Lists (23)
Evals
Fun Project Ideas
Hate Speech
Interview Prep
Kernels
Lexicons
LLM API Powertools
LLM Deployment
LLM-RL
LM Eval
Local LLMs
ML PowerTools
Multimodal
Pretraining Dataset
Python Tooling
RAG
RIdeas
Streamlit Components
Style Transfer
BaselinesSynthetic Data
Telemetry
TTS
Websites
Stars
AI agents running research on single-GPU nanochat training automatically
🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.
A fast, helpful, and open-source document parser
Build and run agents you can see, understand and trust.
Minimal and readable coding agent harness implementation in Python to explain the core components of coding agents.
Mount Hugging Face Buckets and repos as local filesystems. No download, no copy, no waiting.
Wan: Open and Advanced Large-Scale Video Generative Models
Multilingual Document Layout Parsing in a Single Vision-Language Model
Code accompanying the paper “Fractional Rotation, Full Potential? Investigating Performance and Convergence of Partial RoPE.”
Hundreds of models & providers. One command to find what runs on your hardware.
Parallel rsync-like pull sync over SSH with resume
[ICLR 2025] 🧬 RegMix: Data Mixture as Regression for Language Model Pre-training (Spotlight)
Code for 'Answer Matching Outperforms Multiple Choice for Language Model Evaluation' paper
A framework for efficient model inference with omni-modality models
Call commands safely by checking them rigorously against an allow-list
🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
Build compute kernels and load them from the Hub.
A simple, fast and robust program-aware agentic inference system.
Qwen3.5 is the large language model series developed by Qwen team, Alibaba Cloud.
Every Eval Ever is a shared schema and crowdsourced eval database. It defines a standardized metadata format for storing AI evaluation results — from leaderboard scrapes and research papers to loca…
A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.
Build reliable Gen AI solutions without overhead 🍕
Gets your TFLOPs for your GPU quickly
Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2
Explorations into the proposed SDFT, Self-Distillation Enables Continual Learning, from Shenfeld et al. of MIT
A template for research projects in computer science/machine learning using python and julia