| { | |
| "_name_or_path": "/gladstone/theodoris/lab/pretrained_models/encoder/240402_194213_geneformer_94M_L12_emb512_SL4096_E3_B4_LR0.0005_LScosine_WU5000_Oadamw_DS8/models", | |
| "architectures": [ | |
| "BertForMaskedLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.02, | |
| "classifier_dropout": null, | |
| "hidden_act": "relu", | |
| "hidden_dropout_prob": 0.02, | |
| "hidden_size": 512, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1024, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 4096, | |
| "model_type": "bert", | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 0, | |
| "position_embedding_type": "absolute", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.37.1", | |
| "type_vocab_size": 2, | |
| "use_cache": true, | |
| "vocab_size": 20275 | |
| } | |