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

versae
/
roberta-base-ncc-512b

Fill-Mask
Transformers
JAX
TensorBoard
roberta
Model card Files Files and versions
xet
Metrics Training metrics Community

Instructions to use versae/roberta-base-ncc-512b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use versae/roberta-base-ncc-512b with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("fill-mask", model="versae/roberta-base-ncc-512b")
    # Load model directly
    from transformers import AutoTokenizer, AutoModelForMaskedLM
    
    tokenizer = AutoTokenizer.from_pretrained("versae/roberta-base-ncc-512b")
    model = AutoModelForMaskedLM.from_pretrained("versae/roberta-base-ncc-512b")
  • Notebooks
  • Google Colab
  • Kaggle
roberta-base-ncc-512b
853 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 169 commits
versae's picture
versae
Final evals
9c4ec38 over 4 years ago
  • wandb
    Final evals over 4 years ago
  • .gitattributes
    1.45 kB
    Saving weights and logs of step 111000 over 4 years ago
  • config.json
    639 Bytes
    Testing lr 0.00015 over 4 years ago
  • eval_results.json
    122 Bytes
    Final evals over 4 years ago
  • events.out.tfevents.1642691672.t1v-n-00e295a4-w-0.2612942.0.v2
    24 MB
    xet
    Saving weights and logs of step 162000 over 4 years ago
  • flax_model.msgpack
    499 MB
    xet
    Saving weights and logs of step 162000 over 4 years ago
  • merges.txt
    476 kB
    Testing lr 0.00015 over 4 years ago
  • run_mlm_flax.py
    36 kB
    Saving weights and logs of step 1000 over 4 years ago
  • special_tokens_map.json
    239 Bytes
    Testing lr 0.00015 over 4 years ago
  • tokenizer.json
    2.15 MB
    Testing lr 0.00015 over 4 years ago
  • tokenizer_config.json
    314 Bytes
    Testing lr 0.00015 over 4 years ago
  • train.128.sh
    715 Bytes
    Testing lr 0.00015 over 4 years ago
  • train.512.sh
    737 Bytes
    Testing lr 0.00015 over 4 years ago
  • vocab.json
    818 kB
    Testing lr 0.00015 over 4 years ago