Instructions to use google/flan-ul2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/flan-ul2 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("google/flan-ul2") model = AutoModelForSeq2SeqLM.from_pretrained("google/flan-ul2") - Notebooks
- Google Colab
- Kaggle
Generate text in readable format?
#19
by AshokRaja - opened
In all the cases that I tested, the model just generates texts only in sequential sentence format. Is it capable of generating text in readable format like: bullet points or New line added where ever necessary?
i'm looking for same thing. Does any thing worked for you?
Not without additional fine-tuning with adding extra tokens into the tokenizer. The tokenizer provided with the model treats line breaks (and some other formatting characters like tabs) as whitespaces.