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
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

ARTeLab
/
it5-summarization-mlsum

Summarization
Transformers
PyTorch
Safetensors
Italian
t5
text2text-generation
text-generation-inference
Model card Files Files and versions
xet
Community
5

Instructions to use ARTeLab/it5-summarization-mlsum with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use ARTeLab/it5-summarization-mlsum with Transformers:

    # Use a pipeline as a high-level helper
    # Warning: Pipeline type "summarization" is no longer supported in transformers v5.
    # You must load the model directly (see below) or downgrade to v4.x with:
    # 'pip install "transformers<5.0.0'
    from transformers import pipeline
    
    pipe = pipeline("summarization", model="ARTeLab/it5-summarization-mlsum")
    # Load model directly
    from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
    
    tokenizer = AutoTokenizer.from_pretrained("ARTeLab/it5-summarization-mlsum")
    model = AutoModelForSeq2SeqLM.from_pretrained("ARTeLab/it5-summarization-mlsum")
  • Notebooks
  • Google Colab
  • Kaggle
it5-summarization-mlsum
992 MB
Ctrl+K
Ctrl+K
  • 5 contributors
History: 7 commits
efederici's picture
efederici
Update README.md
8d103e8 over 4 years ago
  • .gitattributes
    1.18 kB
    initial commit over 4 years ago
  • README.md
    1.08 kB
    Update README.md over 4 years ago
  • all_results.json
    842 Bytes
    add trained model over 4 years ago
  • config.json
    703 Bytes
    add trained model over 4 years ago
  • eval_results.json
    329 Bytes
    add trained model over 4 years ago
  • generated_predictions.txt
    422 kB
    add trained model over 4 years ago
  • predict_results.json
    341 Bytes
    add trained model over 4 years ago
  • pytorch_model.bin

    Detected Pickle imports (3)

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

    What is a pickle import?

    990 MB
    xet
    add trained model over 4 years ago
  • special_tokens_map.json
    1.79 kB
    add trained model over 4 years ago
  • tokenizer.json
    1.02 MB
    add trained model over 4 years ago
  • tokenizer_config.json
    1.91 kB
    add trained model over 4 years ago
  • train_results.json
    194 Bytes
    add trained model over 4 years ago
  • trainer_state.json
    5.72 kB
    add trained model over 4 years ago
  • training_args.bin

    Detected Pickle imports (5)

    • "transformers.trainer_utils.HubStrategy",
    • "transformers.trainer_utils.SchedulerType",
    • "transformers.training_args_seq2seq.Seq2SeqTrainingArguments",
    • "torch.device",
    • "transformers.trainer_utils.IntervalStrategy"

    How to fix it?

    2.93 kB
    xet
    add trained model over 4 years ago