Feature Extraction
sentence-transformers
Safetensors
Transformers
nanovdr_doc
visual-document-retrieval
document-ai
nanovdr
knowledge-distillation
retrieval
custom_code
Instructions to use nanovdr/NanoVDR-D-HiRes-Qwen3VL8B-4096 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use nanovdr/NanoVDR-D-HiRes-Qwen3VL8B-4096 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("nanovdr/NanoVDR-D-HiRes-Qwen3VL8B-4096", trust_remote_code=True) sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Transformers
How to use nanovdr/NanoVDR-D-HiRes-Qwen3VL8B-4096 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="nanovdr/NanoVDR-D-HiRes-Qwen3VL8B-4096", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nanovdr/NanoVDR-D-HiRes-Qwen3VL8B-4096", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Ship the tiling image processor; load as a SentenceTransformer too
Browse files- preprocessor_config.json +12 -2
preprocessor_config.json
CHANGED
|
@@ -1,4 +1,8 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"crop_size": {
|
| 3 |
"height": 448,
|
| 4 |
"width": 448
|
|
@@ -8,12 +12,14 @@
|
|
| 8 |
"do_normalize": true,
|
| 9 |
"do_rescale": true,
|
| 10 |
"do_resize": true,
|
|
|
|
| 11 |
"image_mean": [
|
| 12 |
0.485,
|
| 13 |
0.456,
|
| 14 |
0.406
|
| 15 |
],
|
| 16 |
-
"image_processor_type": "
|
|
|
|
| 17 |
"image_std": [
|
| 18 |
0.229,
|
| 19 |
0.224,
|
|
@@ -23,5 +29,9 @@
|
|
| 23 |
"rescale_factor": 0.00392156862745098,
|
| 24 |
"size": {
|
| 25 |
"shortest_edge": 448
|
| 26 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"auto_map": {
|
| 3 |
+
"AutoImageProcessor": "processing_nanovdr_doc.NanoVDRDocImageProcessor",
|
| 4 |
+
"AutoProcessor": "processing_nanovdr_doc.NanoVDRDocImageProcessor"
|
| 5 |
+
},
|
| 6 |
"crop_size": {
|
| 7 |
"height": 448,
|
| 8 |
"width": 448
|
|
|
|
| 12 |
"do_normalize": true,
|
| 13 |
"do_rescale": true,
|
| 14 |
"do_resize": true,
|
| 15 |
+
"do_tile": true,
|
| 16 |
"image_mean": [
|
| 17 |
0.485,
|
| 18 |
0.456,
|
| 19 |
0.406
|
| 20 |
],
|
| 21 |
+
"image_processor_type": "NanoVDRDocImageProcessor",
|
| 22 |
+
"image_size": 448,
|
| 23 |
"image_std": [
|
| 24 |
0.229,
|
| 25 |
0.224,
|
|
|
|
| 29 |
"rescale_factor": 0.00392156862745098,
|
| 30 |
"size": {
|
| 31 |
"shortest_edge": 448
|
| 32 |
+
},
|
| 33 |
+
"tile_max_num": 6,
|
| 34 |
+
"tile_max_total": 7,
|
| 35 |
+
"tile_min_num": 1,
|
| 36 |
+
"tile_use_thumbnail": true
|
| 37 |
}
|