Fill-Mask
Transformers
Safetensors
English
esmc
biology
esm
protein
protein-language-model
protein-embeddings
masked-language-modeling
transfer-learning
variant-effect-prediction
protein-engineering
Instructions to use Rocketknight1/ESMC-600M-temp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Rocketknight1/ESMC-600M-temp with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="Rocketknight1/ESMC-600M-temp")# Load model directly from transformers import AutoModelForMaskedLM model = AutoModelForMaskedLM.from_pretrained("Rocketknight1/ESMC-600M-temp", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "EsmcForMaskedLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": null, | |
| "classifier_dropout": 0.1, | |
| "dtype": "float32", | |
| "eos_token_id": null, | |
| "expansion_ratio": 2.6666666666666665, | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 1152, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "mask_token_id": 32, | |
| "max_position_embeddings": 2048, | |
| "mlp_bias": false, | |
| "model_type": "esmc", | |
| "num_attention_heads": 18, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 18, | |
| "pad_token_id": 1, | |
| "rope_parameters": { | |
| "rope_theta": 10000.0, | |
| "rope_type": "default" | |
| }, | |
| "scale_residue": true, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.14.0.dev0", | |
| "vocab_size": 64 | |
| } | |