Update config.json

config.json

@@ -1,55 +1,62 @@
 {
-    "architectures": [
-        "Gemma3ForConditionalGeneration"
-    ],
-    "boi_token_index": 255999,
-    "eoi_token_index": 256000,
-    "eos_token_id": 1,
+  "architectures": [
+    "Gemma3ForConditionalGeneration"
+  ],
+  "boi_token_index": 255999,
+  "eoi_token_index": 256000,
+  "eos_token_id": 1,
+  "image_token_index": 262144,
+  "initializer_range": 0.02,
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
+  "quantization": {
+    "group_size": 64,
+    "bits": 4,
+    "mode": "affine"
+  },
+  "quantization_config": {
+    "group_size": 64,
+    "bits": 4,
+    "mode": "affine"
+  },
+  "vision_config": {
+    "model_type": "gemma3_vision",
+    "mm_tokens_per_image": 256,
     "image_token_index": 262144,
+    "boi_token_index": 255999,
+    "eoi_token_index": 256000
+  },
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "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,
-    "mm_tokens_per_image": 256,
-    "model_type": "gemma3",
-    "quantization": {
-        "group_size": 64,
-        "bits": 4,
-        "mode": "affine"
-    },
-    "quantization_config": {
-        "group_size": 64,
-        "bits": 4,
-        "mode": "affine"
-    },
-    "text_config": {
-        "attention_bias": false,
-        "attention_dropout": 0.0,
-        "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": 1e-06,
-        "rope_local_base_freq": 10000.0,
-        "rope_scaling": {
-            "factor": 8.0,
-            "rope_type": "linear"
-        },
-        "rope_theta": 1000000.0,
-        "sliding_window": 1024,
-        "sliding_window_pattern": 6,
-        "torch_dtype": "bfloat16",
-        "use_cache": true,
-        "vocab_size": 262208
+    "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": 1e-06,
+    "rope_local_base_freq": 10000.0,
+    "rope_scaling": {
+      "factor": 8.0,
+      "rope_type": "linear"
     },
+    "rope_theta": 1000000.0,
+    "sliding_window": 1024,
+    "sliding_window_pattern": 6,
     "torch_dtype": "bfloat16",
-    "transformers_version": "4.50.0.dev0",
-    "use_cache": false
-}
+    "use_cache": true,
+    "vocab_size": 262208
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.0.dev0",
+  "use_cache": false
+}