FlanT5
FLAN, which stands for Fine-tuned LAnguage Net (FLAN), is a technique for instruction tuning to learn how to solve natural language processing tasks in general. It can be used to answer questions or tasks across many languages - you can read more here. We currently have the following Flan-T5 models available below however if you would like any others contact support, and we can quickly add it for you. In order to deploy it you can use the identifier below:
- Flan XL:
flan-t5-xl
Once you’ve deployed a FLAN model, you can supply the endpoint with a prompt. Here’s an example of how to call the deployed endpoint:
Request Parameters
curl --location --request POST 'https://run.cerebrium.ai/flan-t5-xl-webhook/predict' \
--header 'Authorization: <API_KEY>' \
--header 'Content-Type: application/json' \
--data-raw '{
"prompt": "translate English to German: How old are you?"
}'
This is the Cerebrium API key used to authenticate your request. You can get it from your Cerebrium dashboard.
The prompt you would like FLAN to process.
{
"run_id": "<UUID_STRING>",
"run_time_ms": 251.14917755126953,
"message": "Successfully generated",
"result": "Wie alt sind Sie?"
}
Response Parameters
A unique identifier for the run that you can use to associate prompts with webhook endpoints.
The amount of time in millisecond it took to run your function. This is what you will be billed for.
Whether of not the response was successful
The result generated from FLAN
curl --location --request POST 'https://run.cerebrium.ai/flan-t5-xl-webhook/predict' \
--header 'Authorization: <API_KEY>' \
--header 'Content-Type: application/json' \
--data-raw '{
"prompt": "translate English to German: How old are you?"
}'
{
"run_id": "<UUID_STRING>",
"run_time_ms": 251.14917755126953,
"message": "Successfully generated",
"result": "Wie alt sind Sie?"
}