Spaces:

david167
/

question-generation-api

Sleeping

App Files Files Community

question-generation-api

416 kB

Ctrl+K

Ctrl+K

1 contributor

History: 71 commits

david167's picture

Enable concurrency_limit=10 for better parallel processing

0b2f34f 7 months ago

.gitattributes

1.52 kB
initial commit 8 months ago
.gitignore

472 Bytes
Initial setup: Question Generation API with DeepHermes reasoning model 8 months ago
2024 NFL Rule Book.csv

320 kB
Major update: Add NFL training data generation and improve model handling 8 months ago
Dockerfile

1.28 kB
Major update: Add NFL training data generation and improve model handling 8 months ago
README.md

5.24 kB
Switch back to Llama-3.1-8B-Instruct model: update prompts, generation params, and UI descriptions 8 months ago
app.py

13.8 kB
Upgrade to Llama 3.1 8B-Instruct for better long-form content 8 months ago
generate_nfl_training_data.py

18.9 kB
Major update: Add NFL training data generation and improve model handling 8 months ago
gradio_app.py

9.7 kB
Enable concurrency_limit=10 for better parallel processing 7 months ago
gradio_app_complex.py

9.26 kB
SIMPLE WORKING API: Fix Gradio interface issues, use simple Interface instead of Blocks, proper API structure 8 months ago
gradio_app_new.py

7.81 kB
Fix Gradio interface: Remove chatbot format issues, add proper API endpoint structure 8 months ago
gradio_app_old.py

13 kB
ELEGANT API REWRITE: Clean architecture, smart token allocation, proper JSON extraction - eliminate placeholder generation 8 months ago
gradio_app_simple.py

7.16 kB
BULLETPROOF API: Remove ALL State components, use JSON inputs instead, proper input/output matching, ZERO GRADIO ERRORS 8 months ago
requirements.txt

297 Bytes
Fix build error: Remove flash-attn dependency 8 months ago
run_nfl_generator.py

3.65 kB
Major update: Add NFL training data generation and improve model handling 8 months ago
sample_2024_nfl_rulebook.csv

1.51 kB
Major update: Add NFL training data generation and improve model handling 8 months ago
upgrade_models.py

2.54 kB
Upgrade to Llama 3.1 8B-Instruct for better long-form content 8 months ago