Instructions to use philschmid/flan-ul2-20b-fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use philschmid/flan-ul2-20b-fp16 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("philschmid/flan-ul2-20b-fp16") model = AutoModelForSeq2SeqLM.from_pretrained("philschmid/flan-ul2-20b-fp16", device_map="auto") - Notebooks
- Google Colab
- Kaggle
SageMaker Deploy Error
#1
by nickmandylas - opened
Receiving the following error when deployed the model & trying to run predict method:
An error occurred (ModelError) when calling the InvokeEndpoint operation: Received client error (400) from primary with message "{
"code": 400,
"type": "InternalServerException",
"message": "Could not load model /.sagemaker/mms/models/philschmid__flan-ul2-20b-fp16 with any of the following classes: (\u003cclass \u0027transformers.models.auto.modeling_auto.AutoModelForSeq2SeqLM\u0027\u003e, \u003cclass \u0027transformers.models.t5.modeling_t5.T5ForConditionalGeneration\u0027\u003e)."
}```
--
Edit: Used incorrect deployment strategy. Followed your blog. Thank you Phil.
nickmandylas changed discussion status to closed