Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

Idan
/
fga-avsd

Transformers
Safetensors
fga_avsd_generation
audio-visual-scene-aware-dialog
video-question-answering
factor-graph-attention
multimodal
Model card Files Files and versions
xet
Community

Instructions to use Idan/fga-avsd with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use Idan/fga-avsd with Transformers:

    # Load model directly
    from transformers import AVSDForResponseGeneration
    model = AVSDForResponseGeneration.from_pretrained("Idan/fga-avsd", device_map="auto")
  • Notebooks
  • Google Colab
  • Kaggle
fga-avsd
54.8 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 7 commits
Idan's picture
Idan
Seeded numbers; the grounding gap is resolved by projection width
0ea23aa verified 2 days ago
  • .gitattributes
    1.52 kB
    initial commit 3 days ago
  • README.md
    4.16 kB
    Seeded numbers; the grounding gap is resolved by projection width 2 days ago
  • config.json
    797 Bytes
    Widen the decoder projection to 1024: CIDEr 0.887, and the video ablation now bites 2 days ago
  • model.safetensors
    54.6 MB
    xet
    Widen the decoder projection to 1024: CIDEr 0.887, and the video ablation now bites 2 days ago
  • pred_q1024_s3.json
    86.2 kB
    Predictions from the published checkpoint 2 days ago
  • pred_v4_paper.json
    86.6 kB
    Generated answers for all 1,710 test questions 3 days ago