Hugging Face's logo

Spaces:
david167
/
question-generation-api
Paused

App Files Community
question-generation-api / app.py

Commit History

  1. Upgrade to Llama 3.1 8B-Instruct for better long-form content⁠

    david167
    6ea58d5

  1. Fix build error: Remove flash-attn dependency⁠

    david167
    7629837

  2. Speed optimizations: Switch to Mistral-7B + optimize generation params⁠

    david167
    fac0be2

  1. Major update: Add NFL training data generation and improve model handling⁠

    david167
    992eedb

  1. Fix syntax errors: correct comma placement and indentation

    david167
    0b607e8

  2. Force all CUDA operations to cuda:0 and use device_map to prevent multi-GPU distribution

    david167
    01a04bc

  3. Fix multi-GPU device placement error: disable device_map auto and ensure tensors on same device

    david167
    0331461

  4. Fix duplicate import in app.py

    david167
    000a38b

  5. Switch to Llama-3.1-8B-Instruct: update model loading, prompts, and generation parameters

    david167
    8b5e9db

  6. Switch to FLAN-T5-Large: uses standard HF storage, excellent for question generation

    david167
    203ee8d

  7. Fix XetHub issue: use Meta-Llama-3.1-8B-Instruct (official HF storage)

    david167
    444b4d9

  8. Fix download errors and warnings: retry logic + clean startup logs

    david167
    de72460

  9. Fix version conflict: use PyTorch 2.5.0 + TorchVision 0.20.0 exact match

    david167
    67f9bcb

  10. Use PyTorch 2.5.1 with safetensors to avoid CVE-2025-32434 - practical fix

    david167
    c6d6f6c

  11. Fix PyTorch CVE-2025-32434: upgrade to v2.6+, use safetensors, restore Llama 3.1

    david167
    adea437

  12. Deploy temporary working model: DialoGPT while awaiting Llama 3.1 access

    david167
    23353f8

  13. Fix permissions error: proper cache directory and HF token auth for Llama 3.1

    david167
    bd1b0d6

  14. Major optimization: Replace llama-cpp-python with transformers to eliminate compilation

    david167
    4656a02

  15. Simplify build: use CPU llama-cpp-python for reliability

    david167
    0516287

  16. Initial setup: Question Generation API with DeepHermes reasoning model

    david167
    0bf99b7