'image-to-text' not supported for provider 'zai-org'

#49
by BelegNeurion - opened
import os
from huggingface_hub import InferenceClient

client = InferenceClient(
    provider="zai-org",
    api_key=os.environ["HF_TOKEN"],
)

output = client.image_to_text("cats.jpg", model="zai-org/GLM-OCR")

Image OCR failed for model 'zai-org/GLM-OCR': Task 'image-to-text' not supported for provider 'zai-org'. Available tasks: ['conversational', 'text-to-image']

Am I missing something here?

Sign up or log in to comment