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

AbstractPhil
/
qwen3.5-0.8b-relay-caption

Transformers
image-captioning
adapter
qwen3.5
relay-patchwork
Model card Files Files and versions
xet
Community

Instructions to use AbstractPhil/qwen3.5-0.8b-relay-caption with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use AbstractPhil/qwen3.5-0.8b-relay-caption with Transformers:

    # Load model directly
    from transformers import AutoModel
    model = AutoModel.from_pretrained("AbstractPhil/qwen3.5-0.8b-relay-caption", device_map="auto")
  • Notebooks
  • Google Colab
  • Kaggle
qwen3.5-0.8b-relay-caption
50.3 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 3 commits
AbstractPhil's picture
AbstractPhil
card: e004e trade-off caveat (depth JSON validity 1.0->0.0 with adapter loaded) + current loader
7a824fa verified 12 days ago
  • .gitattributes
    1.52 kB
    initial commit 12 days ago
  • README.md
    3.57 kB
    card: e004e trade-off caveat (depth JSON validity 1.0->0.0 with adapter loaded) + current loader 12 days ago
  • relay_caption.py
    5.78 kB
    RelayPatchwork caption adapter v1: card + fidelity-tested loader + both seed checkpoints (held-out 0.408->0.706/0.704; artifact+loader gates PASS; e004e trade-off documented) 12 days ago
  • v35e4_caption_full_s0.pt

    Detected Pickle imports (3)

    • "collections.OrderedDict",
    • "torch.FloatStorage",
    • "torch._utils._rebuild_tensor_v2"

    What is a pickle import?

    25.2 MB
    xet
    RelayPatchwork caption adapter v1: card + fidelity-tested loader + both seed checkpoints (held-out 0.408->0.706/0.704; artifact+loader gates PASS; e004e trade-off documented) 12 days ago
  • v35e4_caption_full_s1.pt

    Detected Pickle imports (3)

    • "collections.OrderedDict",
    • "torch._utils._rebuild_tensor_v2",
    • "torch.FloatStorage"

    What is a pickle import?

    25.2 MB
    xet
    RelayPatchwork caption adapter v1: card + fidelity-tested loader + both seed checkpoints (held-out 0.408->0.706/0.704; artifact+loader gates PASS; e004e trade-off documented) 12 days ago