support qwen-vl-chat model for dataset

hemm/models/qwen_vl.py

@@ -0,0 +1,34 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers.generation import GenerationConfig
+import torch
+torch.manual_seed(1234)
+
+tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-VL", trust_remote_code=True)
+
+# use bf16
+# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-VL", device_map="auto", trust_remote_code=True, bf16=True).eval()
+# use fp16
+# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-VL", device_map="auto", trust_remote_code=True, fp16=True).eval()
+# use cpu only
+# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-VL", device_map="cpu", trust_remote_code=True).eval()
+# use cuda device
+model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-VL", device_map="cuda", trust_remote_code=True).eval()
+
+# Specify hyperparameters for generation (No need to do this if you are using transformers>=4.32.0)
+# model.generation_config = GenerationConfig.from_pretrained("Qwen/Qwen-VL", trust_remote_code=True)
+
+query = tokenizer.from_list_format([
+    {'image': 'https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg'},
+    {'text': 'Generate the caption in English with grounding:'},
+])
+inputs = tokenizer(query, return_tensors='pt')
+inputs = inputs.to(model.device)
+pred = model.generate(**inputs)
+response = tokenizer.decode(pred.cpu()[0], skip_special_tokens=False)
+print(response)
+# <img>https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg</img>Generate the caption in English with grounding:<ref> Woman</ref><box>(451,379),(731,806)</box> and<ref> her dog</ref><box>(219,424),(576,896)</box> playing on the beach<|endoftext|>
+image = tokenizer.draw_bbox_on_latest_picture(response)
+if image:
+  image.save('2.jpg')
+else:
+  print("no box")