Instructions to use IDEA-CCNL/Randeng-T5-784M-QA-Chinese with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use IDEA-CCNL/Randeng-T5-784M-QA-Chinese with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="IDEA-CCNL/Randeng-T5-784M-QA-Chinese")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("IDEA-CCNL/Randeng-T5-784M-QA-Chinese") model = AutoModelForSeq2SeqLM.from_pretrained("IDEA-CCNL/Randeng-T5-784M-QA-Chinese") - Notebooks
- Google Colab
- Kaggle
You have to specify either decoder_input_ids or decoder_inputs_embeds
#2
by jfxiong - opened
see title
got same error
What is the version of transformers? the 4.21.1 version works fine. You can downgrade transformers or follow the document of batch_decode function of your version.
Justcode changed discussion status to closed