Stars
A pure-functional implementation of a machine learning transformer model in Python/JAX
Code for paper "The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning"
A high-throughput and memory-efficient inference and serving engine for LLMs
From the Transistor to the Web Browser, a rough outline for a 12 week course
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"
Fully open reproduction of DeepSeek-R1
Understanding the interplay between memorization and generalization in neural networks, featuring MAT, a learning algorithm to enhance robustness by mitigating spurious correlations.
Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"
Use Alfred to switch iTerm2 tabs
The fastest way to create an HTML app
Advantage Alignment Algorithms (ICLR 2025 oral)
A simple, performant and scalable Jax LLM!
QLoRA: Efficient Finetuning of Quantized LLMs
The fundamental package for scientific computing with Python.
High accuracy RAG for answering questions from scientific documents with citations
A playbook for systematically maximizing the performance of deep learning models.
ChatGPT for Mac, living in your menubar.
The Github home of Orbot: Tor on Android (Also available on gitlab!)
Stable Diffusion web UI
A series of tutorial notebooks on denoising diffusion probabilistic models in PyTorch
Your browser's reference manager: automatic paper detection (Arxiv, OpenReview & more), publication venue matching and code repository discovery! Also enhances ArXiv: BibTex citation, Markdown link…
From search engines, to science, to robotics, this reposity is meant to showcase the use of reinforcement learning in the world..
Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow