{
  "_attn_implementation_autoset": true,
  "activation": "gelu",
  "architectures": [
    "DistilBertForMaskedLM"
  ],
  "attention_dropout": 0.1,
  "dim": 768,
  "dropout": 0.1,
  "hidden_dim": 3072,
  "initializer_range": 0.02,
  "max_position_embeddings": 512,
  "model_type": "distilbert",
  "n_heads": 12,
  "n_layers": 6,
  "neuron": {
    "auto_cast": null,
    "auto_cast_type": null,
    "compiler_type": "neuronx-cc",
    "compiler_version": "2.16.372.0+4a9b2326",
    "dynamic_batch_size": false,
    "inline_weights_to_neff": true,
    "input_names": [
      "input_ids",
      "attention_mask"
    ],
    "model_type": "distilbert",
    "optlevel": "2",
    "output_attentions": false,
    "output_hidden_states": false,
    "output_names": [
      "logits"
    ],
    "static_batch_size": 1,
    "static_sequence_length": 128,
    "task": "fill-mask",
    "tensor_parallel_size": 1
  },
  "pad_token_id": 0,
  "qa_dropout": 0.1,
  "seq_classif_dropout": 0.2,
  "sinusoidal_pos_embds": false,
  "tie_weights_": true,
  "torch_dtype": "float32",
  "torchscript": true,
  "transformers_version": "4.51.3",
  "vocab_size": 30522
}