optimum-neuron-cache
/
neuronxcc-2.14.227.0+2d4f85be
/0_REGISTRY
/0.0.25.dev0
/inference
/bert
/sentence-transformers
/all-MiniLM-L6-v2
/dd461006bf8288f7b624.json
{"architectures": ["BertModel"], "attention_probs_dropout_prob": 0.1, "classifier_dropout": null, "export_model_type": "transformer", "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 384, "initializer_range": 0.02, "intermediate_size": 1536, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "bert", "neuron": {"auto_cast": null, "auto_cast_type": null, "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "disable_fallback": false, "disable_fast_relayout": false, "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 16}, "num_attention_heads": 12, "num_hidden_layers": 6, "position_embedding_type": "absolute", "task": "feature-extraction", "type_vocab_size": 2, "use_cache": true, "vocab_size": 30522} |