Upload 4 files
Browse files
modular_model_index.json
CHANGED
|
@@ -70,5 +70,33 @@
|
|
| 70 |
],
|
| 71 |
"variant": null
|
| 72 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 73 |
]
|
| 74 |
}
|
|
|
|
| 70 |
],
|
| 71 |
"variant": null
|
| 72 |
}
|
| 73 |
+
],
|
| 74 |
+
"vision_encoder": [
|
| 75 |
+
"transformers",
|
| 76 |
+
"Qwen3_5VisionModel",
|
| 77 |
+
{
|
| 78 |
+
"pretrained_model_name_or_path": null,
|
| 79 |
+
"revision": null,
|
| 80 |
+
"subfolder": "vision_encoder",
|
| 81 |
+
"type_hint": [
|
| 82 |
+
"transformers",
|
| 83 |
+
"Qwen3_5VisionModel"
|
| 84 |
+
],
|
| 85 |
+
"variant": null
|
| 86 |
+
}
|
| 87 |
+
],
|
| 88 |
+
"vision_processor": [
|
| 89 |
+
"transformers",
|
| 90 |
+
"Qwen2VLImageProcessor",
|
| 91 |
+
{
|
| 92 |
+
"pretrained_model_name_or_path": null,
|
| 93 |
+
"revision": null,
|
| 94 |
+
"subfolder": "vision_processor",
|
| 95 |
+
"type_hint": [
|
| 96 |
+
"transformers",
|
| 97 |
+
"Qwen2VLImageProcessor"
|
| 98 |
+
],
|
| 99 |
+
"variant": null
|
| 100 |
+
}
|
| 101 |
]
|
| 102 |
}
|
vision_encoder/config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5VisionModel"
|
| 4 |
+
],
|
| 5 |
+
"deepstack_visual_indexes": [],
|
| 6 |
+
"depth": 27,
|
| 7 |
+
"dtype": "bfloat16",
|
| 8 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 9 |
+
"hidden_size": 1152,
|
| 10 |
+
"in_channels": 3,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 4304,
|
| 13 |
+
"model_type": "qwen3_5_vision",
|
| 14 |
+
"num_heads": 16,
|
| 15 |
+
"num_position_embeddings": 2304,
|
| 16 |
+
"out_hidden_size": 4096,
|
| 17 |
+
"patch_size": 16,
|
| 18 |
+
"spatial_merge_size": 2,
|
| 19 |
+
"temporal_patch_size": 2,
|
| 20 |
+
"transformers_version": "5.14.1"
|
| 21 |
+
}
|
vision_encoder/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb4e2f104a06ab655aaa0a5adab221c4dfbab38685e965c3f3ee8c9f57b1f86c
|
| 3 |
+
size 912053664
|
vision_processor/preprocessor_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": true,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.5,
|
| 8 |
+
0.5,
|
| 9 |
+
0.5
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.5,
|
| 14 |
+
0.5,
|
| 15 |
+
0.5
|
| 16 |
+
],
|
| 17 |
+
"merge_size": 2,
|
| 18 |
+
"patch_size": 16,
|
| 19 |
+
"resample": 3,
|
| 20 |
+
"rescale_factor": 0.00392156862745098,
|
| 21 |
+
"size": {
|
| 22 |
+
"longest_edge": 16777216,
|
| 23 |
+
"shortest_edge": 65536
|
| 24 |
+
},
|
| 25 |
+
"temporal_patch_size": 2
|
| 26 |
+
}
|