Instructions to use google/flan-t5-xxl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/flan-t5-xxl with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("google/flan-t5-xxl") model = AutoModelForSeq2SeqLM.from_pretrained("google/flan-t5-xxl") - Notebooks
- Google Colab
- Kaggle
Minimum number of tokens in generate
#38
by rachith - opened
To avoid duplication, please see here: and https://discuss.huggingface.co/t/minimum-number-of-tokens-in-generate/33481?u=rachith
In essence, I think min_new_tokens in model.generate() doesnt do what its supposed to it and it seems like a general issue not restricted to flant5? Or is it?