| { | |
| "_name_or_path": "/users/engs2263/compact-distilbert/models/bio-miniALBERT-128/final/model", | |
| "architectures": [ | |
| "MiniAlbertForMaskedLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": 2, | |
| "classifier_dropout": null, | |
| "classifier_dropout_prob": 0.1, | |
| "down_scale_factor": 1, | |
| "embedding_size": 128, | |
| "eos_token_id": 3, | |
| "gap_size": 0, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "inner_group_num": 1, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 512, | |
| "model_type": "bert", | |
| "net_structure_type": 0, | |
| "num_attention_heads": 12, | |
| "num_hidden_groups": 1, | |
| "num_hidden_layers": 6, | |
| "num_memory_blocks": 0, | |
| "pad_token_id": 0, | |
| "position_embedding_type": "absolute", | |
| "reduction_factor": 16, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.27.0.dev0", | |
| "type_vocab_size": 2, | |
| "use_adapter": true, | |
| "use_cache": true, | |
| "vocab_size": 28996 | |
| } | |