{
  "architectures": [
    "BertModel"
  ],
  "attention_probs_dropout_prob": 0.1,
  "classifier_dropout": null,
  "dtype": "float32",
  "export_model_type": "transformer",
  "gradient_checkpointing": false,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "id2label": {
    "0": "LABEL_0"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "LABEL_0": 0
  },
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 512,
  "model_type": "bert",
  "neuron": {
    "auto_cast": "matmul",
    "auto_cast_type": "bf16",
    "compiler_type": "neuronx-cc",
    "compiler_version": "2.21.33363.0+82129205",
    "disable_fallback": false,
    "disable_fast_relayout": false,
    "dynamic_batch_size": false,
    "float_dtype": "fp32",
    "inline_weights_to_neff": true,
    "instance_type": "trn1",
    "int_dtype": "int64",
    "model_type": "transformer",
    "optlevel": "2",
    "output_attentions": false,
    "output_hidden_states": false,
    "static_batch_size": 2,
    "static_sequence_length": 512,
    "task": "feature-extraction",
    "tensor_parallel_size": 1
  },
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 0,
  "position_embedding_type": "absolute",
  "torchscript": true,
  "transformers_version": "4.57.1",
  "type_vocab_size": 2,
  "use_cache": true,
  "vocab_size": 30522
}