Hello everyone, I successfully fine-tuned a model for text classification. Now I would like to run my trained model to get labels for a large test dataset (around 20,000 texts). So I had the idea to instantiate a Trainer with my model and use the trainer.predict() method on my data. This works fin…

Using Trainer at inference time

ndvb May 4, 2023, 7:35pm 10

It would be nice if we could instantiate Trainer with no output_dir for inference… Or if the predict() function could be run without Trainer

3 Likes

Topic		Replies	Views
How do I use a fine-tuned Trainer model for inference correctly? 🤗Transformers	0	983	June 9, 2023
How to do inference with fined-tuned huggingface models? 🤗Transformers	3	820	February 4, 2024
Looking for tool class to do predictions 🤗Transformers	3	551	October 9, 2020
Batch size for trainer.predict() 🤗Transformers	4	6911	November 26, 2022
How to make single-input inference faster? Create my own pipeline? 🤗Transformers	9	3949	August 26, 2021