sudo docker run --runtime nvidia --gpus '"device=0,1"' --ipc=host -p 18434:8000 -v hf_cache:/root/.cache/huggingface -d -e HF_ENDPOINT=https://hf-mirror.com -e HF_HUB_ENABLE_HF_TRANSFER=0 --name Qwen-VL-Chat vllm/vllm-openai:latest --model Qwen/Qwen-VL-Chat --tokenizer Qwen/Qwen-VL-Chat --tensor-parallel-size 2 --trust-remote-code --chat-template examples/template_chatml.jinja --dtype='half' 

Error in API call: 400 {"object":"error","message":"Token id 151859 is out of vocabulary","type":"BadRequestError","param":null,"code":400} 

import requests import base64 import time # Function to encode the image to base64 def encode_image(image_path): with open(image_path, "rb") as image_file: return base64.b64encode(image_file.read()).decode("utf-8") def main(): # Path to your image image_path = "test2.jpg" base64_image = encode_image(image_path) # API configuration api_base = "http://192.168.50.18:18434/v1/chat/completions" model_name = "Qwen/Qwen-VL-Chat" # Input prompt user_prompt_text = ( "What's inside the image?" ) # Prepare the payload payload_template = { "model": model_name, "messages": [ { "role": "user", "content": [ # {"type": "image_url", "image_url": {"url": "https://i.imgur.com/T3S0cvu.jpeg"}}, {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{base64_image}"}}, {"type": "text", "text": user_prompt_text} ] } ], "max_tokens": 300 } for i in range(1, 2): print(f"===== API called {i} times =====") startTime = time.time() response = requests.post(api_base, json=payload_template) if response.status_code != 200: print("Error in API call:", response.status_code, response.text) else: completion = response.json()["choices"][0]["message"]["content"] tokens = response.json()["usage"]["prompt_tokens"] print("Model Response:", completion) print("tokens:", tokens) print("time used: {:.2f} 秒".format(time.time() - startTime)) print() if __name__ == "__main__": main()