col-a-guo/guo_chen_jang_ms_project

Python

1

251 commits

updated May 22, 2026

See the code

README

FOR SUBMISSION REQUIREMENTS:

Files don't require any user input. Just install dependencies and run. Train and test for each model are in the same file.

Current version needs feb_20_stitched (test and train), feb_24_combined (test and train), and BERT_pretrain.txt to run everything.

BERTgetpretraintxt.py is set up for local and here for viewing purposes, it won't run without a much larger dataset download.

Push to Hub won't work without huggingface login.

All code is original; some AI assistance, especially on rote tasks (e.g. data cleaning, visualization, baseline comments) but minimal for important parts (i.e. the actual models, specific comments)

Not written in Markdown, so it's shown here as plain text — view it formatted on GitHub.

col-a-guo/guo_chen_jang_ms_project

Python

1

251 commits

updated May 22, 2026

See the code

README

FOR SUBMISSION REQUIREMENTS:

Files don't require any user input. Just install dependencies and run. Train and test for each model are in the same file.

Current version needs feb_20_stitched (test and train), feb_24_combined (test and train), and BERT_pretrain.txt to run everything.

BERTgetpretraintxt.py is set up for local and here for viewing purposes, it won't run without a much larger dataset download.

Push to Hub won't work without huggingface login.

All code is original; some AI assistance, especially on rote tasks (e.g. data cleaning, visualization, baseline comments) but minimal for important parts (i.e. the actual models, specific comments)

Not written in Markdown, so it's shown here as plain text — view it formatted on GitHub.