Instructions to use ModelTC/bert-base-uncased-qnli with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ModelTC/bert-base-uncased-qnli with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="ModelTC/bert-base-uncased-qnli")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("ModelTC/bert-base-uncased-qnli") model = AutoModelForSequenceClassification.from_pretrained("ModelTC/bert-base-uncased-qnli", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download optimizer.pt from ModelTC/bert-base-uncased-qnli: direct link, hf CLI and curl.
- Browser
- Download file 876 MB
-
https://huggingface.co/ModelTC/bert-base-uncased-qnli/resolve/refs%2Fpr%2F1/optimizer.pt
- Command line
-
hf download hf://ModelTC/bert-base-uncased-qnli@refs/pr/1/optimizer.pt
-
curl -L -o optimizer.pt https://huggingface.co/ModelTC/bert-base-uncased-qnli/resolve/refs%2Fpr%2F1/optimizer.pt
876 MB
- Xet hash:
- 8432ed92b95fdeeae7ba7131f1e422a97543c2921dba2642a0130e39b2298cbe
- Size of remote file:
- 876 MB
- SHA256:
- e4e0196c52812a4ce94c341e5c7bc3e504c8110615de60f69e67d1231b82d384
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.