Full training results & evaluation with BERTScore

Add evaluation_report.json for metrics display

Add metrics tab with evaluation report, show all labels

Force HF Space rebuild with cache bust

Updated Gradio Demo to match new approac for book descritpions and shown metrics

Medium training run

Fix literary summaries: exclude plays/epics, use human summaries from BookSum

Fix literary summaries: use only BookSum data (not Gutenberg excerpts)

Medium training run

Fix regression: restore balanced training settings, add technical manual filter

Medium training run

Major improvements: real titles, anti-overfitting, better demo UX

Merge remote-tracking branch 'refs/remotes/origin/main'

Medium training run

Changed license

New trianing run on english only data

Add English language filter to all data downloads

Updated Training run, fixed dataset langauge issue

Improve discovery dataset quality

Demo requirements bug fix

Fix type hints in demo_gradio.py for Pylance

Trigger rebuild

Use HF Datasets for discovery demo

Fix catalog.json path resolution for HF Space

Redesign Gradio demo as book/paper discovery tool

Fix Gradio demo metrics display and visualization script MLflow URI

Updated the model with new bug fixes

Fixed compiling issue, added legnth penalty, and atttempting freezing encoder layers 0-5 to lower parameters and preserve T5's langauge understanding.

Optimize Docker for CPU-only (10x faster builds)

Remove custom theme - use Gradio default for compatibility

Ignore mlruns.db binary file

Minor fixes to Gradio and visualization scripts

Improve emotion task architecture and fix visualizations

Clean up codebase and fix training bugs

Fix Gradio demo: whole-book summaries, emotion sorting, styling

Add demo data for HF Space (books + news samples)

Redesign Gradio demo with book/news browsing, update .gitignore

Update Gradio demo, inference factory, and evaluation results

Update Gradio demo, inference factory, and evaluation results

Update LexiMind: improved training, model architecture, and evaluation

Improve summarization output quality

Expand datasets: GoEmotions (28 emotions), Yahoo Answers (10 topics), BookSum

Fix: Regenerate tokenizer without add_prefix_space to fix CI

Demo: Update Gradio UI with metrics, visualizations, and clean tabs

CI: Add sentencepiece for T5 tokenizer tests

CI: Split lint and test jobs, add pip caching for faster builds

Track spiece.model with Git LFS

Fix tokenizer files, remove LFS dependency for .model files

Exclude binary files (png, pt) from repo

Fix Pylance type errors, add inductor compilation support