config.json

{
  "audio_config": {
    "_name_or_path": "",
    "architectures": null,
    "attention_chunk_size": 12,
    "attention_context_left": 13,
    "attention_context_right": 0,
    "attention_invalid_logits_value": -1000000000.0,
    "attention_logit_cap": 50.0,
    "chunk_size_feed_forward": 0,
    "conv_kernel_size": 5,
    "dtype": "bfloat16",
    "gradient_clipping": 10000000000.0,
    "hidden_act": "silu",
    "hidden_size": 1024,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "model_type": "gemma4_audio",
    "num_attention_heads": 8,
    "num_hidden_layers": 12,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_proj_dims": 1536,
    "problem_type": null,
    "residual_weight": 0.5,
    "return_dict": true,
    "rms_norm_eps": 1e-06,
    "subsampling_conv_channels": [
      128,
      32
    ],
    "use_clipped_linears": false
  },
  "audio_token_id": 258881,
  "boa_token_id": 256000,
  "boi_token_id": 255999,
  "eoa_token_id": 258883,
  "eoa_token_index": 258883,
  "eoi_token_id": 258882,
  "eos_token_id": [
    1,
    106
  ],
  "image_token_id": 258880,
  "initializer_range": 0.02,
  "model_type": "gemma4",
  "quantization_config": {
    "module_quant_configs": {
      "^lm_head$": {
        "num_bits": 2
      },
      "audio_tower(?!.*lconv1d\\.linear_start)": {
        "num_bits": 2
      },
      "audio_tower\\.layers\\.\\d+\\.lconv1d\\.linear_start\\.": {
        "num_bits": 4
      },
      "language_model\\.embed_tokens$": {
        "num_bits": 2
      },
      "language_model\\.embed_tokens_per_layer$": {
        "num_bits": 4
      },
      "language_model\\.layers\\.(\\d|1[0-4])\\.mlp\\.": {
        "num_bits": 4
      },
      "language_model\\.layers\\.\\d+\\.mlp\\.": {
        "num_bits": 2
      },
      "language_model\\.layers\\.\\d+\\.per_layer_input_gate$": {
        "num_bits": 8
      },
      "language_model\\.layers\\.\\d+\\.per_layer_projection$": {
        "num_bits": 8
      },
      "language_model\\.layers\\.\\d+\\.self_attn\\.": {
        "num_bits": 4
      },
      "vision_tower": {
        "num_bits": 8
      }
    },
    "modules_to_not_convert": [
      "model.vision_tower.patch_embedder",
      "model.audio_tower.subsample_conv_projection",
      "model.audio_tower.output_proj",
      "relative_k_proj",
      "model.embed_audio",
      "model.embed_vision",
      "per_layer_model_projection"
    ],
    "num_bits": 4,
    "quant_method": "gemma",
    "quantize_embeddings": true
  },
  "text_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "attention_k_eq_v": false,
    "bos_token_id": 2,
    "dtype": "bfloat16",
    "enable_moe_block": false,
    "eos_token_id": 1,
    "final_logit_softcapping": 30.0,
    "global_head_dim": 512,
    "head_dim": 256,
    "hidden_activation": "gelu_pytorch_tanh",
    "hidden_size": 1536,
    "hidden_size_per_layer_input": 256,
    "initializer_range": 0.02,
    "intermediate_size": 6144,
    "layer_types": [
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention"
    ],
    "max_position_embeddings": 131072,
    "model_type": "gemma4_text",
    "moe_intermediate_size": null,
    "num_attention_heads": 8,
    "num_experts": null,
    "num_global_key_value_heads": null,
    "num_hidden_layers": 35,
    "num_key_value_heads": 1,
    "num_kv_shared_layers": 20,
    "pad_token_id": 0,
    "rms_norm_eps": 1e-06,
    "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"
      }
    },
    "sliding_window": 512,
    "tie_word_embeddings": false,
    "top_k_experts": null,
    "use_bidirectional_attention": null,
    "use_cache": true,
    "use_double_wide_mlp": true,
    "vocab_size": 262144,
    "vocab_size_per_layer_input": 262144
  },
  "tie_word_embeddings": false,
  "transformers_version": "5.10.0.dev0",
  "video_token_id": 258884,
  "vision_config": {
    "_name_or_path": "",
    "architectures": null,
    "attention_bias": false,
    "attention_dropout": 0.0,
    "chunk_size_feed_forward": 0,
    "default_output_length": 280,
    "dtype": "bfloat16",
    "global_head_dim": 64,
    "head_dim": 64,
    "hidden_activation": "gelu_pytorch_tanh",
    "hidden_size": 768,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "max_position_embeddings": 131072,
    "model_type": "gemma4_vision",
    "num_attention_heads": 12,
    "num_hidden_layers": 16,
    "num_key_value_heads": 12,
    "output_attentions": false,
    "output_hidden_states": false,
    "patch_size": 16,
    "pooling_kernel_size": 3,
    "position_embedding_size": 10240,
    "problem_type": null,
    "return_dict": true,
    "rms_norm_eps": 1e-06,
    "rope_parameters": {
      "rope_theta": 100.0,
      "rope_type": "default"
    },
    "standardize": false,
    "use_clipped_linears": false
  },
  "vision_soft_tokens_per_image": 280
}