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")# 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
how to install?
#1
by koshinryuu - opened
should I use the openAI clip? https://github.com/openai/CLIP
should I use the openAI clip? https://github.com/openai/CLIP
yap, the vision encoder is from opanai. We only tune the Roberta
koshinryuu changed discussion title from how to install, to how to install?
if I want to fine-tune your model on one custom data(data size is small), may I ask which code should I follow?