Spaces:
Running
Running
Commit History
-
Use explicit Spaces GPU decorators Running
shouryad1105a7 -
Add Spaces GPU decorators for ZeroGPU startup
shourya96d64c3 -
Fix Gradio launch argument for v5
shouryaef56a1c -
Downgrade Gradio for Spaces compatibility
shouryade8cf16 -
Fix Spaces startup configuration
shouryab9d335b
-
fixes
shouryacc69299 -
Add generated PPTX slides and improved converter script
shouryabbaad34
-
Fix NER model ID and add resilient fallback loading
shouryad153152 -
Fix summarization JSON output and generation config
shourya3e2bd13 -
Pin Python runtime and anyio for stability
shourya0cbebb5 -
Update app docs, setup scripts, and utils
shourya62a67da
-
Fix Gradio 6.0 deprecation warnings: move theme to launch(), remove share=True on Spaces, disable SSR warnings
shourya7909984 -
Add pre-downloaded lightweight models (DistilBERT + BERT) for offline demo - 675MB via Git LFS
shourya8e7816a -
Add pre-session setup scripts
shourya- download_models.py: Pre-cache all models locally (~2-3GB) - convert_slides_to_pptx.py: Convert markdown slides to PPTX - prewarm_spaces.py: Test Spaces app and verify everything works - setup.sh: Automated all-in-one setup - scripts/README.md: Complete documentation and troubleshooting These scripts prepare for your session in ~30 minutes total. Recommended: Run on laptop ~30 min before presenting.2a31b59 -
Optimize Spaces startup performance
shourya- Implement lazy loading for sentence-transformers (only load on-demand) - Force CPU usage for pipelines (safer for Spaces with limited resources) - Remove gr.Examples components to reduce startup time - Add error handling for pipeline loading - Use import caching to prevent repeated module loads These changes should make the app startup 50-70% faster.6995afb -
Add missing sentence-transformers dependency
shouryafa7a6ba -
Add HuggingFace Enabling Sessions interactive demo
shourya- Created Gradio app with 3 tabs (Session 1 intro, Session 2 hands-on, Resources) - Added configuration for 5 NLP tasks (Sentiment, NER, QA, Summarization, Similarity) - Created utility functions for model inference and tokenization - Added comprehensive slide content (SESSION1, SESSION2) - Added sample data and demo examples - Created speaker notes with detailed presentation guide - Updated README with full documentation Features: - Live inference playground with 5+ NLP tasks - Interactive tokenization explorer - Sample data for all demonstrations - Production-ready configuration - Attendee-friendly resources tab10b8b4e -
test
shourya1ac4772
-
initial commit
Verified signature008f208