Stars
Qwen3-4B + LoRA + ms-swift + Hermes，在 Glaive FC v2 上微调工具调用。
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
Open Source AI Platform - AI Chat with advanced features that works with every LLM
Source code for the X Recommendation Algorithm
Paper List for Contrastive Learning for Natural Language Processing
《Machine Learning Systems: Design and Implementation》 (V2 is launching soon）
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow
A curated list of awesome resources related to Semantic Search🔎 and Semantic Similarity tasks.
Paper list of log-based anomaly detection
Deploy DL/ ML inference pipelines with minimal extra code.
Simple XLSX and CSV to dictionary converter
Boosting your Web Services of Deep Learning Applications.
Easy and Efficient Transformer : Scalable Inference Solution For Large NLP model
Unsupervised text tokenizer for Neural Network-based text generation.
TextBox 2.0 is a text generation library with pre-trained language models
HyperTag - Intuitive Knowledge Management WebApp & CLI for Humans using Deep Learning & Tags
RLStructures is a library to facilitate the implementation of new reinforcement learning algorithms. It includes a library, a tutorial, and different RL algorithms provided as examples.
A Data Engineering & Machine Learning Knowledge Hub
DeText: A Deep Neural Text Understanding Framework for Ranking and Classification Tasks
Python爬虫实战 - 模拟登陆各大网站 包含但不限于：滑块验证、拼多多、美团、百度、bilibili、大众点评、淘宝，如果喜欢请start ❤️
Transformers are Graph Neural Networks!
Tendis is a high-performance distributed storage system fully compatible with the Redis protocol.
天池中药说明书实体识别挑战冠军方案；中文命名实体识别；NER; BERT-CRF & BERT-SPAN & BERT-MRC；Pytorch
A Python library for anomaly detection across tabular, time series, graph, text, image, and audio data. 60+ detectors, benchmark-backed ADEngine orchestration, and an agentic workflow for AI agents.
State of the Art Natural Language Processing