qwen-vl-utils

import os import torch # Required for device check and dtype from qwen_vl_utils.model import load_model_and_tokenizer from qwen_vl_utils.utils import gen_inference # NOTE: This example requires a Qwen-VL model checkpoint. # 1. Download a model, e.g., 'Qwen/Qwen-VL-Chat' from Hugging Face. # 2. Set the environment variable QWEN_VL_MODEL_PATH to its local path. # e.g., export QWEN_VL_MODEL_PATH="/path/to/Qwen-VL-Chat" model_path = os.environ.get('QWEN_VL_MODEL_PATH', '') if not model_path: print("WARNING: Please set the QWEN_VL_MODEL_PATH environment variable with your model's local path.") print("Skipping model loading and inference for quickstart.") else: try: device = "cuda" if torch.cuda.is_available() else "cpu" print(f"Using device: {device}") # Load model and tokenizer # For Qwen-VL-Chat models, torch.bfloat16 might be preferred for memory/performance if supported. # model, tokenizer = load_model_and_tokenizer(model_path, device=device, torch_dtype=torch.bfloat16) model, tokenizer = load_model_and_tokenizer(model_path, device=device) print("Model and tokenizer loaded successfully.") # Example query and image query = "What objects are in this image?" # Replace with a real image path (local or URL) for actual inference. # For this example, we'll use a placeholder URL. Real execution requires a valid image. image_input = "https://img.alicdn.com/imgextra/i3/O1CN01fQxAAx1hN0g3bM0d8_!!6000000004245-2-tps-1000-1000.png" # Generate inference print(f"Generating inference for query: '{query}' with image: {image_input}") response = gen_inference(model, tokenizer, query, image_input) print("\n--- Qwen-VL Inference Result ---") print(response) print("----------------------------------") except Exception as e: print(f"\nAn error occurred during quickstart execution: {e}") print("Please ensure your model path is correct, PyTorch with CUDA is installed (if using GPU), and all dependencies are met.")