Google AI 2018 BERT pytorch implementation

TensorFlow code and pre-trained models for BERT

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

A concise but complete implementation of CLIP with various experimental improvements from recent papers

Deep Pyramid Convolutional Neural Networks for Text Categorization in PyTorch

Build ChatGPT over your data, all with natural language

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

A developer reference project for creating Retrieval Augmented Generation (RAG) chatbots on Windows using TensorRT-LLM

Langchain-Chatchat（原Langchain-ChatGLM, Qwen 与 Llama 等）基于 Langchain 与 ChatGLM 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen a…

开源易用的中文离线OCR，识别率媲美大厂，并且提供了易用的web页面及web的接口，方便人类日常工作使用或者其他程序来调用~

超轻量级中文ocr，支持竖排文字识别, 支持ncnn、mnn、tnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M

Free Offline OCR 离线的中文文本检测+识别SDK

[ECCV2024] Official code implementation of Vary: Scaling Up the Vision Vocabulary of Large Vision Language Models.

C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4

GLM-Pretrain in Megatron-Deepspeed for DCU

从头开始训练一个chatglm小模型

Firefly中文LLaMA-2大模型，支持增量预训练Baichuan2、Llama2、Llama、Falcon、Qwen、Baichuan、InternLM、Bloom等大模型

MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO。

OrionStar-Yi-34B-Chat 是一款开源中英文Chat模型，由猎户星空基于Yi-34B开源模型、使用15W+高质量语料微调而成。

XVERSE-13B: A multilingual large language model developed by XVERSE Technology Inc.

该仓库主要记录 大模型（LLMs） 算法工程师相关的面试题

爬虫集合

爬取百度百科中文页面，抽取三元组信息，构建中文知识图谱

反中共政治宣传库。Anti Chinese government propaganda. 住在中国真名用户的网友请别给星星，不然你要被警察请喝茶。常见问答集，新闻集和饭店和音乐建议。卐习万岁卐。冠状病毒审查郝海东新疆改造中心六四事件法轮功 996.ICU709大抓捕巴拿马文件邓家贵低端人口西藏骚乱。Friends who live in China and have real name on…

基于scrapy的层次优先队列方法爬取中文维基百科，并自动抽取结构和半结构数据

Scrapy, a fast high-level web crawling & scraping framework for Python.

Knowledge Distillation For Transformer Language Models

XtremeDistil framework for distilling/compressing massive multilingual neural network models to tiny and efficient models for AI at scale