| { | |
| "attention_probs_dropout_prob": 0.1, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "layer_norm_eps": 1e-07, | |
| "legacy": true, | |
| "max_position_embeddings": 512, | |
| "max_relative_positions": -1, | |
| "model_type": "deberta-v2", | |
| "neuron": { | |
| "auto_cast": "matmul", | |
| "auto_cast_type": "bf16", | |
| "compiler_type": "neuronx-cc", | |
| "compiler_version": "2.21.18209.0+043b1bf7", | |
| "disable_fallback": false, | |
| "disable_fast_relayout": false, | |
| "dynamic_batch_size": false, | |
| "float_dtype": "fp32", | |
| "inline_weights_to_neff": true, | |
| "instance_type": "inf2", | |
| "int_dtype": "int64", | |
| "model_type": "deberta-v2", | |
| "optlevel": "2", | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "static_batch_size": 1, | |
| "static_sequence_length": 128, | |
| "task": "fill-mask", | |
| "tensor_parallel_size": 1 | |
| }, | |
| "norm_rel_ebd": "layer_norm", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "pad_token_id": 0, | |
| "pooler_dropout": 0, | |
| "pooler_hidden_act": "gelu", | |
| "pooler_hidden_size": 1024, | |
| "pos_att_type": [ | |
| "p2c", | |
| "c2p" | |
| ], | |
| "position_biased_input": false, | |
| "position_buckets": 256, | |
| "relative_attention": true, | |
| "share_att_key": true, | |
| "torch_dtype": "float32", | |
| "torchscript": true, | |
| "transformers_version": "4.55.4", | |
| "type_vocab_size": 0, | |
| "vocab_size": 128100 | |
| } | |