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
/
captionbert-8192-v2

Feature Extraction
Transformers
TensorBoard
Safetensors
English
captionbert_v2
sentence-similarity
consensus-distillation
geometric-deep-learning
amoe
custom_code
Model card Files Files and versions
xet
Metrics Training metrics Community

Instructions to use AbstractPhil/captionbert-8192-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use AbstractPhil/captionbert-8192-v2 with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("feature-extraction", model="AbstractPhil/captionbert-8192-v2", trust_remote_code=True)
    # Load model directly
    from transformers import AutoModel
    model = AutoModel.from_pretrained("AbstractPhil/captionbert-8192-v2", trust_remote_code=True, device_map="auto")
  • Notebooks
  • Google Colab
  • Kaggle
captionbert-8192-v2 / amoe
84.1 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 27 commits
AbstractPhil's picture
AbstractPhil
remove stray: byte-identical duplicate (sha256 45bcbf0c) of amoe/sts/captionbert-v2-sts-anchor.anchor.pt, which survives. The combo folder ships only its own -combo anchor; the solo anchor sitting here invited loading the wrong artifact
be530bf verified about 9 hours ago
  • collective
    card: this folder is the 3-ANCHOR COLLECTIVE, not the 2-anchor moe run - the moe card had been copied here wholesale (wrong title, wrong anchor table, wrong results, moe-v1 amplitude telemetry). Real 8-task rows, greedy sweep incl. the random capacity control, correct in-folder load paths, masked-vs-solo labelled about 9 hours ago
  • moe-v2
    card: moe-v2 carries its OWN numbers and the tau sweep (sharper routing is worse, monotone in 2 seeds while separation rises). Load path pointed at amoe/moe/ whose anchors are a DIFFERENT checkpoint (f13ad5ad vs 0029ad69) - fixed to this folder about 9 hours ago
  • moe
    final: 2 anchors + dispatch + card 1 day ago
  • sts-combo
    remove stray: byte-identical duplicate (sha256 45bcbf0c) of amoe/sts/captionbert-v2-sts-anchor.anchor.pt, which survives. The combo folder ships only its own -combo anchor; the solo anchor sitting here invited loading the wrong artifact about 9 hours ago
  • sts
    final anchor 2 days ago