sonald
Follow
Stars
Put an end to code hallucinations! GitMCP is a free, open-source, remote MCP server for any GitHub project
Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
『ゼロから作る Deep Learning ❸』(O'Reilly Japan, 2020)
A lightweight data processing framework built on DuckDB and 3FS.
Clean, minimal, accessible reproduction of DeepSeek R1-Zero
Fully open reproduction of DeepSeek-R1
A course on aligning smol models.
Curated list of datasets and tools for post-training.
👻 Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.
Examples and guides for using the Gemini API
🚀 The fast, Pythonic way to build MCP servers and clients
A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.
A full-featured, hackable Next.js AI chatbot built by Vercel
LLaVA-CoT, a visual language model capable of spontaneous, systematic reasoning
Netflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team | Netflix级字幕切割、翻译、对齐、甚至加上配音，一键全自动视频搬运AI字幕组
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
Composable building blocks to build Llama Apps
A playbook for systematically maximizing the performance of deep learning models.
Efficient Triton Kernels for LLM Training
Install PyTorch distributions with computation backend auto-detection
The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
LostRuins / koboldcpp
Forked from ggml-org/llama.cppRun GGUF models easily with a KoboldAI UI. One File. Zero Install.