Awesome Pretrained Chinese NLP Models，高质量中文预训练模型&大模型&多模态模型&大语言模型集合

keras implement of transformers for humans

[ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.

text2vec, text to vector. 文本向量表征工具，把文本转化为向量矩阵，实现了Word2Vec、RankBM25、Sentence-BERT、CoSENT等文本表征、文本相似度计算模型，开箱即用。

An Open-Source Package for Neural Relation Extraction (NRE)

Keras implementation of RetinaNet object detection.

A framework for serving and evaluating LLM routers - save LLM costs without compromising quality

⛹️ Pytorch ReID: A tiny, friendly, strong pytorch implement of person re-id / vehicle re-id baseline. Tutorial 👉https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial

Papers on Computational Advertising

使用Bert，ERNIE，进行中文文本分类

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

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

Code samples from the "Python Cookbook, 3rd Edition", published by O'Reilly & Associates, May, 2013.

An Open-Source Package for Knowledge Embedding (KE)

Machine Learning Pipelines for Kubeflow

Implementation and experiments of graph embedding algorithms.

Simple RL training for reasoning

基于向量数据库与GPT3.5的通用本地知识库方案(A universal local knowledge base solution based on vector database and GPT3.5)

Tensorflow Faster RCNN for Object Detection

Representation learning on large graphs using stochastic graph convolutions.

[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821

MS-Agent: Lightweight Framework for Empowering Agents with Autonomous Exploration in Complex Task Scenarios

Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL

Graph Attention Networks (https://arxiv.org/abs/1710.10903)

Classic papers and resources on recommendation

Fast R-CNN

Generate embeddings from large-scale graph-structured data.

PyTorch extensions for high performance and large scale training.