🤝 Open to Collab

Logan Hallee PRO

lhallee

Synthyra

·

https://synthyra.com/

AI & ML interests

I'm interested in using protein language models to design and annotate amino acid sequences.

Recent Activity

updated a dataset 1 day ago

Synthyra/SwissProt-Latent-Separation

published a dataset 1 day ago

Synthyra/SwissProt-Latent-Separation

updated a model 2 days ago

Synthyra/ESMFold2-Experimental-Fast-Cutoff2025

View all activity

Organizations

New activity in Synthyra/ESM2-150M 6 months ago

Lower results?

#1 opened 6 months ago by

New activity in Synthyra/Profluent-E1-150M 7 months ago

The checkpoint you are trying to load has model type `E1` but Transformers does not recognize this architecture

#1 opened 7 months ago by

New activity in Synthyra/ESMplusplus_small 9 months ago

Thanks for this!

#4 opened 9 months ago by

New activity in Synthyra/ESM2-8M 10 months ago

CLS pooling with ESM2

#1 opened 10 months ago by

nestorgonzalovich

New activity in Synthyra/ESM2-650M 10 months ago

Confusion about ESM-650M's Output Layer: Independent Decoder vs. Weight Tying

#1 opened 10 months ago by

New activity in Synthyra/ESMplusplus_large 10 months ago

Mismatch Between Logits Output Size and Vocab Size in ESMplusplus Model for MLM Task

#10 opened 10 months ago by

New activity in Synthyra/ESMplusplus_large 11 months ago

Have you or your group also done similar work for ESM3？

#9 opened 11 months ago by

New activity in Synthyra/ESMplusplus_large 12 months ago

The outputs of ESMC 600M and your model are not fully consistent

#8 opened 12 months ago by

New activity in GleghornLab/DSM_650 about 1 year ago

Unconditional Sequence Generation does not work

#2 opened about 1 year ago by

Cannot import DSM model

#1 opened about 1 year ago by

New activity in Synthyra/ESMplusplus_small about 1 year ago

Bug in attention map computation

#3 opened over 1 year ago by

New activity in lhallee/foldseek_dataset about 1 year ago

Request for info

#2 opened about 1 year ago by

New activity in boltz-community/boltz-1 about 1 year ago

🚩 Report: Ethical issue(s)

#4 opened over 1 year ago by

New activity in Synthyra/ESMplusplus_large about 1 year ago

Returning attention maps - an empty object returned

#7 opened about 1 year ago by

New activity in Synthyra/ESMplusplus_large over 1 year ago

Using ESM-C Original Weights or Re-Trained?

#6 opened over 1 year ago by

question for logits

#4 opened over 1 year ago by

New activity in Synthyra/ESMplusplus_small over 1 year ago

Always predicts <unk> issue

#2 opened over 1 year ago by

New activity in Synthyra/ESMplusplus_large over 1 year ago

Some instructions regarding fine-tuning & classification with ESM++ model

#3 opened over 1 year ago by

New activity in Synthyra/FastESM2_650 over 1 year ago

Which Layer to use for Representations?

#2 opened over 1 year ago by

New activity in Synthyra/ESMplusplus_small over 1 year ago

Why is the vocab size 64?

#1 opened over 1 year ago by