esm

esm copied to clipboard

esm v3.1.5 AttributeError when using local ESMC-300M model weight

5

Hi! I try to use esmc-300m to generate embedding. when i use ver. 3.1.5, it will give the AttributeError: property 'cls_token' of 'EsmSequenceTokenizer' object has no setter. However, when i...

Zuttergutao

How to Generate Embeddings of protein sequences using ESM C

27

Hi, I would like to know how to generate embeddings of protein sequences using ESM C? Is it similar to ESM-2. Is it possible to generate embeddings from the 3d...

anonimoustt

So, I was looking at the embeddings code provided previously : ``` from esm.models.esm3 import ESM3 from esm.sdk.api import ESMProtein, SamplingConfig from esm.utils.constants.models import ESM3_OPEN_SMALL client = ESM3.from_pretrained(ESM3_OPEN_SMALL, device="cpu") #...

grpinto

Can ESMC extract embeddings using the structure track?

2

Hello, I am trying to extract embeddings locally using the ESMC model and would like to know whether it is possible to use the structure track for this purpose. I...

RichenLee

AttributeError: 'ESMProteinError' object has no attribute 'hidden_states'

5

--------------------------------------------------------------------------- AttributeError Traceback (most recent call last) Cell In[58], [line 5](vscode-notebook-cell:?execution_count=58&line=5) [1](vscode-notebook-cell:?execution_count=58&line=1) import torch [3](vscode-notebook-cell:?execution_count=58&line=3) # we'll summarize the embeddings using their mean across the sequence dimension [4](vscode-notebook-cell:?execution_count=58&line=4) # which...

jinlong-abc

Disable return all hidden states to reduce gpu memory use

1

I found that using default parameters for inference resulted in abnormally high GPU memory usage. To fix this problem, I added a parameter `return_hidden_states = False` to control whether to...

heya5

Hi, I'm trying to run through the residue annotation pipeline. I noticed that in [encode_decode.py](https://github.com/evolutionaryscale/esm/blob/494e2e1d5c25e8d8bfae466ce8b50959d845d816/esm/utils/function/encode_decode.py#L75) we have: ```python ra_tokens = residue_annotations_tokenizer.tokenize( { "interpro_site_descriptions": descriptions, "interpro_site_starts": starts, "interpro_site_ends": ends, }, sequence=sequence,...

dandingsky

Hello everybody and thanks for the awsome work, i'm currently trying to fine-tune esm3 on a dataset of protein complexes and i would like to have clarification about chain_id and...

j3rk0

Hi, thank you for the great work and the updates! I directly ran the codes in **Forge Batch Executor Section**, and the exception would be thrown: ``("embed_sequence() got an unexpected...

asceking

ESMC AttributeError

2

>>> from esm.models.esmc import ESMC >>> client = ESMC.from_pretrained("esmc_300m").to("cpu") Traceback (most recent call last): File "", line 1, in File "/home/work/mindformers/esm_env/lib/python3.10/site-packages/esm/models/esmc.py", line 86, in from_pretrained model = load_local_model(model_name, device=device) File...

Mgctz