Transformers
PyTorch
TensorFlow
JAX
TensorBoard
Italian
mt5
text2text-generation
italian
sequence-to-sequence
squad_it
text2text-question-answering
Eval Results (legacy)
Instructions to use gsarti/mt5-small-question-answering with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use gsarti/mt5-small-question-answering with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("gsarti/mt5-small-question-answering") model = AutoModelForSeq2SeqLM.from_pretrained("gsarti/mt5-small-question-answering", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 9cd3577e6cc5d0d15cb179994c6996cea5a51bb667eba4fc5a73ffd1a61ae818
- Size of remote file:
- 1.2 GB
- SHA256:
- 4befcc31e1ad6a509f86d6a984c949d4033616dccac47352e1d0f907e6d537e5
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.