Instructions to use VARabi/ALDi-Token-DI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use VARabi/ALDi-Token-DI with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="VARabi/ALDi-Token-DI")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("VARabi/ALDi-Token-DI") model = AutoModelForTokenClassification.from_pretrained("VARabi/ALDi-Token-DI", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download optimizer.pt from VARabi/ALDi-Token-DI: direct link, hf CLI and curl.
- Browser
- Download file 1.3 GB
-
https://huggingface.co/VARabi/ALDi-Token-DI/resolve/main/optimizer.pt
- Command line
-
hf download hf://VARabi/ALDi-Token-DI/optimizer.pt
-
curl -L -o optimizer.pt https://huggingface.co/VARabi/ALDi-Token-DI/resolve/main/optimizer.pt
1.3 GB
- Xet hash:
- ce9f214eacecb646a3688fb2f65be87a5105b09a74dfda82dd7dd1fb4c0779ab
- Size of remote file:
- 1.3 GB
- SHA256:
- dc0454bac094eb9bcfc5225a1906cb99c102336172ef9e7bafc8054a4c830871
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.