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

EleutherAI
/
GPT-2-wikitext-chunks-epsroot-0

Safetensors
gpt2
Model card Files Files and versions
xet
Community
GPT-2-wikitext-chunks-epsroot-0
1.15 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 3 commits
luciaquirke's picture
luciaquirke
Add epsroot-0 AdamW optimizer state for Adam-normalized attribution
f821b85 verified about 1 month ago
  • .gitattributes
    1.52 kB
    initial commit about 1 month ago
  • config.json
    961 Bytes
    Add base GPT-2 trained on wikitext 512-chunks (eps_root=0), before leave-1%-out retrains (checkpoints/step_287) about 1 month ago
  • generation_config.json
    119 Bytes
    Add base GPT-2 trained on wikitext 512-chunks (eps_root=0), before leave-1%-out retrains (checkpoints/step_287) about 1 month ago
  • model.safetensors
    498 MB
    xet
    Add base GPT-2 trained on wikitext 512-chunks (eps_root=0), before leave-1%-out retrains (checkpoints/step_287) about 1 month ago
  • optimizer.pt

    Detected Pickle imports (3)

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

    What is a pickle import?

    652 MB
    xet
    Add epsroot-0 AdamW optimizer state for Adam-normalized attribution about 1 month ago
  • tokenizer.json
    3.56 MB
    Add base GPT-2 trained on wikitext 512-chunks (eps_root=0), before leave-1%-out retrains (checkpoints/step_287) about 1 month ago
  • tokenizer_config.json
    315 Bytes
    Add base GPT-2 trained on wikitext 512-chunks (eps_root=0), before leave-1%-out retrains (checkpoints/step_287) about 1 month ago