Commit Graph

Select branches

Hide Pull Requests

main

Mono Color

• 0c199256dd Add extra debugging main Timothy Allen 2023-12-31 10:32:32 +02:00
• c1e3ffdc0b Switch to SentencePiece for tokenisation and Roberta for the model Timothy Allen 2023-12-30 15:19:52 +02:00
• 9052767750 Convert to a multi-hot index in the CSV, to simplify our DataSets and DataLoaders Timothy Allen 2023-12-30 12:30:43 +02:00
• 0752eefaaa Add original title to story text Timothy Allen 2023-12-30 12:29:56 +02:00
• d2a5bb1717 Cleanup, and device-aware training Timothy Allen 2023-12-21 11:29:59 +02:00
• d46a5baebe Fix evaluation, as well as progress reporting. Timothy Allen 2023-12-19 09:26:27 +02:00
• 6864e43ce4 Metadata Timothy Allen 2023-12-13 20:22:39 +02:00
• 22df0a0ba0 First working model tim 2023-12-13 19:15:46 +02:00
• b96c920d33 Get model working (basically) tim 2023-12-13 11:57:48 +02:00
• 58edb72e6a Add reminder about old categories tim 2023-12-02 00:17:58 +02:00
• 6c46404234 Format for poetry and add debugging tim 2023-12-01 23:02:05 +02:00
• 06512d71d5 Add dependencies tim 2023-12-01 22:16:56 +02:00
• 327367bbea Move to new location tim 2023-12-01 21:44:36 +02:00
• b02fa3c9b0 Clean up some minor issues (like iterating over the DataSet) & simplify tim 2023-12-01 21:05:47 +02:00
• 31319bab0c Add possible split between training and validation data tim 2023-11-30 02:00:56 +02:00
• 7108652756 First pass at imbibing a CSV of data and turning it into a dataset, and thence into a dataloader tim 2023-11-30 01:53:49 +02:00
• 60f8afefea Convert a bunch of XML files into a CSV dataset tim 2023-11-29 22:08:11 +02:00
• 3fcd445a83 v0.1.1 tim 2023-12-01 21:26:17 +02:00
• 3c912c4171 v0.1.0 tim 2023-12-01 21:24:42 +02:00