Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

Resa-Yi
/
STILL-Trained-from-Scratch-SAE-OctoThinker-1B-Hybrid-Base-131k

Model card Files Files and versions
xet
Community
STILL-Trained-from-Scratch-SAE-OctoThinker-1B-Hybrid-Base-131k
4.3 GB
  • 2 contributors
History: 2 commits
farukakgul
add sae trained from scratch at layer 6
8d52005 3 months ago
  • model.layers.6
    add sae trained from scratch at layer 6 3 months ago
  • .gitattributes
    1.52 kB
    initial commit 3 months ago
  • README.md
    31 Bytes
    initial commit 3 months ago
  • config.json
    856 Bytes
    add sae trained from scratch at layer 6 3 months ago
  • optimizer_0.pt

    Detected Pickle imports (3)

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

    What is a pickle import?

    2.15 GB
    xet
    add sae trained from scratch at layer 6 3 months ago
  • rank_0_state.pt
    1.05 MB
    xet
    add sae trained from scratch at layer 6 3 months ago
  • state.pt

    Pickle imports

    • No problematic imports detected

    What is a pickle import?

    856 Bytes
    xet
    add sae trained from scratch at layer 6 3 months ago