mgrankin
Follow
Stars
Staging area for a public release of Theorizer
Open-source framework for the research and development of foundation models.
Self-hosted, multi-user API that drops bots into Google Meet for real-time transcripts.
DSPy: The framework for programming—not prompting—language models
AIDE: AI-Driven Exploration in the Space of Code. The machine Learning engineering agent that automates AI R&D.
Entropy Based Sampling and Parallel CoT Decoding
Language modeling and instruction tuning for Russian
[ICLR 2025] Automated Design of Agentic Systems
MERA (Multimodal Evaluation for Russian-language Architectures) is a new open benchmark for the Russian language for evaluating fundamental models.
Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, 20+ clouds, or on-prem).
Mastering Diverse Domains through World Models
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
You like pytorch? You like micrograd? You love tinygrad! ❤️
Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion
A latent text-to-image diffusion model
Python library which enables complex compositions of language models such as scratchpads, chain of thought, tool use, selection-inference, and more.
Full description can be found here: https://discuss.huggingface.co/t/pretrain-gpt-neo-for-open-source-github-copilot-model/7678?u=ncoop57
Benchmarks of approximate nearest neighbor libraries in Python
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
Unifying Variational Autoencoder (VAE) implementations in Pytorch (NeurIPS 2022)
Code for the paper "Planning with Diffusion for Flexible Behavior Synthesis"
Official code and model checkpoints for our EMNLP 2022 paper "RankGen - Improving Text Generation with Large Ranking Models" (https://arxiv.org/abs/2205.09726).