Skills for Real Engineers. Straight from my .agents directory.

Examples for Recommenders - easy to train and deploy on accelerated infrastructure.

Academic Research Skills for Claude Code: research → write → review → revise → finalize

TradingAgents: Multi-Agents LLM Financial Trading Framework

Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.

Benchmarking Chat Assistants on Long-Term Interactive Memory (ICLR 2025)

a curated list of data for reasoning ai

🚀 Efficient implementations for emerging model architectures

LLM training in simple, raw C/CUDA

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

A Cookbook to start building with LLMs

📰 Must-read papers on KV Cache Compression (constantly updating 🤗).

📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥

Unofficial implementation of Titans, SOTA memory for transformers, in Pytorch

[COLM 2025] LIMO: Less is More for Reasoning

Training Large Language Model to Reason in a Continuous Latent Space

Unofficial PyTorch/🤗Transformers(Gemma/Llama3) implementation of Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

Code release for paper "Test-Time Training Done Right"

Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States

Latest Advances on Long Chain-of-Thought Reasoning

Unified KV Cache Compression Methods for Auto-Regressive Models

Awesome LLM compression research papers and tools.

A PyTorch library for all things Reinforcement Learning (RL) for Combinatorial Optimization (CO)

PyTorch implementation for our NeurIPS 2023 spotlight paper "Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets".

Retrieval and Retrieval-augmented LLMs

Benchmarks of approximate nearest neighbor libraries in Python

A library for advanced large language model reasoning