stas00
Toolmaker. Author. Software creator, optimizer and harmonizer. Makes things work. Current domains: LLM/Retrieval/RAG/Scalability/Machine Learning
Stasosphere Online Inc. / Contextual.AIBC, Canada
Pinned Repositories
fastai-transcript
Video Transcripts of fast.ai MOOC courses made into searchable ebooks
git-tools
helper git tools
gpt-neo-fine-tuning-example
Fine-Tune EleutherAI GPT-Neo And GPT-J-6B To Generate Netflix Movie Descriptions Using Hugginface And DeepSpeed
ipyexperiments
Automatic GPU+CPU memory profiling, re-use and memory leaks detection using jupyter/ipython experiment containers
ml-engineering
Machine Learning Engineering Open Book
ml-ways
ML/DL Math and Method notes
porting
Helper scripts and notes that were used while porting various nlp models
python-tools
Python tools
stas00
the-art-of-debugging
The Art of Debugging
stas00's Repositories
stas00/ml-engineering
Machine Learning Engineering Open Book
stas00/the-art-of-debugging
The Art of Debugging
stas00/ipyexperiments
Automatic GPU+CPU memory profiling, re-use and memory leaks detection using jupyter/ipython experiment containers
stas00/ml-ways
ML/DL Math and Method notes
stas00/python-tools
Python tools
stas00/stas00
stas00/git-tools
helper git tools
stas00/conda-tools
helper tools for the conda environment
stas00/transformers
🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.
stas00/backups
an effort to resist Internet entropy - save useful knowledge
stas00/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
stas00/cookbook
Deep learning for dummies. All the practical details and useful utilities that go into working with real models.
stas00/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
stas00/accelerate
A simple way to train and use NLP models with multi-GPU, TPU, mixed-precision
stas00/hpc-toolkit
Cloud HPC Toolkit is an open-source software offered by Google Cloud which makes it easy for customers to deploy HPC environments on Google Cloud.
stas00/NeMo
NeMo: a toolkit for conversational AI
stas00/psg
Pocket Survival Guide for Sys Admin - http://psg.skinforum.org/ -
stas00/pytorch-lightning
The lightweight PyTorch wrapper for ML researchers. Scale your models. Write less boilerplate
stas00/unix-tools
Miscellaneous tools
stas00/bigscience-backup
stas00/datatrove
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
stas00/evaluate
🤗 Evaluate: A library for easily evaluating machine learning models and datasets.
stas00/m4-logs-backup
M4 experiment logbook
stas00/metaseq-backup
Repo for external large-scale work
stas00/nccl-tests
NCCL Tests
stas00/PIXIU
This repository introduces PIXIU, an open-source resource featuring the first financial large language models (LLMs), instruction tuning data, and evaluation benchmarks to holistically assess financial LLMs. Our goal is to continually push forward the open-source development of financial artificial intelligence (AI).
stas00/SimpleParsing
Simple, Elegant, Typed Argument Parsing with argparse
stas00/TransformerSizing
stas00/triton
Development repository for the Triton language and compiler
stas00/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs