Instructions to use ModelTC/roberta-base-qqp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ModelTC/roberta-base-qqp with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="ModelTC/roberta-base-qqp")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("ModelTC/roberta-base-qqp") model = AutoModelForSequenceClassification.from_pretrained("ModelTC/roberta-base-qqp", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download optimizer.pt from ModelTC/roberta-base-qqp: direct link, hf CLI and curl.
- Browser
- Download file 997 MB
-
https://huggingface.co/ModelTC/roberta-base-qqp/resolve/main/optimizer.pt
- Command line
-
hf download hf://ModelTC/roberta-base-qqp/optimizer.pt
-
curl -L -o optimizer.pt https://huggingface.co/ModelTC/roberta-base-qqp/resolve/main/optimizer.pt
997 MB
- Xet hash:
- 04b0cab9bd9f8482d82f7f5d6b86c66e66732f6eaceea0c6160b30eed45f96ae
- Size of remote file:
- 997 MB
- SHA256:
- aec343a5d7621f55ed3aab706b2cb04d8702ec27f96f1f559a45d7bed50a567e
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.