Feature Extraction
Transformers
English
esmc_sae
biology
esm
protein
sparse-autoencoder
interpretability
protein-embeddings
protein-language-model
unsupervised-learning
Instructions to use biohub/ESMC-600M-sae-layer27-k32-codebook131072 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use biohub/ESMC-600M-sae-layer27-k32-codebook131072 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="biohub/ESMC-600M-sae-layer27-k32-codebook131072")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("biohub/ESMC-600M-sae-layer27-k32-codebook131072", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from biohub/ESMC-600M-sae-layer27-k32-codebook131072: direct link, hf CLI and curl.
- Browser
- Download file 209 Bytes
-
https://huggingface.co/biohub/ESMC-600M-sae-layer27-k32-codebook131072/resolve/main/config.json
- Command line
-
hf download hf://biohub/ESMC-600M-sae-layer27-k32-codebook131072/config.json
-
curl -L -o config.json https://huggingface.co/biohub/ESMC-600M-sae-layer27-k32-codebook131072/resolve/main/config.json
209 Bytes
| { | |
| "available_layers": [ | |
| 27 | |
| ], | |
| "codebook_dim": 131072, | |
| "d_model": 1152, | |
| "k": 32, | |
| "model_type": "esmc_sae", | |
| "transformers_version": "4.57.6", | |
| "use_residual_update_instead_of_states": false | |
| } | |