Jeonghwan Kim
Jeonghwan Kim
https://github.com/google-research/albert/blob/932b41f0319fbef7efd069d5ff545e3358574e19/create_pretraining_data.py#L306 In line 306, there is appears to be a probable issue. For `random.randint(start, end)`, the method is end-inclusive. So, when `len(current_chunk) == 2`, line 309 would stop at a...
### Describe the issue Issue: Hi, I've been experiencing issue with the pre-training of LLaVA-1.5 model and my set up is as follows: - 4x A100 80G - CUDA 11.7...
### Anthology ID 2024.findings-naacl.159 ### Type of Change Revision ### PDF of the Revision or Erratum [why_so_gullible_ack_added_naacl2024_findings.pdf](https://github.com/user-attachments/files/17139861/why_so_gullible_ack_added_naacl2024_findings.pdf) ### Brief Description of Changes This revision adds the Acknowledgements section to the...