LLMs-for-RecSys

Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, and other large language models.

提取微信聊天记录，将其导出成HTML、Word、Excel文档永久保存，对聊天记录进行分析生成年度聊天报告，用聊天数据训练专属于个人的AI聊天助手

Learn how to design, develop, deploy and iterate on production-grade ML applications.

Finetune Llama 3.3, DeepSeek-R1 & Reasoning LLMs 2x faster with 70% less memory! ?

Self-hosted AI coding assistant

Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.

AI's query engine - Platform for building AI that can learn and answer questions over large scale federated data.

An open-source RAG-based tool for chatting with your documents.

LLM based autonomous agent that conducts deep local and web research on any topic and generates a long report with citations.

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.