config.json

{
  "architectures": [
    "ProtSTModel"
  ],
  "auto_map": {
    "AutoModel": "modeling_protst.ProtSTModel",
    "AutoConfig": "configuration_protst.ProtSTConfig"
  },
  "model_type": "protst",
  "protein_config": {
    "_name_or_path": "/tmp/facebook/esm1b_t33_650M_UR50S",
    "architectures": [
      "EsmForMaskedLM"
    ],
    "attention_probs_dropout_prob": 0.0,
    "classifier_dropout": null,
    "emb_layer_norm_before": true,
    "esmfold_config": null,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.0,
    "hidden_size": 1280,
    "initializer_range": 0.02,
    "intermediate_size": 5120,
    "is_folding_model": false,
    "layer_norm_eps": 1e-05,
    "mask_token_id": 32,
    "max_position_embeddings": 1026,
    "model_type": "esm",
    "num_attention_heads": 20,
    "num_hidden_layers": 33,
    "cls_token_id": 0,
    "pad_token_id": 1,
    "eos_token_id": 2,
    "position_embedding_type": "absolute",
    "token_dropout": true,
    "torch_dtype": "float32",
    "use_cache": true,
    "vocab_list": null,
    "vocab_size": 33
  },
  "text_config": {
    "architectures": [
      "BertForMaskedLM"
    ],
    "model_type": "bert",
    "attention_probs_dropout_prob": 0.1,
    "hidden_act": "gelu",
    "pad_token_id": 0,
    "cls_token_id": 2,
    "sep_token_id": 3,
    "hidden_dropout_prob": 0.1,
    "hidden_size": 768,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "max_position_embeddings": 512,
    "num_attention_heads": 12,
    "num_hidden_layers": 12,
    "type_vocab_size": 2,
    "vocab_size": 30522
  },
  "torch_dtype": "float32",
  "transformers_version": "4.37.0.dev0"
}