Instructions to use bn22/CLIP-ViT-S-16-PRUNED-VISION with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bn22/CLIP-ViT-S-16-PRUNED-VISION with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="bn22/CLIP-ViT-S-16-PRUNED-VISION")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("bn22/CLIP-ViT-S-16-PRUNED-VISION") model = AutoModel.from_pretrained("bn22/CLIP-ViT-S-16-PRUNED-VISION", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload model
Browse files- config.json +2 -19
- model.safetensors +1 -1
config.json
CHANGED
|
@@ -1,38 +1,21 @@
|
|
| 1 |
{
|
| 2 |
-
"add_cross_attention": false,
|
| 3 |
"architectures": [
|
| 4 |
"CLIPVisionModel"
|
| 5 |
],
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
-
"bos_token_id": null,
|
| 8 |
-
"decoder_start_token_id": null,
|
| 9 |
-
"dropout": 0.0,
|
| 10 |
"dtype": "float32",
|
| 11 |
-
"
|
| 12 |
-
"finetuning_task": null,
|
| 13 |
-
"hidden_act": "quick_gelu",
|
| 14 |
"hidden_size": 384,
|
| 15 |
"image_size": 224,
|
| 16 |
"initializer_factor": 1.0,
|
| 17 |
"initializer_range": 0.02,
|
| 18 |
"intermediate_size": 3072,
|
| 19 |
-
"is_decoder": false,
|
| 20 |
"layer_norm_eps": 1e-05,
|
| 21 |
"model_type": "clip_vision_model",
|
| 22 |
"num_attention_heads": 12,
|
| 23 |
"num_channels": 3,
|
| 24 |
"num_hidden_layers": 12,
|
| 25 |
-
"pad_token_id": null,
|
| 26 |
"patch_size": 16,
|
| 27 |
-
"prefix": null,
|
| 28 |
"projection_dim": 512,
|
| 29 |
-
"
|
| 30 |
-
"sep_token_id": null,
|
| 31 |
-
"task_specific_params": null,
|
| 32 |
-
"tie_encoder_decoder": false,
|
| 33 |
-
"tie_word_embeddings": true,
|
| 34 |
-
"tokenizer_class": null,
|
| 35 |
-
"torchscript": false,
|
| 36 |
-
"transformers_version": "5.0.0",
|
| 37 |
-
"use_bfloat16": false
|
| 38 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"CLIPVisionModel"
|
| 4 |
],
|
| 5 |
"attention_dropout": 0.0,
|
|
|
|
|
|
|
|
|
|
| 6 |
"dtype": "float32",
|
| 7 |
+
"hidden_act": "gelu",
|
|
|
|
|
|
|
| 8 |
"hidden_size": 384,
|
| 9 |
"image_size": 224,
|
| 10 |
"initializer_factor": 1.0,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
"intermediate_size": 3072,
|
|
|
|
| 13 |
"layer_norm_eps": 1e-05,
|
| 14 |
"model_type": "clip_vision_model",
|
| 15 |
"num_attention_heads": 12,
|
| 16 |
"num_channels": 3,
|
| 17 |
"num_hidden_layers": 12,
|
|
|
|
| 18 |
"patch_size": 16,
|
|
|
|
| 19 |
"projection_dim": 512,
|
| 20 |
+
"transformers_version": "5.0.0"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 143384680
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:339094efb3ce0e19abff00e5908fde39e7143ca3f81e223364de1c11e9891221
|
| 3 |
size 143384680
|