementation of Generating Diverse High-Fidelity Images with VQ-VAE-2 in PyTorch

A Collection of BM25 Algorithms in Python

Retrieval and Retrieval-augmented LLMs

A word alignment tool based on famous GIZA++, extended to support multi-threading, resume training and incremental training.

Giza++

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

Language Models as Semantic Indexers (ICML 2024)

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

K-Means clustering - constrained with minimum and maximum cluster size. Documentation: https://joshlk.github.io/k-means-constrained

我的超迷你机械臂机器人项目。

Learning to Tokenize for Generative Retrieval (NeurIPS 2023)

Details on how to get Binance public data

SIGIR'21: Optimizing DR with hard negatives and achieving SOTA first-stage retrieval performance on TREC DL Track.

CIKM'21: JPQ substantially improves the efficiency of Dense Retrieval with 30x compression ratio, 10x CPU speedup and 2x GPU speedup.

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

Inference code for Llama models

[ACL 2024] Progressive LLaMA with Block Expansion.