{ "architectures": [ "GemmaForSequenceClassification" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 2, "dtype": "float32", "eos_token_id": 1, "head_dim": 256, "hidden_act": "gelu", "hidden_activation": null, "hidden_size": 2048, "id2label": { "0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2" }, "initializer_range": 0.02, "intermediate_size": 16384, "label2id": { "LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2 }, "max_position_embeddings": 8192, "model_type": "gemma", "num_attention_heads": 8, "num_hidden_layers": 18, "num_key_value_heads": 1, "pad_token_id": 0, "problem_type": "single_label_classification", "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000.0, "transformers_version": "4.57.0", "use_cache": true, "vocab_size": 256000 }