esm

esm copied to clipboard

Get the multiple layer attention map from ESMC

1

Thanks for your wonderful work. I'm wondering is it possible to get the multiple layer attention maps from ESMC-6B via ESM3ForgeInferenceClient?

Luchixiang

Hi, Thank you for open-sourcing ESM3—it’s an excellent resource! I’m currently working on training a VQ-VAE model inspired by the structure tokenizer in ESM3 and have some questions about the...

Buddha7771

Repeated sequence generation of ESM3 with condition

1

I am trying to use ESM3 for sequence design by specifying the coordinates and amino acid composition of key motifs. However, I found that using the default temperature of 0.7...

wwzll123

new pip install; ESM3 bfloat16 / float32 compatibility error

1

Hi all; thanks for all the updates! Recently I tried to do a fresh install from `pip install esm`, but get an type compability error from a forward pass. Model...

mzio

TypeError: ESM3SageMakerClient._post() got an unexpected keyword argument 'return_bytes'

2

I am using Cloudformation to deploy ESMC-300M. Then, I am using the code snippet as shared in the Readme of this repo to invoke the model endpoint but I am...

kunalaperiambio

what is the per residue representation in ESM-C?

1

Hello, In the old ESM2, we use this code to get per residue embeddings at 33-layer: ```python # Load ESM-2 model model, alphabet = esm.pretrained.esm2_t33_650M_UR50D() batch_converter = alphabet.get_batch_converter() model.eval() #...

peiyaoli

CUDA out of memory

1

I'm trying to use ESM3 to encode protein complexs to tensors, but facing "CUDA out of memory error". Is there any solution for "CUDA out of memory" error when processing...

darkcorvushhh

ESM-3 open is now available on AWS Bedrock through the Bedrock Marketplace deployments using the invokeModel API. This is a similar interface to the invokeEndpoint interface from SageMaker but it...

lhnealreilly

Are the different esm3 model variants not open source? Does that mean we cannot download the model weight files, cannot perform model inference locally, and cannot do retraining or fine-tuning?

meiyiyeshi

An error occurred when running Quickstart for ESM3-open. replace() argument 2 must be str, not None

6

When I ran the "Quickstart for ESM3-open" file(open.py), the following error occurred(slurm-1031673.txt). from huggingface_hub import login from esm.models.esm3 import ESM3 from esm.sdk.api import ESM3InferenceClient, ESMProtein, GenerationConfig # Will instruct you...

pdxooo