Behnaz Rivandi comments

Repositories
Issues
Comments

Results 3 comments of


                                            Behnaz Rivandi

Question about training stage3 in videochat2

Thanks a lot for your reply! I am working on a project where I intend to replace the decoder part of the model with the mT0-xl model (multilingual). However, I...

Json files of pretraining dataset

You can download these datasets from the following links: webvid-10M: [TempoFunk/webvid-10M](https://huggingface.co/datasets/TempoFunk/webvid-10M/tree/main) cc12m: [GitHub Repository](https://github.com/rom1504/img2dataset/blob/main/dataset_examples/cc12m.md)

Using Gradient Accumulation

Thank you for your response. I have another question regarding the extra_num_query_tokens. Specifically, I'm interested in understanding if you've tested the scenario where this parameter is set to 0. How...