Rafael Fernández López's starred repositories
LLM-Shearing
[ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning
PowerInfer
High-speed Large Language Model Serving on PCs with Consumer-grade GPUs
NixThePlanet
Run macOS, Windows and more via a single Nix command, or simple nixosModules
rust-design-axioms
Discovering and describing Rust's design axioms
NeMo-Guardrails
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
advent-of-cuda
Doing advent of code with CUDA and rust.
bitsandbytes
Accessible large language models via k-bit quantization for PyTorch.
paperless-ngx
A community-supported supercharged version of paperless: scan, index and archive all your physical documents