I am fine-tuning several binary classification BERT models, all using bert-base-uncased. I understand that I can save my trained model and reload it later. I noticed that in the stored folder, the largest file is pytorch_model.bin (478MB), which appeared in every model I saved. If this is the pre-trained model (before finetuning), can I save it only once and later using it when loading different models?
Related topics
Topic | Replies | Views | Activity | |
---|---|---|---|---|
How to load model with .pth and avoid ponderous pytorch_model.bin | 0 | 1934 | September 8, 2023 | |
Size of saved model: Is there a way to make it smaller for deploy? | 1 | 604 | July 27, 2023 | |
Any model's size is huge when saved as opposed to downloading from hub pretrained | 3 | 380 | February 17, 2024 | |
Predicting with model and trying to save at the same time gives different prediction results and doesnt save | 0 | 312 | April 8, 2023 | |
How can I load specific checkpoint of trained model | 0 | 614 | April 28, 2022 |