Starred repositories
nodew / fullstack-langgraph-quickstart
Forked from google-gemini/gemini-fullstack-langgraph-quickstartGet started with building Fullstack Agents using LangGraph
Continuous Thought Machines, because thought takes time and reasoning is a process.
Fully open reproduction of DeepSeek-R1
A course on aligning smol models.
🌱 a fast, batteries-included static-site generator that transforms Markdown content into fully functional websites
Perplexica is an AI-powered search engine. It is an Open source alternative to Perplexity AI
【AAAI 2024】An Empirical Study of CLIP for Text-based Person Search
Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval (CVPR 2023)
The Programmable Cypher-based Neuro-Symbolic AGI that lets you program its behavior using Graph-based Prompt Programming: for people who want AI to behave as expected
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
[LREC-COLING 2024 (Oral), Interspeech 2024 (Oral), NAACL 2025, ACL 2025] A Series of Multilingual Multitask Medical Speech Processing
An efficent implementation of the method proposed in "The Era of 1-bit LLMs"
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
[CVPRW 2024] TrafficVLM: A Controllable Visual Language Model for Traffic Video Captioning. Official code for the 3rd place solution of the AI City Challenge 2024 Track 2.
LostRuins / koboldcpp
Forked from ggml-org/llama.cppRun GGUF models easily with a KoboldAI UI. One File. Zero Install.
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.
Machine Learning Engineering Open Book
Convert all of libgen to high quality markdown
Awesome Machine Unlearning (A Survey of Machine Unlearning)
Convert Machine Learning Code Between Frameworks
Library for communication with ChatGPT. Now it supports Vision Question.
Official repo for consistency models.
The 7th place solution of the 7th AI City Challenge Track 2.
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
hungphongtrn / RWKV-LM
Forked from BlinkDL/RWKV-LMRWKV is a RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, …
An ongoing list of pandas quirks