valayDave
Follow
Stars
DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
Solve Visual Understanding with Reinforced VLMs
Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.
Clean, minimal, accessible reproduction of DeepSeek R1-Zero
Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Collection of best practices, reference architectures, model training examples and utilities to train large models on AWS.
This is a plugin which lets EC2 developers use libfabric as network provider while running NCCL applications.
An extensible benchmark for evaluating large language models on planning
Machine Learning Engineering Open Book
A curated list of engineering blogs
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
Testing designs for a benchmarking operator (in experimental mode!)
A generative world for general-purpose robotics & embodied AI learning.
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Probabilistic language based on pattern matching and constraint propagation, 153 examples
Metaflow flows for analyzing topics and sentiments in Hacker News
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…
🔎 📈 🐍 💰 Backtest trading strategies in Python.
A massively parallel, high-level programming language
A Data Streaming Library for Efficient Neural Network Training