Building blocks for foundation models.

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

This repository contains a LLM benchmark for the social deduction game `Resistance Avalon'

Python PDF parser for scientific publications: content and figures

HTML to Markdown converter and crawler.

FinGLM: 致力于构建一个开放的、公益的、持久的金融大模型项目，利用开源开放来促进「AI+金融」。

A toolkit for reproducible reinforcement learning research.

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

Code accompanying the paper "Deep reinforcement learning for multiparameter optimization in de novo drug design"

Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案，结构参考alpaca

A RWKV management and startup tool, full automation, only 8MB. And provides an interface compatible with the OpenAI API. RWKV is a large language model that is fully open source and available for c…

Implementation of MolSearch paper

Mining synonyms from unstructured and semi-structured data

CLUENER2020 中文细粒度命名实体识别 Fine Grained Named Entity Recognition

此项目是机器学习(Machine Learning)、深度学习(Deep Learning)、NLP面试中常考到的知识点和代码实现，也是作为一个算法工程师必会的理论基础知识。

🔥 经典编程书籍大全，涵盖：计算机系统与网络、系统架构、算法与数据结构、前端开发、后端开发、移动开发、数据库、测试、项目与团队、程序员职业修炼、求职面试等

搜索所有中文NLP数据集，附常用英文NLP数据集

关于一些经典论文源码的逐行中文笔记

Source code and dataset for ACL 2019 paper "ERNIE: Enhanced Language Representation with Informative Entities"

Entity and Relation Extraction Based on TensorFlow and BERT. 基于TensorFlow和BERT的管道式实体及关系抽取，2019语言与智能技术竞赛信息抽取任务解决方案。Schema based Knowledge Extraction, SKE 2019