Instructions to use IDEA-CCNL/Taiyi-CLIP-Roberta-102M-Chinese with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use IDEA-CCNL/Taiyi-CLIP-Roberta-102M-Chinese with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="IDEA-CCNL/Taiyi-CLIP-Roberta-102M-Chinese")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("IDEA-CCNL/Taiyi-CLIP-Roberta-102M-Chinese") model = AutoModelForSequenceClassification.from_pretrained("IDEA-CCNL/Taiyi-CLIP-Roberta-102M-Chinese", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
ec67cfd
1
Parent(s): e1aa040
update coco result
Browse files
README.md
CHANGED
|
@@ -71,9 +71,9 @@ with torch.no_grad():
|
|
| 71 |
|
| 72 |
| model | dataset | Top1 | Top5 | Top10 |
|
| 73 |
| ---- | ---- | ---- | ---- | ---- |
|
| 74 |
-
| Taiyi-CLIP-Roberta-102M-Chinese | Flickr30k-CNA-test | 44.06
|
| 75 |
-
| Taiyi-CLIP-Roberta-102M-Chinese | COCO-CN-test | 46.
|
| 76 |
-
| Taiyi-CLIP-Roberta-102M-Chinese | wukong50k | 48.67
|
| 77 |
|
| 78 |
|
| 79 |
# Citation
|
|
|
|
| 71 |
|
| 72 |
| model | dataset | Top1 | Top5 | Top10 |
|
| 73 |
| ---- | ---- | ---- | ---- | ---- |
|
| 74 |
+
| Taiyi-CLIP-Roberta-102M-Chinese | Flickr30k-CNA-test | 44.06% | 71.42% | 80.84% |
|
| 75 |
+
| Taiyi-CLIP-Roberta-102M-Chinese | COCO-CN-test | 46.24% | 78.06% | 88.88% |
|
| 76 |
+
| Taiyi-CLIP-Roberta-102M-Chinese | wukong50k | 48.67% | 81.77% | 90.09% |
|
| 77 |
|
| 78 |
|
| 79 |
# Citation
|