03 Error When Using Qwen/Qwen2.5-VL-32B-Instruct with Inference Provider

Models
2

Hmm… It works…

from huggingface_hub import InferenceClient

client = InferenceClient(
    model="Qwen/Qwen2.5-VL-32B-Instruct",
    provider="fireworks-ai",
    api_key="hf_********",
)

IMAGE_URL = "https://upload.wikimedia.org/wikipedia/commons/4/4d/Cat_November_2010-1a.jpg"

resp = client.chat.completions.create(
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "Describe the image in one sentence."},
            {"type": "image_url", "image_url": {"url": IMAGE_URL}},
        ],
    }],
    max_tokens=128,
)

print(resp.choices[0].message["content"]) # 这是一张猫的照片。图片中的猫有条纹的毛色，主要是棕色和黑色相间的条纹。它的耳朵竖立，眼睛是绿色的，正直视着镜头。猫的胡须清晰可见，前爪放在一个浅色的表面上，可能是石头或混凝土。背景模糊，显示出一些树枝和天空，表明猫可能在户外。整体画面给人一种宁静而专注的感觉，猫的姿态显得警觉且好奇。
1 Like