{
  "_attn_implementation_autoset": true,
  "_name_or_path": "hf-internal-testing/tiny-random-EsmForMaskedLM",
  "architectures": [
    "EsmForMaskedLM"
  ],
  "attention_probs_dropout_prob": 0.1,
  "classifier_dropout": null,
  "emb_layer_norm_before": null,
  "esmfold_config": null,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 32,
  "initializer_range": 0.02,
  "intermediate_size": 37,
  "is_folding_model": false,
  "layer_norm_eps": 1e-12,
  "mask_token_id": null,
  "max_position_embeddings": 512,
  "model_type": "esm",
  "num_attention_heads": 4,
  "num_hidden_layers": 5,
  "pad_token_id": 1,
  "position_embedding_type": "absolute",
  "token_dropout": false,
  "transformers_version": "4.48.2",
  "type_vocab_size": 16,
  "use_cache": true,
  "vocab_list": null,
  "vocab_size": 33
}