Hugging Face's logo

google
/
tipsv2-g14

Zero-Shot Image Classification
Transformers
Safetensors
tipsv2
feature-extraction
vision
image-text
contrastive-learning
zero-shot
custom_code
Model card Files
xet
 Community
1
tipsv2-g14

Commit History

  1. Use relative imports for sibling modules (fixes local loading, save_pretrained, pickling)

    gberton
    3b89486

  1. Support sentencepiece 0.2.2 in text tokenizer

    gberton
    9b6d9f0

  1. Add arXiv tag to link the paper

    gberton
    Verified signature
    69dfacd

  2. Add arXiv paper link to citation

    gberton
    Verified signature
    88e2798

  3. Update files for transformers integration (#1)⁠

    gberton +1: guarin
    54cb39b

  1. Fix broken image URL and add missing .cpu() in code snippets

    gberton
    Verified signature
    a4f58f8

  2. Remove zero-shot segmentation snippet, link to GitHub for advanced use cases

    Gabriele
    18d5063

  1. PCA visualization: add whitening and sigmoid

    Gabriele
    4842da4

  2. Add navigation table linking all variants and DPT heads

    Gabriele
    cf63d64

  1. Switch to bus image with matching classes

    Gabriele
    be4b3bf

  2. Improve code examples: better classes, descriptive comments

    Gabriele
    d867321

  3. Use cat photo, add print statements to code examples

    Gabriele
    c1eb665

  4. Fix meta device crash: use pure Python for drop_path_rate

    Gabriele
    1785a7e

  5. Fix zero-shot segmentation section, use public example image

    Gabriele
    ee929f8

  1. Update README

    Gabriele
    c7d0623

  2. Align image_encoder.py drop_path_rate computation with upstream

    Gabriele
    8e6f865

  3. Upload README.md with huggingface_hub

    gberton
    Verified signature
    0a0e878

  1. Upload model.safetensors with huggingface_hub

    gberton
    Verified signature
    593cb6c

  2. Upload README.md with huggingface_hub

    gberton
    Verified signature
    7ff1d09

  3. Upload config.json with huggingface_hub

    gberton
    Verified signature
    e3627f6

  4. Upload tokenizer.model with huggingface_hub

    gberton
    Verified signature
    23b4e86

  5. Upload text_encoder.py with huggingface_hub

    gberton
    Verified signature
    aee1bb7

  6. Upload image_encoder.py with huggingface_hub

    gberton
    Verified signature
    cfbf0ec

  7. Upload modeling_tips.py with huggingface_hub

    gberton
    Verified signature
    8a5436b

  8. Upload configuration_tips.py with huggingface_hub

    gberton
    Verified signature
    a0a1e6a

  9. initial commit

    gberton
    Verified signature
    fad3103