Summarization
Transformers
PyTorch
TensorFlow
JAX
TensorBoard
Italian
mt5
text2text-generation
italian
sequence-to-sequence
fanpage
ilpost
Instructions to use gsarti/mt5-base-news-summarization with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use gsarti/mt5-base-news-summarization 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="gsarti/mt5-base-news-summarization")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("gsarti/mt5-base-news-summarization") model = AutoModelForSeq2SeqLM.from_pretrained("gsarti/mt5-base-news-summarization", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from gsarti/mt5-base-news-summarization: direct link, hf CLI and curl.
- Browser
- Download file 408 Bytes
-
https://huggingface.co/gsarti/mt5-base-news-summarization/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://gsarti/mt5-base-news-summarization/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/gsarti/mt5-base-news-summarization/resolve/main/tokenizer_config.json
408 Bytes
| {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "name_or_path": "google/mt5-base", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"} |