import torch from datasets import Dataset from modelscope import snapshot_download, AutoTokenizer from qwen_vl_utils import process_vision_info from transformers import ( TrainingArguments, Trainer, DataCollatorForSeq2Seq, Qwen2VLForConditionalGeneration, AutoProcessor, ) import json # 在modelscope上下载Qwen2-VL模型到本地目录下 # model_dir = snapshot_download( # model_id="Qwen/Qwen2-VL-2B-Instruct", # cache_dir=model_path, # revision="master" # ) # print(f"模型已下载到: {model_dir}") model_dir = "/root/PMN_WS/qwen-test/model/Qwen/Qwen2-VL-2B-Instruct" # 使用Transformers加载模型权重 tokenizer = AutoTokenizer.from_pretrained(model_dir, use_fast=False, trust_remote_code=True) processor = AutoProcessor.from_pretrained(model_dir) model = Qwen2VLForConditionalGeneration.from_pretrained( model_dir, torch_dtype="auto", device_map="auto" ) messages = [ { "role": "user", "content": [ { "type": "image", "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg", }, {"type": "text", "text": "Describe this image."}, ], } ] # Preparation for inference text = processor.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) image_inputs, video_inputs = process_vision_info(messages) inputs = processor( text=[text], images=image_inputs, videos=video_inputs, padding=True, return_tensors="pt", ) inputs = inputs.to("cuda") # Inference: Generation of the output generated_ids = model.generate(**inputs, max_new_tokens=128) generated_ids_trimmed = [ out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids) ] output_text = processor.batch_decode( generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False ) print(output_text)