I don’t know… even models that don’t seem to be like that have the same behavior. Maybe the whole thing is buggy.
HF_TOKEN = "my token"
import requests
#API_URL = "https://api-inference.huggingface.co/models/google/flan-t5-large"
API_URL = "https://api-inference.huggingface.co/models/Qwen/Qwen2.5-3B"
HEADERS = {"Authorization": f"Bearer {HF_TOKEN}"}
response = requests.get(API_URL, headers=HEADERS)
print("Response status code:", response.status_code)
print("Response JSON:", response.json())