Hugging Face's logo

poiccard
/
jais-13b-chat-adn

Text Generation
Transformers
PyTorch
Arabic
English
jais
Arabic
English
LLM
Decoder
causal-lm
conversational
custom_code
Inference Endpoints
Model card Files Community
2

API Implementation Error

#2
by infojunkie - opened
Discussion
infojunkie
•
edited Oct 1, 2023

Thanks for making the model available for deployment!

I have added my own inference endpoint using your repo, but when I type a prompt in the "Test your endpoint!" text box, I get an error:
API Implementation Error: Invalid output: output must be of type <conversation: <generated_responses:Array; past_user_inputs:Array>>

Any idea what I'm doing wrong?

Thanks!

poiccard
 Owner

@infojunkie
if you are testing in the huggingface web application - yes will not work, as the code now returns entire response for convenience (including initial promp)
please check with python code, or with curl command ( there are tabs)
sample curl
curl https://YOUR_ENDPOINT.aws.endpoints.huggingface.cloud -X POST -d '{"inputs": "ما هي عاصمة الامارات؟"}' -H "Authorization: Bearer YOUR_TOKEN" -H "Content-Type: application/json"

infojunkie

Thanks for your reply!

infojunkie changed discussion status to closed

Sign up or log in to comment