Nicholas Broad's Projects
Training a CLM using flash attention 2 in Azure ML
Tools for curating biomedical training data for large-scale language modeling
Use models like Llama as an encoder-decoder
Generate massive amounts of fake data in the browser and node.js
Experiments on the health fact dataset
A collection of various notebooks for atypical transformer usage.
A scrapy project to pull text from the pages of harrypotter.fandom.com to use in a RAG model.
Upload images to put on kaggle
Prevent PyTorch's `CUDA error: out of memory` in just 1 line of code.
CodeForDurham helps Meals on Wheels
Speed tests for language models in pytorch
Notebooks using the Hugging Face libraries ๐ค
Create a serverless lambda function to pull recent news headlines and store them in a database
Using short models to classify long texts
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.
Use labels as tokens to classify a sequence.
๐คTransformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.
Notes with important details about papers, models, libraries related to transformers
Code for the Kaggle competition: U.S. Patent Phrase to Phrase Matching https://www.kaggle.com/competitions/us-patent-phrase-to-phrase-matching