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
-
Set tokenizer model_max_length to 2048
As described in the FLAN-UL2 blog, the receptive field of the model was increased from 512 to 2048. There is also a `n_positions` in the model config, set to 512, but I can't see its use in `transformers` 🤔880eaf5
-
Update README.md
5dfdc8c -
Update README.md
701c4a4 -
AutoModelForConditionalGeneration -> T5ForConditionalGeneration (#3)
- AutoModelForConditionalGeneration -> T5ForConditionalGeneration (8f7211daa43bf51809b7293b59b7b5a787477930) Co-authored-by: Koki Tanaka <gojiteji@users.noreply.huggingface.co>3d9a23c -
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