{
  "_name_or_path": "hf-internal-testing/tiny-random-BertModel",
  "architectures": [
    "BertModel"
  ],
  "attention_probs_dropout_prob": 0.1,
  "classifier_dropout": null,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 32,
  "initializer_range": 0.02,
  "intermediate_size": 37,
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 512,
  "model_type": "bert",
  "neuron": {
    "auto_cast": "matmul",
    "auto_cast_type": "fp16",
    "compiler_type": "neuronx-cc",
    "compiler_version": "2.12.68.0+4480452af",
    "dynamic_batch_size": false,
    "inline_weights_to_neff": false,
    "input_names": [
      "input_ids",
      "attention_mask",
      "token_type_ids"
    ],
    "model_type": "bert",
    "optlevel": "2",
    "output_attentions": false,
    "output_hidden_states": false,
    "output_names": [
      "last_hidden_state",
      "pooler_output"
    ],
    "static_batch_size": 1,
    "static_sequence_length": 16
  },
  "num_attention_heads": 4,
  "num_hidden_layers": 5,
  "pad_token_id": 0,
  "position_embedding_type": "absolute",
  "task": "feature-extraction",
  "torchscript": true,
  "transformers_version": "4.36.2",
  "type_vocab_size": 16,
  "use_cache": true,
  "vocab_size": 1124
}