language:
- en
tags:
- biology
- esm
- protein
extra_gated_heading: Agree to license and to share information
extra_gated_description: >-
The information you provide will be collected, stored, processed and shared in
accordance with the [EvolutionaryScale Privacy
Policy](https://www.evolutionaryscale.ai/legal/privacy)
extra_gated_prompt: >-
[EvolutionaryScale Community License
Agreement](https://www.evolutionaryscale.ai/legal/community-license-agreement)
**The Big Picture:**
1. The EvolutionaryScale AI Model is **only** available under this Community
License Agreement for **non-commercial use** by **individuals** or
**non-commercial organizations**.
2. You **may not** use the EvolutionaryScale AI Model or any derivative works
of the EvolutionaryScale AI Model or its outputs:
a. in connection with **any commercial activities**, for example
b. to develop **any product or service** such as hosting the AI Model behind an API; or
c. in connection to **drug development**; or
d. without attribution to EvolutionaryScale and this Community License Agreement; or
e. to **train** any other **large language model**, any technology for protein representation learning or protein generation or any other AI-powered third party model **similar to EvolutionaryScale’s AI Model**, even for non-commercial usage.
3. You **can publish, share and adapt** the EvolutionaryScale AI Model and its
outputs for **non-commercial purposes** in accordance with the Community
License Agreement
extra_gated_fields:
Name: text
Country: country
Role: text
Affiliation (Lab/group/division and Institution): text
Please describe your intended use of ESM3: text
Is your background primarily computational or experimental:
type: select
options:
- Computational
- Experimental
- Mixed
How did you learn about ESM3?:
type: select
options:
- Social media post
- News article
- Paper pre-print
- Word of mouth
- Other
I accept the CLA: checkbox
I agree to use this dataset for non-commercial use ONLY: checkbox
Model Card for esm3-sm-open-v1
esm3-sm-open-v1 is trained on 2.78 billion natural proteins. With synthetic data augmentation, this led to 3.15 billion protein sequences, 236 million protein structures, and 539 million proteins with function annotations, totaling 771 billion tokens.
esm3-sm-open-v1 is a generative model capable of designing proteins conditioned on partial prompts of sequence, structure and function.
Safety is an important part of our model - data related to viruses has been removed from the training dataset, as well as some proteins belonging to organisms on the USDA Select Agents and Toxins list. The function decoder has been filtered for potentially harmful keywords.
Usage
Using ESM3 requires esm
pip install esm
Please refer to the readme and notebooks in the esm repository for details on how to use the model.
License
This repository is under a custom non-commercial license.