Instructions to use OFA-Sys/chinese-clip-vit-base-patch16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OFA-Sys/chinese-clip-vit-base-patch16 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="OFA-Sys/chinese-clip-vit-base-patch16") pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# Load model directly from transformers import AutoProcessor, AutoModelForZeroShotImageClassification processor = AutoProcessor.from_pretrained("OFA-Sys/chinese-clip-vit-base-patch16") model = AutoModelForZeroShotImageClassification.from_pretrained("OFA-Sys/chinese-clip-vit-base-patch16", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update config.json
Browse files- config.json +3 -3
config.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
],
|
| 5 |
"initializer_factor": 1.0,
|
| 6 |
"logit_scale_init_value": 2.6592,
|
| 7 |
-
"model_type": "
|
| 8 |
"projection_dim": 512,
|
| 9 |
"text_config": {
|
| 10 |
"architectures": [
|
|
@@ -21,7 +21,7 @@
|
|
| 21 |
"intermediate_size": 3072,
|
| 22 |
"layer_norm_eps": 1e-12,
|
| 23 |
"max_position_embeddings": 512,
|
| 24 |
-
"model_type": "
|
| 25 |
"num_attention_heads": 12,
|
| 26 |
"num_hidden_layers": 12,
|
| 27 |
"output_past": true,
|
|
@@ -75,7 +75,7 @@
|
|
| 75 |
"length_penalty": 1.0,
|
| 76 |
"max_length": 20,
|
| 77 |
"min_length": 0,
|
| 78 |
-
"model_type": "
|
| 79 |
"no_repeat_ngram_size": 0,
|
| 80 |
"num_attention_heads": 12,
|
| 81 |
"num_beam_groups": 1,
|
|
|
|
| 4 |
],
|
| 5 |
"initializer_factor": 1.0,
|
| 6 |
"logit_scale_init_value": 2.6592,
|
| 7 |
+
"model_type": "chinese_clip",
|
| 8 |
"projection_dim": 512,
|
| 9 |
"text_config": {
|
| 10 |
"architectures": [
|
|
|
|
| 21 |
"intermediate_size": 3072,
|
| 22 |
"layer_norm_eps": 1e-12,
|
| 23 |
"max_position_embeddings": 512,
|
| 24 |
+
"model_type": "chinese_clip_text_model",
|
| 25 |
"num_attention_heads": 12,
|
| 26 |
"num_hidden_layers": 12,
|
| 27 |
"output_past": true,
|
|
|
|
| 75 |
"length_penalty": 1.0,
|
| 76 |
"max_length": 20,
|
| 77 |
"min_length": 0,
|
| 78 |
+
"model_type": "chinese_clip_vision_model",
|
| 79 |
"no_repeat_ngram_size": 0,
|
| 80 |
"num_attention_heads": 12,
|
| 81 |
"num_beam_groups": 1,
|