Is there a way to get GenerateResponse full json when calling sagemaker endpoints #1029
-
|
The schema here (https://huggingface.github.io/text-generation-inference/#/Text%20Generation%20Inference/generate) shows the response contains details and generated_text. Currently, the output response from the sagemaker endpoints using TGI only return generated_text. Is there a way to get the full output json in the response to a sagemaker endpoint request? |
Beta Was this translation helpful? Give feedback.
Replies: 3 comments 1 reply
-
|
Bumping this! |
Beta Was this translation helpful? Give feedback.
-
|
You need to provide "decoder_input_details": true,
"details": true,in the parameters to get the details |
Beta Was this translation helpful? Give feedback.
-
|
Thank you! |
Beta Was this translation helpful? Give feedback.
You need to provide
in the parameters to get the details