config.json

{
  "architectures": [
    "Gemma3OmniForConditionalGeneration"
  ],
  "audio_token_index": 262151,
  "auto_map": {
    "AutoConfig": "configuration_gemma3_omni.Gemma3OmniConfig",
    "AutoFeatureExtractor": "processing_gemma3_omni.Gemma3AudioFeatureExtractor",
    "AutoModel": "modeling_gemma3_omni.Gemma3OmniForConditionalGeneration",
    "AutoModelForCausalLM": "modeling_gemma3_omni.Gemma3OmniForConditionalGeneration",
    "AutoProcessor": "processing_gemma3_omni.Gemma3OmniProcessor"
  },
  "boi_token_index": 255999,
  "eoi_token_index": 256000,
  "eos_token_id": [
    1,
    106
  ],
  "image_token_index": 262152,
  "initializer_range": 0.02,
  "mm_tokens_per_image": 256,
  "model_type": "gemma3omni",
  "text_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "attn_logit_softcapping": null,
    "final_logit_softcapping": null,
    "head_dim": 128,
    "hidden_activation": "gelu_pytorch_tanh",
    "hidden_size": 5376,
    "initializer_range": 0.02,
    "intermediate_size": 21504,
    "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",
      "sliding_attention",
      "sliding_attention"
    ],
    "max_position_embeddings": 131072,
    "model_type": "gemma3_text",
    "num_attention_heads": 32,
    "num_hidden_layers": 62,
    "num_key_value_heads": 16,
    "query_pre_attn_scalar": 168,
    "rms_norm_eps": 1e-06,
    "rope_local_base_freq": 10000.0,
    "rope_scaling": {
      "factor": 8.0,
      "rope_type": "linear"
    },
    "rope_theta": 1000000.0,
    "sliding_window": 1024,
    "torch_dtype": "float32",
    "use_cache": true,
    "vocab_size": 262208
  },
  "torch_dtype": "bfloat16",
  "transformers_version": "4.53.0.dev0",
  "vision_config": {
    "attention_dropout": 0.0,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 1152,
    "image_size": 896,
    "intermediate_size": 4304,
    "layer_norm_eps": 1e-06,
    "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
  }
}