| { | |
| "architecture": { | |
| "embedding_size": 768, | |
| "hidden_size": 768, | |
| "intermediate_size": 3072, | |
| "num_hidden_layers": 12, | |
| "num_attention_heads": 12, | |
| "attention_head_size": 64, | |
| "attention_probs_dropout_prob": 0.1, | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_act": "gelu", | |
| "initializer_range": 0.02, | |
| "layer_norm_eps": 1e-07, | |
| "max_position_embeddings": 0, | |
| "max_relative_positions": 512, | |
| "position_buckets": 0, | |
| "norm_rel_ebd": "none", | |
| "pos_att_type": "c2p", | |
| "position_biased_input": false, | |
| "relative_attention": true, | |
| "share_att_key": false, | |
| "type_vocab_size": 0, | |
| "vocab_size": 211 | |
| }, | |
| "source_checkpoint_sha256": "5ec58973aa95dc71495081857abadfc5e736fe019ebd55866a8c269a5f3e2914", | |
| "representation": "final_layer_cls", | |
| "model_variant": "A1", | |
| "training_stage": "step2" | |
| } | |