Stars
大语言模型ChatGLM-6B为基座,接入文档阅读功能进行实时问答,可上传txt/docx/pdf多种文件类型。
Question and Answer based on Anything.
BELLE: Be Everyone's Large Language model Engine(开源中文对话大模型)
整理开源的中文大语言模型,以规模较小、可私有化部署、训练成本较低的模型为主,包括底座模型,垂直领域微调及应用,数据集与教程等。
A high-throughput and memory-efficient inference and serving engine for LLMs
纯c++的全平台llm加速库,支持python调用,chatglm-6B级模型单卡可达10000+token / s,支持glm, llama, moss基座,手机端流畅运行
NLP language models in pytorch implementation
ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型
Using GPT to organize and access information, and generate questions. Long term goal is to make an agent-like research assistant.
This repository implements a contrastive learning model for hierarchical text classification. This work has been accepted as the long paper "Incorporating Hierarchy into Text Encoder: a Contrastive…
ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型
An open-source tool-augmented conversational language model from Fudan University
Deep Reinforcement Learning Lab, a platform designed to make DRL technology and fun for everyone
BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer
fastNLP: A Modularized and Extensible NLP Framework. Currently still in incubation.
code for ACL 2020 paper: FLAT: Chinese NER Using Flat-Lattice Transformer
DeepIE: Deep Learning for Information Extraction
Reject complicated operations for incorporating lexicon for Chinese NER.
Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
基于Pytorch的文本分类框架,支持TextCNN、Bert、Electra等。
Pytorch BERT-BiLSTM-CRF For NER
使用Bert,ERNIE,进行中文文本分类
The repository is used to record some useful and reusable codes.