Instructions to use multimolecule/esmc-600m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MultiMolecule
How to use multimolecule/esmc-600m with MultiMolecule:
pip install multimolecule
from multimolecule import AutoModel, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("multimolecule/esmc-600m") model = AutoModel.from_pretrained("multimolecule/esmc-600m") inputs = tokenizer("Paris is the A of France.", return_tensors="pt") outputs = model(**inputs) embeddings = outputs.last_hidden_stateimport multimolecule from transformers import pipeline predictor = pipeline("fill-mask", model="multimolecule/esmc-600m") output = predictor("Paris is the <mask> of France.") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from multimolecule/esmc-600m: direct link, hf CLI and curl.
- Browser
- Download file 2.3 GB
-
https://huggingface.co/multimolecule/esmc-600m/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://multimolecule/esmc-600m/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/multimolecule/esmc-600m/resolve/main/pytorch_model.bin
2.3 GB
- Xet hash:
- 448cd624a8b26807540d46f68c9e23b56867358de6b311f2a896c81e6a0ed123
- Size of remote file:
- 2.3 GB
- SHA256:
- 6a589068e66736afd4cab97d5062edb020cbc1d68705c38efdbce5f1e8f038c3
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.