Instructions to use josmunpen/mt5-small-spanish-summarization with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use josmunpen/mt5-small-spanish-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="josmunpen/mt5-small-spanish-summarization")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("josmunpen/mt5-small-spanish-summarization") model = AutoModelForSeq2SeqLM.from_pretrained("josmunpen/mt5-small-spanish-summarization") - Notebooks
- Google Colab
- Kaggle
how to get bigger responses?
#3
by masterchop - opened
the sumarizatrion is to small is there a way to make it bigger.
Hi!
Since the model is trained to generate headlines, its outputs are usually short. Here you can check the frequency of words used as output in the dataset:
Also, the max_length field of the target tokenizer was set to 128.
If you want other types of outputs, I'm afraid you should retrain the model.
Thank you for answeing.
masterchop changed discussion status to closed
