{
  "transformers_version": "5.6.2",
  "architectures": [
    "EsmForMaskedLM"
  ],
  "output_hidden_states": false,
  "return_dict": true,
  "dtype": "bfloat16",
  "chunk_size_feed_forward": 0,
  "is_encoder_decoder": false,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1"
  },
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1
  },
  "problem_type": null,
  "vocab_size": 33,
  "mask_token_id": 32,
  "pad_token_id": 1,
  "hidden_size": 2560,
  "num_hidden_layers": 36,
  "num_attention_heads": 40,
  "intermediate_size": 10240,
  "hidden_dropout_prob": 0.0,
  "attention_probs_dropout_prob": 0.0,
  "max_position_embeddings": 1026,
  "rope_theta": 10000.0,
  "initializer_range": 0.02,
  "layer_norm_eps": 1e-05,
  "position_embedding_type": "rotary",
  "use_cache": true,
  "emb_layer_norm_before": false,
  "token_dropout": true,
  "is_folding_model": false,
  "esmfold_config": null,
  "vocab_list": null,
  "is_decoder": false,
  "add_cross_attention": false,
  "tie_word_embeddings": true,
  "bos_token_id": null,
  "eos_token_id": 2,
  "classifier_dropout": null,
  "hidden_act": "gelu",
  "model_type": "esm",
  "output_attentions": false
}