Upload 19 files

config.json

@@ -204,7 +204,7 @@
   "vision_batch_size": 16,
   "vision_config": {
     "hidden_size": 48,
-    "image_size": 100,
+    "image_size": 448,
     "intermediate_size": 64,
     "model_type": "siglip_vision_model",
     "num_attention_heads": 4,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59a686f1801e1ed4d44e8e1ac7fc175dcae2b581570dea016e586c9f59e35c75
-size 5535352
+oid sha256:8043a2ab28496cf9167e6df08230db6506c5abb291188e842469837bee682e5c
+size 5628952

preprocessor_config.json

@@ -0,0 +1,43 @@
+{
+  "auto_map": {
+    "AutoImageProcessor": "image_processing_minicpmv.MiniCPMVImageProcessor",
+    "AutoProcessor": "processing_minicpmo.MiniCPMOProcessor"
+  },
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 80,
+  "hop_length": 160,
+  "im_end": "</image>",
+  "im_id_end": "</image_id>",
+  "im_id_start": "<image_id>",
+  "im_start": "<image>",
+  "image_feature_size": 64,
+  "image_processor_type": "MiniCPMVImageProcessor",
+  "max_slice_nums": 9,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "norm_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "norm_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "patch_size": 14,
+  "processor_class": "MiniCPMOProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000,
+  "scale_resolution": 448,
+  "slice_end": "</slice>",
+  "slice_mode": true,
+  "slice_start": "<slice>",
+  "unk": "<unk>",
+  "use_image_id": true,
+  "version": 2.6
+}

processor_config.json

@@ -0,0 +1,6 @@
+{
+  "auto_map": {
+    "AutoProcessor": "processing_minicpmo.MiniCPMOProcessor"
+  },
+  "processor_class": "MiniCPMOProcessor"
+}