Stars
电影推荐系统（Movie Recommendation System，前端：Vue3 + Element Plus + axios）前后端分离项目
FastAPI + vue3 前后端分离后台管理系统，包含PC端，微信小程序端。接口使用：FastAPI+Pydantic+SQLAlchemy 2.0+Mysql，PC 端使用：Vue3+Typescript+Vite+Element Plus，小程序使用：Uni-APP + uview ui。异步存储，RBAC 权限管理，定时任务，部门管理等功能。
Streamlit APP to recommend movies based on 3 different systems
商品类目预测，使用 Spring Boot 开发框架和 Spark MLlib 机器学习框架，通过 TF-IDF 和 Bayes 算法，训练出一个商品类目预测模型。该模型可以根据商品名称自动预测出商品类目。项目对外提供 RESTFul 接口。
ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型
This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.
Official repository of NEFTune: Noisy Embeddings Improves Instruction Finetuning
LLMs interview notes and answers:该仓库主要记录大模型（LLMs）算法工程师相关的面试题和参考答案
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…
Supercharge Your LLM Application Evaluations 🚀
FinGLM: 致力于构建一个开放的、公益的、持久的金融大模型项目，利用开源开放来促进「AI+金融」。
Argilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets
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。
An Instruction-tuned Large Language Model for E-commerce
Multilingual/multidomain question generation datasets, models, and python library for question generation.
The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.
A series of large language models developed by Baichuan Intelligent Technology
Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.
Code and data for "Lost in the Middle: How Language Models Use Long Contexts"
中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)
large language model training-3-stages+deployment
本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）