{ "_name_or_path": "/content/alephbertgimmel/alephbertgimmel-base/ckpt_69200--Max128Seq", "architectures": [ "BertForMultiLabelTokenClassification" ], "attention_probs_dropout_prob": 0.1, "classifier_dropout": null, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "id2label": { "0": "\"#", "1": "#\u05d4", "2": "#\u05d4\u05d5", "3": "#\u05d4\u05dd", "4": "#\u05d4\u05df", "5": "#\u05d5", "6": "#\u05d9", "7": "#\u05d9\u05d4", "8": "#\u05d9\u05d5", "9": "#\u05da", "10": "#\u05db\u05dd", "11": "#\u05dd", "12": "#\u05df", "13": "#\u05e0\u05d5", "14": "#\u05e0\u05d9", "15": "'#", "16": "\u05d1#", "17": "\u05d4#", "18": "\u05d5#", "19": "\u05db#", "20": "\u05db\u05e9#", "21": "\u05dc#", "22": "\u05de#", "23": "\u05de\u05e9#", "24": "\u05e9#" }, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "\"#": 0, "#\u05d4": 1, "#\u05d4\u05d5": 2, "#\u05d4\u05dd": 3, "#\u05d4\u05df": 4, "#\u05d5": 5, "#\u05d9": 6, "#\u05d9\u05d4": 7, "#\u05d9\u05d5": 8, "#\u05da": 9, "#\u05db\u05dd": 10, "#\u05dd": 11, "#\u05df": 12, "#\u05e0\u05d5": 13, "#\u05e0\u05d9": 14, "'#": 15, "\u05d1#": 16, "\u05d4#": 17, "\u05d5#": 18, "\u05db#": 19, "\u05db\u05e9#": 20, "\u05dc#": 21, "\u05de#": 22, "\u05de\u05e9#": 23, "\u05e9#": 24 }, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "bert", "num_attention_heads": 12, "num_hidden_layers": 12, "pad_token_id": 3, "position_embedding_type": "absolute", "torch_dtype": "float32", "transformers_version": "4.42.4", "type_vocab_size": 2, "use_cache": true, "vocab_size": 128000 }