-
I tried to run the provided fine_tuning notebook. However, when I try to fine-tune I get the following error:
Loading weights from pretrained model: bert-base-uncased
Some weights of BertForSequen…
-
{
"id": "000000245946",
"image": "000000245946.jpg",
"conversations": [
{
"from": "human",
"value": "\nWhat considerations…
-
-
Hardware - GPU (T4)
Hardware - CPU
Operating System - ubuntu 20.04 running on AWS EC2 g4dn.2xlarge instance
I am currently trying to convert a model (several of different types but for now not ev…
-
Hello,
Thank you for your hard work on the repo.
I want to train the newly added TrOCR for my use case on my dataset.
I am a little confused on how to proceed.
https://huggingface.co/transfo…
-
It would be very useful to compare real training performance on amd and nvidia cards.
For Nvidia cards we have a lot of graphs and tests, for example:
https://github.com/u39kun/deep-learning-benchma…
-
Hey @nreimers,
I have few questions regarding the fine-tuning of sbert model. The questions are as follows:
1) this may be naive question but just wondering, when fine-tuning the sbert model on cu…
-
If a user trains a GNN model without fine-tuning the BERT model, we should provide an option of saving the BERT embeddings on files for next trainings. Computing BERT embeddings are usually the major …
-
Right now, the model (correct me if I'm wrong) appears to be locked down to sequences of max 512, based on running & playing with the code (and this makes sense in the context of the paper).
Are th…
-
### System Info
Pytorch DP
### Who can help?
@pacman100 @younesbelkada @sayakpaul
### Information
- [ ] The official example scripts
- [X] My own modified scripts
### Tasks
- [ ] An officially …