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

throsturx
/
bihmoe-poc

PyTorch
Transformers
English
research
mixture-of-experts
interpretability
Model card Files Files and versions
xet
Community

Instructions to use throsturx/bihmoe-poc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use throsturx/bihmoe-poc with Transformers:

    # Load model directly
    from transformers import AutoModel
    model = AutoModel.from_pretrained("throsturx/bihmoe-poc", dtype="auto")
  • Notebooks
  • Google Colab
  • Kaggle
bihmoe-poc / src /bihmoe /models
19.8 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 11 commits
Throstur
arch: add chiasm_mode=bias to avoid global-branch starvation
74790c5 5 months ago
  • __init__.py
    0 Bytes
    head: make models query-aware (last-token readout) + trainer update 5 months ago
  • blocks.py
    4.68 kB
    arch-v2: asymmetry (local vs global), competitive callosum, optic-chiasm bias; default stem=0 5 months ago
  • dense.py
    2.14 kB
    head: make models query-aware (last-token readout) + trainer update 5 months ago
  • structured.py
    12.9 kB
    arch: add chiasm_mode=bias to avoid global-branch starvation 5 months ago