Instructions to use google/ul2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/ul2 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("google/ul2") model = AutoModelForSeq2SeqLM.from_pretrained("google/ul2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from google/ul2: direct link, hf CLI and curl.
- Browser
- Download file 2.43 MB
-
https://huggingface.co/google/ul2/resolve/main/tokenizer.json
- Command line
-
hf download hf://google/ul2/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/google/ul2/resolve/main/tokenizer.json
2.43 MB
File too large to display, you can check the raw version instead.