Does GPT-J support api access?

Hi, i’m trying to use the gpt-j model to test through the api but i’m getting this error >> The model EleutherAI/gpt-j-6B is too large to be loaded automatically.

can you please tell me how to resolve this?

should i purchase the paid package or am i doing something wrong?

i used this code, i took it from the official website:

import requests

API_URL = "https://api-inference.huggingface.co/models/EleutherAI/gpt-j-6B"
headers = {"Authorization": "Bearer api_KsXRTrcHCdYZNqLVwStUOFmhcwxMWjPJDd"}

def query(payload):
response = requests.post(API_URL, headers=headers, json=payload)
return response.json()

output = query("Can you please let us know more details about your ")

print (output)

this is the output i’m getting:
{'error': 'The model EleutherAI/gpt-j-6B is too large to be loaded automatically.'}

Can you try again?

I just tested the inference widget, and it works for me.