{ "transformers_version": "5.15.0", "architectures": [ "Gemma4ForCausalLM" ], "output_hidden_states": false, "return_dict": true, "dtype": "bfloat16", "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "vocab_size": 262137, "hidden_size": 5376, "intermediate_size": 21504, "num_hidden_layers": 60, "num_attention_heads": 32, "num_key_value_heads": 16, "head_dim": 256, "hidden_activation": "gelu_pytorch_tanh", "max_position_embeddings": 262144, "initializer_range": 0.02, "rms_norm_eps": 1e-06, "use_cache": true, "pad_token_id": 0, "eos_token_id": 1, "bos_token_id": 2, "tie_word_embeddings": true, "rope_parameters": { "full_attention": { "partial_rotary_factor": 0.25, "rope_theta": 1000000.0, "rope_type": "proportional" }, "sliding_attention": { "rope_theta": 10000.0, "rope_type": "default" } }, "attention_bias": false, "attention_dropout": 0.0, "sliding_window": 1024, "layer_types": [ "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention" ], "final_logit_softcapping": 30.0, "use_bidirectional_attention": "vision", "vocab_size_per_layer_input": 262137, "hidden_size_per_layer_input": 0, "attention_k_eq_v": true, "num_kv_shared_layers": 0, "enable_moe_block": false, "use_double_wide_mlp": false, "moe_intermediate_size": null, "model_type": "gemma4_text", "output_attentions": false, "per_layer_config": { "05": { "head_dim": 512, "num_key_value_heads": 4 }, "11": { "head_dim": 512, "num_key_value_heads": 4 }, "17": { "head_dim": 512, "num_key_value_heads": 4 }, "23": { "head_dim": 512, "num_key_value_heads": 4 }, "29": { "head_dim": 512, "num_key_value_heads": 4 }, "35": { "head_dim": 512, "num_key_value_heads": 4 }, "41": { "head_dim": 512, "num_key_value_heads": 4 }, "47": { "head_dim": 512, "num_key_value_heads": 4 }, "53": { "head_dim": 512, "num_key_value_heads": 4 }, "59": { "head_dim": 512, "num_key_value_heads": 4 } } }