🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT!🌏 Train a 26M-parameter GPT from scratch in just 2h!
Updated 2026-01-13 17:46:54 +08:00
🍒 Cherry Studio is a desktop client that supports for multiple LLM providers. Support deepseek-r1
Updated 2026-01-13 17:00:15 +08:00
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.
Updated 2026-01-13 13:32:18 +08:00
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
Updated 2026-01-13 13:20:15 +08:00
A modular graph-based Retrieval-Augmented Generation (RAG) system
Updated 2026-01-13 10:00:21 +08:00
Build your own AI friend
Updated 2026-01-10 16:29:12 +08:00
Ollama Python library
Updated 2026-01-10 15:21:07 +08:00
Action for checking out a repo
Updated 2026-01-10 04:09:42 +08:00
Set up your GitHub Actions workflow with a specific version of Python
Updated 2026-01-08 14:38:06 +08:00
NCCL Tests
Updated 2026-01-07 07:00:17 +08:00
存储runner工作流的仓库
Updated 2025-12-19 18:39:42 +08:00
🌈 MEGREZ | 🍒 Make Extendable GPU Resource EASY
Updated 2025-12-07 22:59:01 +08:00
🌈 MEGREZ | 🍒 Make Extendable GPU Resource EASY - Deploy
Updated 2025-12-07 10:16:56 +08:00
A CPU Realtime VLM in 500M. Surpassed Moondream2 and SmolVLM. Training from scratch with ease.
Updated 2025-04-22 21:49:27 +08:00
R1-onevision, a visual language model capable of deep CoT reasoning.
Updated 2025-04-13 16:55:08 +08:00
Updated 2025-03-27 16:47:01 +08:00
Updated 2025-03-03 13:26:07 +08:00
arxiv-sanity lite: tag arxiv papers of interest get recommendations of similar papers in a nice UI using SVMs over tfidf feature vectors based on paper abstracts.
Updated 2025-03-03 12:49:31 +08:00
Updated 2025-02-27 21:05:25 +08:00