{ | |
"_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": null, | |
"auto_cast_type": null, | |
"compiler_type": "neuron-cc", | |
"compiler_version": "1.20.3.0+ed6db4a2e", | |
"disable_fallback": false, | |
"disable_fast_relayout": false, | |
"dynamic_batch_size": false, | |
"input_names": [ | |
"input_ids", | |
"attention_mask", | |
"token_type_ids" | |
], | |
"output_names": [ | |
"logits" | |
], | |
"static_batch_size": 1, | |
"static_sequence_length": 32 | |
}, | |
"num_attention_heads": 4, | |
"num_hidden_layers": 5, | |
"pad_token_id": 0, | |
"position_embedding_type": "absolute", | |
"task": null, | |
"torch_dtype": "float32", | |
"transformers_version": "4.34.1", | |
"type_vocab_size": 16, | |
"use_cache": true, | |
"vocab_size": 1124 | |
} | |