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:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("google/flan-ul2") model = AutoModelForSeq2SeqLM.from_pretrained("google/flan-ul2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
AutoModelForConditionalGeneration -> T5ForConditionalGeneration
It seems that `AutoModelForConditionalGeneration` doesn't exist in [HF API](https://huggingface.co/docs/transformers/model_doc/auto), so I changed to `T5ForConditionalGeneration` based on [config.json](https://huggingface.co/google/flan-ul2/blob/main/config.json) .8f7211d -
Update README.md
57f845f -
Update README.md
ac13457 -
Update README.md
50f8d3a -
Update README.md
75a0ff3 -
Update README.md (#2)
- Update README.md (789a1c780444af9a54cec6f3e3ac0e1e4cfb982d) Co-authored-by: Arthur Zucker <ArthurZ@users.noreply.huggingface.co>b5c5730 -
Create README.md (#1)
- Create README.md (c242559b11680bc15a00248693eade5235b7e937) Co-authored-by: Arthur Zucker <ArthurZ@users.noreply.huggingface.co>45377e4 -
Upload tokenizer
2153c0b -
Upload T5ForConditionalGeneration
c2e07e1 -
initial commit
Younes Belkadaf6076c3