Instructions to use knowledgator/comprehend_it-multilingual-t5-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use knowledgator/comprehend_it-multilingual-t5-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-classification", model="knowledgator/comprehend_it-multilingual-t5-base")# Load model directly from transformers import T5ForZeroShotClassification model = T5ForZeroShotClassification.from_pretrained("knowledgator/comprehend_it-multilingual-t5-base", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Few shot
#1
by Batchounet - opened
Thanks for the work !It is not specified in the model card, but is this possible to train the algorithm for using it as few_shot classification such as for
comprehend_it-base?
@Batchounet , thank you for contacting us. Yes, you can fine-tune the model using LiqFit in a few shots. However, we are still researching the best hyperparameters to do this. We will be happy to hear your results from the experiments anytime.