Instructions to use arman-aminian/clip-vision-farsi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use arman-aminian/clip-vision-farsi with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="arman-aminian/clip-vision-farsi")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("arman-aminian/clip-vision-farsi") model = AutoModel.from_pretrained("arman-aminian/clip-vision-farsi", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload 2 files
Browse files- config (3).json +23 -0
- pytorch_model (1).bin +3 -0
config (3).json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "openai/clip-vit-base-patch32",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CLIPVisionModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"dropout": 0.0,
|
| 8 |
+
"hidden_act": "quick_gelu",
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"image_size": 224,
|
| 11 |
+
"initializer_factor": 1.0,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-05,
|
| 15 |
+
"model_type": "clip_vision_model",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_channels": 3,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"patch_size": 32,
|
| 20 |
+
"projection_dim": 512,
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.26.1"
|
| 23 |
+
}
|
pytorch_model (1).bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5edce96654a1454dd188f07eba0a743081b5d1d647459f71e7212e3d21ff72b4
|
| 3 |
+
size 349893037
|