Upload folder using huggingface_hub

config.json

@@ -4,6 +4,7 @@
   ],
   "audio_config": {
     "_name_or_path": "",
+    "architectures": null,
     "chunk_size_feed_forward": 0,
     "conf_attention_chunk_size": 12,
     "conf_attention_context_left": 13,
@@ -65,7 +66,6 @@
     "sscp_conv_time_pad_bottom": null,
     "sscp_conv_time_pad_top": null,
     "streaming": false,
-    "tokenizer_class": null,
     "use_clipped_linears": true
   },
   "audio_token_id": 258881,
@@ -194,24 +194,6 @@
     "hidden_activation": "gelu_pytorch_tanh",
     "hidden_size": 768,
     "intermediate_size": 3072,
-    "layer_types": [
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention"
-    ],
     "max_position_embeddings": 131072,
     "model_type": "gemma4_vision",
     "num_attention_heads": 12,
@@ -222,12 +204,10 @@
     "position_embedding_size": 10240,
     "rms_norm_eps": 1e-06,
     "rope_parameters": {
-      "full_attention": {
-        "rope_theta": 100.0,
-        "rope_type": "default"
-      }
+      "rope_theta": 100.0,
+      "rope_type": "default"
     },
-    "use_bidirectional_attention": "vision",
+    "standardize": false,
     "use_clipped_linears": true
   },
   "vision_soft_tokens_per_image": 280

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2e25db7503d031484be7e0d123bed86ce8f609abb3325b33b1fdb391992d43c
-size 15992602796
+oid sha256:d9397575f5910802b4570ca20bfd84164e295878e59706014bad874bdfa6cbef
+size 15992604452

processor_config.json

@@ -28,26 +28,22 @@
     "do_rescale": true,
     "do_resize": true,
     "image_mean": [
-      0.5,
-      0.5,
-      0.5
+      0.0,
+      0.0,
+      0.0
     ],
     "image_processor_type": "Gemma4ImageProcessor",
     "image_seq_length": 280,
     "image_std": [
-      0.5,
-      0.5,
-      0.5
+      1.0,
+      1.0,
+      1.0
     ],
     "max_soft_tokens": 280,
     "patch_size": 16,
     "pooling_kernel_size": 3,
     "resample": 3,
-    "rescale_factor": 0.00392156862745098,
-    "size": {
-      "height": 224,
-      "width": 224
-    }
+    "rescale_factor": 0.00392156862745098
   },
   "image_seq_length": 280,
   "processor_class": "Gemma4Processor"