Nicholas Broad's repositories
strideformer
Using short models to classify long texts
need4speed
Speed tests for language models in pytorch
hf-notebooks
A collection of various notebooks for atypical transformer usage.
encoder-decoders
Use models like Llama as an encoder-decoder
hp_wiki_scrapy
A scrapy project to pull text from the pages of harrypotter.fandom.com to use in a RAG model.
serverless-news
Create a serverless lambda function to pull recent news headlines and store them in a database
azureml-fa2-clm
Training a CLM using flash attention 2 in Azure ML
biomedical
Tools for curating biomedical training data for large-scale language modeling
health-fact
Experiments on the health fact dataset
kaggle-images
Upload images to put on kaggle
koila
Prevent PyTorch's `CUDA error: out of memory` in just 1 line of code.
notebooks
Notebooks using the Hugging Face libraries 🤗
tez
Tez is a super-simple and lightweight Trainer for PyTorch. It also comes with many utils that you can use to tackle over 90% of deep learning projects in PyTorch.
token-sequence-classification
Use labels as tokens to classify a sequence.
transformers
🤗Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.
transformers-notes
Notes with important details about papers, models, libraries related to transformers