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、GRPO。

CNN-RNN中文文本分类，基于TensorFlow

中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard

[EMNLP 2022] An Open Toolkit for Knowledge Graph Extraction and Construction

中文公开聊天语料库

Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。

A series of large language models developed by Baichuan Intelligent Technology

Minimal keyword extraction with BERT

Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)

FlagAI (Fast LArge-scale General AI models) is a fast, easy-to-use and extensible toolkit for large-scale model.

基于ChatGLM-6B + LoRA的Fintune方案

Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调

中文分词

Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.

Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo

GPT2 for Chinese chitchat/用于中文闲聊的GPT2模型(实现了DialoGPT的MMI思想)

A 13B large language model developed by Baichuan Intelligent Technology

InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions

中文langchain项目|小必应，Q.Talk，强聊，QiangTalk

基于ChatGLM-6B、ChatGLM2-6B、ChatGLM3-6B模型，进行下游具体任务微调，涉及Freeze、Lora、P-tuning、全参微调等

Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

💬 RasaGPT is the first headless LLM chatbot platform built on top of Rasa and Langchain. Built w/ Rasa, FastAPI, Langchain, LlamaIndex, SQLModel, pgvector, ngrok, telegram

百亿参数的中英文双语基座大模型

Large-scale pretraining for dialogue

DeepMind's Tacotron-2 Tensorflow implementation

A simple prompt-chatting AI based on wechaty and fintuned NLP model

Prompt Learning for Vision-Language Models (IJCV'22, CVPR'22)

用于训练中英文对话系统的语料库 Datasets for Training Chatbot System

ALIbaba's Collection of Encoder-decoders from MinD (Machine IntelligeNce of Damo) Lab

A Large-scale Chinese Short-Text Conversation Dataset and Chinese pre-training dialog models