{ "model_type": "gemma_3_omni", "architectures": ["Gemma3OmniForConditionalGeneration"], "auto_map": { "AutoProcessor": "processing_gemma3_omni.Gemma3OmniProcessor", "AutoFeatureExtractor": "processing_gemma3_omni.Gemma3AudioFeatureExtractor", "AutoConfig": "modeling_gemma_3_omni.Gemma3Config", "AutoModel": "modeling_gemma_3_omni.Gemma3OmniForConditionalGeneration" }, "boi_token_index": 255999, "eoi_token_index": 256000, "boa_token_index": 256001, "eoa_token_index": 256002, "eos_token_id": [ 1, 106 ], "audio_token_index": 262143, "image_token_index": 262144, "initializer_range": 0.02, "mm_tokens_per_image": 256, "text_config": { "attention_bias": false, "attention_dropout": 0, "attn_logit_softcapping": null, "cache_implementation": "hybrid", "final_logit_softcapping": null, "head_dim": 256, "hidden_activation": "gelu_pytorch_tanh", "hidden_size": 2560, "initializer_range": 0.02, "intermediate_size": 10240, "max_position_embeddings": 131072, "model_type": "gemma3_text", "num_attention_heads": 8, "num_hidden_layers": 34, "num_key_value_heads": 4, "query_pre_attn_scalar": 256, "rms_norm_eps": 0.000001, "rope_local_base_freq": 10000, "rope_scaling": { "factor": 8, "rope_type": "linear" }, "rope_theta": 1000000, "sliding_window": 1024, "sliding_window_pattern": 6, "torch_dtype": "float32", "use_cache": true, "vocab_size": 262208 }, "torch_dtype": "float32", "transformers_version": "4.51.3", "vision_config": { "attention_dropout": 0, "hidden_act": "gelu_pytorch_tanh", "hidden_size": 1152, "image_size": 896, "intermediate_size": 4304, "layer_norm_eps": 0.000001, "model_type": "siglip_vision_model", "num_attention_heads": 16, "num_channels": 3, "num_hidden_layers": 27, "patch_size": 14, "torch_dtype": "float32", "vision_use_head": false } }