Language Models
GPT-Neo

GPT-Neo is a transformer model designed using EleutherAI’s replication of the GPT-3 architecture. GPT-Neo refers to the class of models, while 1.3B, 2.7B etc. represents the number of parameters of the particular pre-trained model. GPT-Neo learns an inner representation of the English language that can be used to extract features useful for downstream tasks. You can read more here. We currently have the following GPT Neo 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:

  • GPT-Neo-1.3b: gpt-neo-1-3b

Once you’ve deployed a GPT model, you can supply the endpoint with a prompt and a few other parameters. Here’s an example of how to call the deployed endpoint:

Request Parameters

  curl --location --request POST 'https://run.cerebrium.ai/gpt-neo-13b-webhook/predict' \
      --header 'Authorization: <API_KEY>' \
      --header 'Content-Type: application/json' \
      --data-raw '{
        "prompt": "My name is Lewis and I like to",
        "max_length": 100,
        "temperature": 0.9
    }'
Authorizationrequired
string

This is the Cerebrium API key used to authenticate your request. You can get it from your Cerebrium dashboard.

promptrequired
string

The prompt you would like GPT to process.

max_lengthrequired
string

The max number of tokens you would like GPT Neo to generate

temperaturerequired
string

Value between 0 and 1 which controls randomness. Lowering the number results in less random completions.

{
  "run_id": "<UUID_STRING>",
  "run_time_ms": 251,
  "message": "Successfully generated text",
  "result": "My name is Lewis and I like to work in a nice calm environment. I recently moved into my own house but I have an office in the same building which is why I work at my desk rather than driving from place to place. I have always"
}

Response Parameters

run_idrequired
string

A unique identifier for the run that you can use to associate prompts with webhook endpoints.

run_time_msrequired
string

The amount of time in millisecond it took to run your function. This is what you will be billed for.

messagerequired
string

Whether of not the response was successful

resultrequired
string

The result generated from GPT Neo