-
I know there is already an ambulance icon however it is represented by a cross which doesn't translate well in Asia and countries where Christianity is not the majority religion.
The more common symb…
-
I would like to inquire whether Caduceus supports variable-length inputs within a batch. From my understanding, the original MambaBlock does not support variable-length inputs, and it seems that Caduc…
-
I am getting an error when trying to do any sequence classification with models that have d_model = 256
Error:
Traceback (most recent call last):
File "/uufs/chpc.utah.edu/common/home/sundar-…
-
Hi there, thanks for creating the great model! I'm trying to use the caduceus architecture to fine-tune on my own task. I noticed that the results using pre-trained or random-initialized models are no…
-
I am trying to pre-train the models used in your genomic benchmark results and I was wondering if you could tell me how to modify these parameters to obatin the cacudeus-ph model and the caduceus w/o …
-
Hi, thank you for your awesome work!
When I tried to run run_pretrain_hyena.sh, I got an unexpected error during validation. It seems that there is something wrong with the fetcher, which sometimes…
-
Font (and image) vendors are free to use colorful emoji glyphs for characters that do not (yet) have the`Emoji` property set in [`emoji-data.txt`](http://www.unicode.org/Public/emoji/latest/emoji-data…
-
Hi,
When I tried to reproduce NT benchmark's results, I met an error that seemed to be related to the train.metric not set in configuration.
I used the script `run_nucleotide_transformer.sh` …
-
Hi,
Thanks for your great work and well-documented code.
I'm currently facing an issue related to the storage requirements for running the vep_embeddings.py script as part of the EQTL VEP analy…
-
I am trying to run the following script:
```python
from transformers import AutoModelForMaskedLM, AutoTokenizer
import torch
import matplotlib.pyplot as plt
import numpy as np
# Check if GPU i…