-
Provide a slider that lets users choose between 3 presets. These would populate the advanced params:
- normal --> default
- highly similar sequences (specificity?) --> Evalue cutoff at e-3; BLOSUM80,…
-
Hi Nathan, we are working with museum samples, so lots of very short fragments. I've noticed that exonerate only uses sequences that are 54bp or longer from our data. We are using exonorate via [MGE](…
-
Dear author,
I have recently studied your work and benefited a lot from it. I would like to ask you for some implementation details.
First, in the implementation of ConvLSTM, do you initialize t…
-
# Expected Behavior
Embedding text with a long-context model like BGE-M3 [1] should be able to output token embeddings for more than 512 tokens (this is of interest for 'late interaction' retrieval…
-
Token indices sequence length is longer than the specified maximum sequence length for this model (84 > 77). Running this sequence through the model will result in indexing errors
The following part …
-
MinGRU (without the LM layers) is considerably slower than standard nn.GRU. My test parameters were: input_size = 10, hidden_size = 100, seq_len = 1000, batch_size = 64.
From my profiler, tested i…
-
**question description**
I have a question about the length limitation of protein sequences, for different sizes of the ESM2 model (8M,35M,150,,,,), what are the maximum lengths of proteins for …
-
## Expected Behavior
`mmseqs download` would be expected to download an up-to-date version of the target 'nr' and 'nt' databases.
## Current Behavior
The download FASTA targets for the 'nr' and '…
-
Problem: When a token is modified, it is no longer part of a sequence but has to be added to it again.
It should remain in the sequence as before.
summary (?)
you have to be the owner
…
-
First of all, thank you for the outstanding work on this repository. I have been using your implementation to fine-tune a model for recognizing extremely long text in Chinese. My input image dimension…