| { | |
| "_attn_implementation_autoset": true, | |
| "architectures": [ | |
| "RobertaForMaskedLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": 0, | |
| "classifier_dropout": null, | |
| "eos_token_id": 2, | |
| "gradient_checkpointing": false, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 514, | |
| "model_type": "roberta", | |
| "neuron": { | |
| "auto_cast": null, | |
| "auto_cast_type": null, | |
| "compiler_type": "neuronx-cc", | |
| "compiler_version": "2.19.8089.0+8ab9f450", | |
| "disable_fallback": false, | |
| "disable_fast_relayout": false, | |
| "dynamic_batch_size": false, | |
| "inline_weights_to_neff": true, | |
| "input_names": [ | |
| "input_ids", | |
| "attention_mask" | |
| ], | |
| "model_type": "roberta", | |
| "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 | |
| }, | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 1, | |
| "position_embedding_type": "absolute", | |
| "torch_dtype": "float32", | |
| "torchscript": true, | |
| "transformers_version": "4.51.3", | |
| "type_vocab_size": 1, | |
| "use_cache": true, | |
| "vocab_size": 52000 | |
| } | |