RLHF implementation details of OAI's 2019 codebase

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

verl: Volcano Engine Reinforcement Learning for LLMs

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

A very simple GRPO implement for reproducing r1-like LLM thinking.

Fully open reproduction of DeepSeek-R1

CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction

A framework for few-shot evaluation of language models.

YaRN: Efficient Context Window Extension of Large Language Models

Dataset and Code for our ACL 2024 paper: "Multimodal Table Understanding". We propose the first large-scale Multimodal IFT and Pre-Train Dataset for table understanding and develop a generalist tab…

A Curated List of Awesome Table Structure Recognition (TSR) Research. Including models, papers, datasets and codes. Continuously updating.

基于序列表格识别算法推理库，集成PP-Structure和modelscope等表格识别算法。

文档图片表格结构识别算法-同花顺算法挑战赛-2022年2-4月春季赛

整理目前开源的最优表格识别模型，完善前后处理，模型转换为ONNX Organize the currently open-source optimal table recognition models, improve pre-processing and post-processing, and convert the models to ONNX.

检测和提取各种场景图片中的表格区域，并纠正透视和旋转问题 Detect and extract table regions from images in various scenarios, and correct perspective and rotation issues.

pix2tex: Using a ViT to convert images of equations into LaTeX code.

A Comprehensive Benchmark for Document Parsing and Evaluation

Grounded Language-Image Pre-training

Ultralytics YOLO11 🚀

DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception

Math OCR model that outputs LaTeX and markdown

Office Automation by Using Pythonf (For Excel, Word, PPT and PDF .....)

The Math23k dataset for downloading

A LaTeX Template for Dissertation Writing at the University of Electronic Science and Technology of China Since 2024

Large language model and dataset for natural language to first-order logic translation

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

[EMNLP 2024] Source code for the paper "Learning Planning-based Reasoning with Trajectory Collection and Process Rewards Synthesizing".

【Generative LLM as Verifiers】推理加速篇：早停法+复用KV缓存+并行推理，实现推理效率提升几十倍