Feature Extraction
Transformers
English
esmc_sae
biology
esm
protein
sparse-autoencoder
interpretability
protein-embeddings
protein-language-model
unsupervised-learning
Instructions to use biohub/ESMC-300M-sae-k64-codebook16384 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use biohub/ESMC-300M-sae-k64-codebook16384 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="biohub/ESMC-300M-sae-k64-codebook16384")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("biohub/ESMC-300M-sae-k64-codebook16384", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Declare use_residual_update_instead_of_states=false
Browse files- config.json +2 -1
config.json
CHANGED
|
@@ -36,5 +36,6 @@
|
|
| 36 |
"d_model": 960,
|
| 37 |
"k": 64,
|
| 38 |
"model_type": "esmc_sae",
|
| 39 |
-
"transformers_version": "4.57.6"
|
|
|
|
| 40 |
}
|
|
|
|
| 36 |
"d_model": 960,
|
| 37 |
"k": 64,
|
| 38 |
"model_type": "esmc_sae",
|
| 39 |
+
"transformers_version": "4.57.6",
|
| 40 |
+
"use_residual_update_instead_of_states": false
|
| 41 |
}
|