Stuck on an issue?

Lightrun Answers was designed to reduce the constant googling that comes with debugging 3rd party libraries. It collects links to all the places you might be looking at while hunting down a tough bug.

And, if you’re still stuck at the end, we’re happy to hop on a call to see how we can help out.

Instructions to use pre-trained models

See original GitHub issue

Given the current documentation, it is not clear to me how to use a pre-trained model. My understanding is that using the following will not download the pre-trained model:

model = ClassificationModel('bert', 'bert-base-multilingual-cased')

If this understanding is correct, how can I download a pre-trained model and use it in simpletransformers. Clear instructions on how to do that would be most welcome.

Issue Analytics

State:
Created 4 years ago
Comments:6 (4 by maintainers)

Top GitHub Comments

1reaction

ThilinaRajapaksecommented, Nov 21, 2019

I realize that it is not explicitly stated in the docs, but that line will download the pre-trained model.

0reactions

ThilinaRajapaksecommented, Apr 17, 2020

Yeah, community models will be downloaded as long as the primary model type (BERT, RoBERTa, XLNet, etc.) is supported for that particular task.

Top Results From Across the Web

How to use a pre-trained deep learning model - Educative.io

Points to consider before moving on to the implementation · Import the required libraries · Load the model · Load the image ·...

Transfer learning from pre-trained models | by Pedro Marcelino

4. Transfer learning process · Select a pre-trained model. · Classify your problem according to the Size-Similarity Matrix. In Figure 3 you have...

Transfer learning and fine-tuning | TensorFlow Core

A pre-trained model is a saved network that was previously trained on a large dataset, typically on a large-scale image-classification task. You either...

Using pretrained models - Hugging Face Course

When using a pretrained model, make sure to check how it was trained, on which datasets, its limits, and its biases. All of...

Transfer Learning in Keras with Computer Vision Models

How to Use Pre-Trained Models ... The use of a pre-trained model is limited only by your creativity. For example, a model may...