Embedded Files
How we used a large language model to train compact sentiment analysis models specifically for literary texts, and what we learned from the results.
Can a 600M-Parameter LLM Learn Sentiment Analysis from a Larger Model?
Can we really benefit from LLM distillation for common DH tasks. Sentiment Analysis with LLMs demonstrates that fine-tuning on synthetic data can be very beneficial even if not so ideal.
I recently built a small tool for a problem that often appears when working with locally hosted language models: how to let other people try a model running on your own machine without setting up a full deployment environment.
New RoBERTa-based experimental model which promises to do well with fiction.
Outputs sentiment from 1 (negative) to 10 (positive).
Fine-tuned LLM to generate short storiesn by title, genre, and keyword
Japan's National Diet Records Analysis App
Download your speeches dataset and reveal topics discussed there.
Page updated
Google Sites
Report abuse