Instructions to use Lucas20250626/semanticgallery-mlx-siglip2-stage1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Lucas20250626/semanticgallery-mlx-siglip2-stage1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="Lucas20250626/semanticgallery-mlx-siglip2-stage1") pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Lucas20250626/semanticgallery-mlx-siglip2-stage1", device_map="auto") - MLX
How to use Lucas20250626/semanticgallery-mlx-siglip2-stage1 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir semanticgallery-mlx-siglip2-stage1 Lucas20250626/semanticgallery-mlx-siglip2-stage1
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Upload summary.json with huggingface_hub
Browse files- summary.json +50 -0
summary.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_path": "/Users/duanyongyao/PythonProjects/SemanticGallery/.cache/mlx/siglip2-base-patch16-224-f32",
|
| 3 |
+
"init_weights": null,
|
| 4 |
+
"weights_file": "/Users/duanyongyao/PythonProjects/SemanticGallery/logs/semanticgallery_public_stage1/weights.safetensors",
|
| 5 |
+
"precision": "bfloat16",
|
| 6 |
+
"lr": 1e-05,
|
| 7 |
+
"weight_decay": 0.01,
|
| 8 |
+
"max_length": 64,
|
| 9 |
+
"batch_size": 2,
|
| 10 |
+
"epochs": 1,
|
| 11 |
+
"seed": 20260403,
|
| 12 |
+
"train_rows": 1587,
|
| 13 |
+
"val_rows": 333,
|
| 14 |
+
"policy": {
|
| 15 |
+
"train": {
|
| 16 |
+
"public": 1587,
|
| 17 |
+
"private": 0,
|
| 18 |
+
"unknown": 0,
|
| 19 |
+
"sources": {
|
| 20 |
+
"flickr30k": 819,
|
| 21 |
+
"screen2words": 768
|
| 22 |
+
}
|
| 23 |
+
},
|
| 24 |
+
"val": {
|
| 25 |
+
"public": 0,
|
| 26 |
+
"private": 0,
|
| 27 |
+
"unknown": 0,
|
| 28 |
+
"sources": {}
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"trainable": {
|
| 32 |
+
"text_last_n": 2,
|
| 33 |
+
"vision_last_n": 2,
|
| 34 |
+
"trainable_parameter_tensors": 83
|
| 35 |
+
},
|
| 36 |
+
"history": [
|
| 37 |
+
{
|
| 38 |
+
"epoch": 1,
|
| 39 |
+
"train_loss": 7.748603820800781e-07,
|
| 40 |
+
"train_loss_last": 7.748603820800781e-07,
|
| 41 |
+
"train_rows": 2,
|
| 42 |
+
"train_steps": 1,
|
| 43 |
+
"train_step_mean_ms": 292.7449999988312,
|
| 44 |
+
"train_grad_norm_mean": 0.000255584716796875,
|
| 45 |
+
"val_loss": 0.00033167004585266113,
|
| 46 |
+
"val_rows": 2,
|
| 47 |
+
"val_steps": 1
|
| 48 |
+
}
|
| 49 |
+
]
|
| 50 |
+
}
|