Upload config.json with huggingface_hub

config.json

@@ -56,16 +56,6 @@
   "image_token_id": 258880,
   "initializer_range": 0.02,
   "model_type": "gemma4",
-  "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,
@@ -160,5 +150,53 @@
   "tie_word_embeddings": true,
   "transformers_version": "5.5.0.dev0",
   "video_token_id": 258884,
-  "vision_soft_tokens_per_image": 280
+  "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": true
+  },
+  "vision_soft_tokens_per_image": 280,
+  "quantization_config": {
+    "bits": 4,
+    "group_size": 64,
+    "mode": "affine"
+  }
 }