Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -28,7 +28,7 @@ The ESMC 6B model has 6 billion parameters, with 80 layers and 2.37e23 training
|
|
| 28 |
|
| 29 |
The [ESMFold2](https://huggingface.co/biohub/ESMFold2) structure prediction models are trained on top of a frozen ESMC 6B language model. ESMFold2 is a state-of-the-art model for protein structure prediction and design that defines a new frontier for speed and accuracy.
|
| 30 |
|
| 31 |
-
The [ESMC sparse autoencoder](https://huggingface.co/
|
| 32 |
|
| 33 |
To run this model with the Biohub Platform API, visit the [Biohub Platform](https://biohub.ai/).
|
| 34 |
|
|
@@ -39,7 +39,7 @@ Read more about ESMC in our paper [here](https://biohub.ai/papers/esm_protein.pd
|
|
| 39 |
Install `esm` from GitHub (a PyPI release is coming soon):
|
| 40 |
|
| 41 |
```
|
| 42 |
-
pip install esm@git+https://github.com/Biohub/esm.git@
|
| 43 |
```
|
| 44 |
|
| 45 |
```py
|
|
@@ -113,9 +113,9 @@ ESMC was trained at multiple scales:
|
|
| 113 |
|
| 114 |
| Model Variant | Description | URL |
|
| 115 |
| :---- | :---- | :---- |
|
| 116 |
-
| ESMC 300M | Smallest variant, publicly released. | [https://huggingface.co/
|
| 117 |
-
| ESMC 600M | Medium variant, publicly released. | [https://huggingface.co/
|
| 118 |
-
| ESMC 6B | Large variant, publicly released. | [https://huggingface.co/
|
| 119 |
|
| 120 |
### System Requirements
|
| 121 |
|
|
|
|
| 28 |
|
| 29 |
The [ESMFold2](https://huggingface.co/biohub/ESMFold2) structure prediction models are trained on top of a frozen ESMC 6B language model. ESMFold2 is a state-of-the-art model for protein structure prediction and design that defines a new frontier for speed and accuracy.
|
| 30 |
|
| 31 |
+
The [ESMC sparse autoencoder](https://huggingface.co/biohub/ESMC-6B-sae-layer60-k64-codebook16384), `ESMC-6B-sae-layer60-k64-codebook16384`, is built on the ESMC 6B model and provides human-interpretable, agent-generated feature descriptions. See the [ESMC SAE overview card](https://huggingface.co/biohub/ESMC-SAE-Overview) for the full set of ESMC SAE variants.
|
| 32 |
|
| 33 |
To run this model with the Biohub Platform API, visit the [Biohub Platform](https://biohub.ai/).
|
| 34 |
|
|
|
|
| 39 |
Install `esm` from GitHub (a PyPI release is coming soon):
|
| 40 |
|
| 41 |
```
|
| 42 |
+
pip install esm@git+https://github.com/Biohub/esm.git@main
|
| 43 |
```
|
| 44 |
|
| 45 |
```py
|
|
|
|
| 113 |
|
| 114 |
| Model Variant | Description | URL |
|
| 115 |
| :---- | :---- | :---- |
|
| 116 |
+
| ESMC 300M | Smallest variant, publicly released. | [https://huggingface.co/biohub/ESMC-300M](https://huggingface.co/biohub/ESMC-300M) |
|
| 117 |
+
| ESMC 600M | Medium variant, publicly released. | [https://huggingface.co/biohub/ESMC-600M](https://huggingface.co/biohub/ESMC-600M) |
|
| 118 |
+
| ESMC 6B | Large variant, publicly released. | [https://huggingface.co/biohub/ESMC-6B](https://huggingface.co/biohub/ESMC-6B) |
|
| 119 |
|
| 120 |
### System Requirements
|
| 121 |
|