Highlights
- Pro
Lists (21)
Sort Name ascending (A-Z)
Agents/MCPs
AI
Datasets
DB
Deep learning
Engineering
Fine-Tuning
inference
LLMs
Machine learning
MCPs
NLP
RAG
Reinforcment learning
Research
Search
Topic modeling
Training
Utility
Vibes
VL
Starred repositories
A character-level discrete diffusion transformer trained on Tiny Shakespeare
A collection of full time roles in SWE, Quant, and PM for new grads.
An open source multi-tool for exploring and publishing data
Official PyTorch implementation of DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs (ICML 2025 Oral)
Research projects built on top of Transformers
Flash Attention Triton kernel with support for second-order derivatives
A nano-sized autograd engine for understanding backpropagation. Visualize gradients, build neural nets, learn how PyTorch works under the hood.
Cell2Sentence: Teaching Large Language Models the Language of Biology
All Algorithms implemented in Python
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
Leveraging BERT and c-TF-IDF to create easily interpretable topics.
Top2Vec learns jointly embedded topic, document and word vectors.
OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.
An elegant PyTorch deep reinforcement learning library.
This is the official implementation of Multi-Agent PPO (MAPPO).
A modular RL library to fine-tune language models to human preferences
MiroRL is an MCP-first reinforcement learning framework for deep research agent.
verl: Volcano Engine Reinforcement Learning for LLMs
Python Implementation of Reinforcement Learning: An Introduction
π Examples for using the dedupe library
Data on COVID-19 (coronavirus) cases, deaths, hospitalizations, tests β’ All countries β’ Updated daily by Our World in Data
π React for interactive command-line apps