Instructions to use mudes/multilingual-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mudes/multilingual-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="mudes/multilingual-base")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("mudes/multilingual-base") model = AutoModelForTokenClassification.from_pretrained("mudes/multilingual-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download optimizer.pt from mudes/multilingual-base: direct link, hf CLI and curl.
- Browser
- Download file 2.22 GB
-
https://huggingface.co/mudes/multilingual-base/resolve/refs%2Fpr%2F1/optimizer.pt
- Command line
-
hf download hf://mudes/multilingual-base@refs/pr/1/optimizer.pt
-
curl -L -o optimizer.pt https://huggingface.co/mudes/multilingual-base/resolve/refs%2Fpr%2F1/optimizer.pt
2.22 GB
- Xet hash:
- 0267141ec684f58d0bf44675d261c36815d000220f3e3a419f3f42f3e31c49cb
- Size of remote file:
- 2.22 GB
- SHA256:
- 8882e88e1c10417ba9420ce17b8f6432066b1d8da1d9c4013c5161455d97b422
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.