{ "_name_or_path": "/gladstone/theodoris/lab/ctheodoris/gf-104m/models/241127_143148_geneformer_94M_L12_emb768_SL4096_E3_B18_LR0.0002_LScosine_WR0.007_Oadamw_DS13/models", "architectures": [ "BertForMaskedLM" ], "attention_probs_dropout_prob": 0.1, "classifier_dropout": null, "hidden_act": "relu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "initializer_range": 0.02, "intermediate_size": 3072, "layer_norm_eps": 1e-12, "max_position_embeddings": 4096, "model_type": "bert", "num_attention_heads": 12, "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 }