Instructions to use VARabi/Sentence-ALDi-50 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use VARabi/Sentence-ALDi-50 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="VARabi/Sentence-ALDi-50")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("VARabi/Sentence-ALDi-50") model = AutoModelForSequenceClassification.from_pretrained("VARabi/Sentence-ALDi-50", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download optimizer.pt from VARabi/Sentence-ALDi-50: direct link, hf CLI and curl.
- Browser
- Download file 1.3 GB
-
https://huggingface.co/VARabi/Sentence-ALDi-50/resolve/main/optimizer.pt
- Command line
-
hf download hf://VARabi/Sentence-ALDi-50/optimizer.pt
-
curl -L -o optimizer.pt https://huggingface.co/VARabi/Sentence-ALDi-50/resolve/main/optimizer.pt
1.3 GB
- Xet hash:
- 49b96aa9e7f3cc2488eb7f9752f94314fb1e5fcb6620462df5f2c5f99f135d26
- Size of remote file:
- 1.3 GB
- SHA256:
- 54c8f56c27e48fce875735c93c58c1a7d55cc84f80fba6896d1fba3c658e0944
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.