Feature Extraction
Transformers
English
esmc_sae
biology
esm
protein
sparse-autoencoder
interpretability
protein-embeddings
protein-language-model
unsupervised-learning
Instructions to use biohub/ESMC-6B-sae-layer60-k512-codebook32768 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use biohub/ESMC-6B-sae-layer60-k512-codebook32768 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="biohub/ESMC-6B-sae-layer60-k512-codebook32768")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("biohub/ESMC-6B-sae-layer60-k512-codebook32768", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -58,7 +58,6 @@ pip install esm@git+https://github.com/Biohub/esm.git@c94ed8d
|
|
| 58 |
You can access an SAE model through Hugging Face using the code below:
|
| 59 |
|
| 60 |
```py
|
| 61 |
-
# pip install esm@git+https://github.com/Biohub/esm.git@c94ed8d
|
| 62 |
import torch
|
| 63 |
from transformers import AutoModel, AutoTokenizer
|
| 64 |
|
|
|
|
| 58 |
You can access an SAE model through Hugging Face using the code below:
|
| 59 |
|
| 60 |
```py
|
|
|
|
| 61 |
import torch
|
| 62 |
from transformers import AutoModel, AutoTokenizer
|
| 63 |
|