config.json

{
  "architectures": [
    "Gemma3ForConditionalGeneration"
  ],
  "boi_token_index": 255999,
  "bos_token_id": 2,
  "dtype": "bfloat16",
  "eoi_token_index": 256000,
  "eos_token_id": 106,
  "image_token_index": 262144,
  "initializer_range": 0.02,
  "mm_tokens_per_image": 256,
  "model_type": "gemma3",
  "pad_token_id": 0,
  "quantization_config": {
    "config_groups": {
      "group_0": {
        "format": "nvfp4-pack-quantized",
        "input_activations": {
          "actorder": null,
          "block_structure": null,
          "dynamic": "local",
          "group_size": 16,
          "num_bits": 4,
          "observer": "minmax",
          "observer_kwargs": {},
          "strategy": "tensor_group",
          "symmetric": true,
          "type": "float"
        },
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": 16,
          "num_bits": 4,
          "observer": "minmax",
          "observer_kwargs": {},
          "strategy": "tensor_group",
          "symmetric": true,
          "type": "float"
        }
      }
    },
    "format": "nvfp4-pack-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "lm_head"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "sparsity_config": {},
    "transform_config": {},
    "version": "0.12.2"
  },
  "text_config": {
    "_sliding_window_pattern": 6,
    "attention_bias": false,
    "attention_dropout": 0.0,
    "attn_logit_softcapping": null,
    "cache_implementation": "hybrid",
    "dtype": "bfloat16",
    "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,
    "rope_scaling": {
      "factor": 8.0,
      "rope_type": "linear"
    },
    "rope_theta": 1000000,
    "sliding_window": 1024,
    "use_cache": true,
    "vocab_size": 262208
  },
  "tie_word_embeddings": false,
  "transformers_version": "4.56.1",
  "unsloth_fixed": true,
  "vision_config": {
    "attention_dropout": 0.0,
    "dtype": "bfloat16",
    "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,
    "vision_use_head": false
  }
}