Update config.json

config.json

@@ -1,37 +1,42 @@
 {
   "architectures": [
-    "Gemma3ForCausalLM"
+    "Gemma3ForConditionalGeneration"
   ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "attn_logit_softcapping": null,
-  "bos_token_id": 2,
-  "cache_implementation": "hybrid",
-  "eos_token_id": 1,
-  "final_logit_softcapping": null,
-  "head_dim": 128,
-  "hidden_activation": "gelu_pytorch_tanh",
-  "hidden_size": 5376,
+  "boi_token_index": 255999,
+  "eoi_token_index": 256000,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "image_token_index": 262144,
   "initializer_range": 0.02,
-  "intermediate_size": 21504,
-  "max_position_embeddings": 131072,
-  "model_type": "gemma3_text",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 62,
-  "num_key_value_heads": 16,
-  "pad_token_id": 0,
-  "query_pre_attn_scalar": 168,
-  "rms_norm_eps": 1e-06,
-  "rope_local_base_freq": 10000.0,
-  "rope_scaling": {
-    "factor": 8.0,
-    "rope_type": "linear"
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
+  "text_config": {
+    "head_dim": 128,
+    "hidden_size": 5376,
+    "intermediate_size": 21504,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 62,
+    "num_key_value_heads": 16,
+    "query_pre_attn_scalar": 168,
+    "rope_scaling": {
+      "factor": 8.0,
+      "rope_type": "linear"
+    },
+    "sliding_window": 1024
   },
-  "rope_theta": 1000000.0,
-  "sliding_window": 1024,
-  "sliding_window_pattern": 6,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.50.0.dev0",
-  "use_cache": true,
-  "vocab_size": 262208
-}
+  "vision_config": {
+    "hidden_size": 1152,
+    "image_size": 896,
+    "intermediate_size": 4304,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "vision_use_head": false
+  }
+}