optimum-neuron-cache
/
neuronxcc-2.12.68.0+4480452af
/0_REGISTRY
/0.0.21.dev0
/inference
/bert
/hf-internal-testing
/tiny-random-BertModel
/0d32d29d2910324c1904.json
{"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, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 16}, "num_attention_heads": 4, "num_hidden_layers": 5, "position_embedding_type": "absolute", "task": "text-classification", "type_vocab_size": 16, "use_cache": true, "vocab_size": 1124} |