Pinned Repositories
aarnphm
bazix
Nix + Bazel = 🥰
dotfiles
managed by chezmoi
editor
neovim configuration where I spend way too much time on
hack-gigabyte
Gigabyte Aero 15W with a spice of MacOS Mojave
sites
generated source of aarnphm[dot]xyz
whispercpp
Pybind11 bindings for Whisper.cpp
BentoML
The easiest way to serve AI/ML models in production - Build Model Inference Service, LLM APIs, Multi-model Inference Graph/Pipelines, LLM/RAG apps, and more!
OpenLLM
Run any open-source LLMs, such as Llama 2, Mistral, as OpenAI compatible API endpoint in the cloud.
peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
aarnphm's Repositories
aarnphm/whispercpp
Pybind11 bindings for Whisper.cpp
aarnphm/bazix
Nix + Bazel = 🥰
aarnphm/editor
neovim configuration where I spend way too much time on
aarnphm/aarnphm
aarnphm/dha-ps
Product similarity API using distilBERT. Deployed on Kubernetes
aarnphm/emulators
a hazard place for all kind of terminal
aarnphm/ayamir-nvimdots
A well configured and structured Neovim.
aarnphm/BentoML
Model Serving Made Easy
aarnphm/distributed-deployment-ml
prototype of ways to distribute a model to a cluster of GPUs.
aarnphm/dix
dotfiles + nix = dix
aarnphm/docstrfmt
A formatter for reStructuredText
aarnphm/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
aarnphm/whisper.cpp
Port of OpenAI's Whisper model in C/C++
aarnphm/workshops
workshop for llm
aarnphm/sites
generated source of aarnphm[dot]xyz
aarnphm/advent
aoc
aarnphm/attrs
Python Classes Without Boilerplate
aarnphm/boyfriendlist
submit pr to join the boyfriend list
aarnphm/ec2-github-runner
A fork of https://github.com/machulav/ec2-github-runner but with unattended run
aarnphm/hatch-fancy-pypi-readme
Fancy PyPI READMEs with Hatch
aarnphm/inference
testing some fast shi*
aarnphm/luasnip-latex-snippets.nvim
A port of Gilles Castel's UltiSnip snippets for LuaSnip.
aarnphm/meta-rag
OpenLLM + Llama Index + RAG = :rocket:
aarnphm/OpenLLM
Operating LLMs in production
aarnphm/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
aarnphm/ragas
Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines
aarnphm/templ
Opinionated template for Python-based projects.
aarnphm/tinygrad
You like pytorch? You like micrograd? You love tinygrad! ❤️
aarnphm/toolbox
aarnphm/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs