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

Gugu8
/
Corpus-ViT

Feature Extraction
Transformers
Safetensors
PyTorch
corpus_vit
vision-encoder
llm-connector
foveated
variable-length
image-text-retrieval
custom_code
Model card Files Files and versions
xet
Community

Instructions to use Gugu8/Corpus-ViT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use Gugu8/Corpus-ViT with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("feature-extraction", model="Gugu8/Corpus-ViT", trust_remote_code=True)
    # pip install -U transformers accelerate
    # Load model directly
    from transformers import AutoModel
    model = AutoModel.from_pretrained("Gugu8/Corpus-ViT", trust_remote_code=True, device_map="auto")
  • Notebooks
  • Google Colab
  • Kaggle
Corpus-ViT
100 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 21 commits
Gugu8's picture
Gugu8
Corpus-ViT v31: trained at full k_max=49 budget, 31.10 mean R@1 held-out
fe2a391 verified 18 days ago
  • .gitattributes
    1.52 kB
    initial commit 22 days ago
  • README.md
    9.02 kB
    Corpus-ViT v31: trained at full k_max=49 budget, 31.10 mean R@1 held-out 18 days ago
  • benchmarks_kaggle_v28_60k.json
    4.27 kB
    Corpus-ViT v31: trained at full k_max=49 budget, 31.10 mean R@1 held-out 18 days ago
  • benchmarks_kaggle_v31_kmax49_heldout.json
    2.37 kB
    Corpus-ViT v31: trained at full k_max=49 budget, 31.10 mean R@1 held-out 18 days ago
  • config.json
    862 Bytes
    Corpus-ViT v31: trained at full k_max=49 budget, 31.10 mean R@1 held-out 18 days ago
  • configuration_corpusvit.py
    1.42 kB
    Make config self-contained so trust_remote_code loading works 22 days ago
  • model.safetensors
    99.8 MB
    xet
    Corpus-ViT v31: trained at full k_max=49 budget, 31.10 mean R@1 held-out 18 days ago
  • modeling_corpusvit.py
    12.2 kB
    Docs: report k=49 operating point (30.00 mean R@1); k_max is the budget cap (grid*grid=49), not 24 19 days ago
  • train_corpusvit.py
    2.22 kB
    Corpus-ViT: foveated encoder with runtime-selectable token budget (49+3k) 22 days ago
  • train_log_v28_60k.jsonl
    209 kB
    Corpus-ViT v31: trained at full k_max=49 budget, 31.10 mean R@1 held-out 18 days ago
  • train_log_v31_kmax49.jsonl
    209 kB
    Corpus-ViT v31: trained at full k_max=49 budget, 31.10 mean R@1 held-out 18 days ago