Benjamin Warner's repositories
commented-transformers
Highly commented implementations of Transformers in PyTorch
NLPbookstudygroup
NLP with Transformers Study Group Materials & Resources
fastai2022part2studygroup
fastai course 2022 part 2 study group presentation resources
blurr
A library that integrates huggingface transformers with the world of fastai, giving fastai devs everything they need to train, evaluate, and deploy transformer specific models.
cramming
Cramming the training of a (BERT-type) language model into limited compute.
cule
CuLE: A CUDA port of the Atari Learning Environment (ALE)
fastai
The fastai deep learning library
fastai2_tabular_hybrid
Developing and integrating methods for fastai2 tabular with other datatypes
fastai_extensions
Code you can use jointly with fastai
reinforcement_scratch
Hugging Face Deep Reinforcement Learning Course Scratch Repo
fastcore
Python supercharged for the fastai library
ffcv
FFCV: Fast Forward Computer Vision (and other ML workloads!)
flash-attention
Fast and memory-efficient exact attention
images_for_blog_posts
Separate Repository of Larger Images for benjaminwarner.dev
llama-recipes
Examples and recipes for Llama 2 model
nbdev
Create delightful python projects using Jupyter Notebooks
stable-diffusion-dream-script
This version of CompVis/stable-diffusion features an interactive command-line script that combines text2img and img2img functionality in a "dream bot" style interface.
subclassed_tensors
Exploring Channels Last in PyTorch
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
vos
source code for ICLR'22 paper "VOS: Learning What You Don’t Know by Virtual Outlier Synthesis"
workflows
Composite Actions workflows for use in fastai projects