feat: qwen2-vl 测试

app.py

@@ -1,14 +1,54 @@
 import gradio as gr
 import spaces
 import torch
+import os
+import subprocess
 
-zero = torch.Tensor([0]).cuda()
-print(zero.device) # <-- 'cpu' 🤔
+os.system("pip install git+https://github.com/huggingface/transformers")
+
+from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
+from qwen_vl_utils import process_vision_info
+
+model = Qwen2VLForConditionalGeneration.from_pretrained("Qwen/Qwen2-VL-7B-Instruct").cuda()
+processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-7B-Instruct")
 
 @spaces.GPU
-def greet(n):
-    print(zero.device) # <-- 'cuda:0' 🤗
-    return f"Hello {zero + n} Tensor"
+def infer(n):
+    if len(n) < 1:
+        n = "请将图里文字转成markdown"
+    messages = [
+        {
+            "role": "user",
+            "content": [
+                {
+                    "type": "image",
+                    "image": "https://lf3-static.bytednsdoc.com/obj/eden-cn/pbovhozuha/screenshot-20240923-164458.png",
+                },
+                {"type": "text", "text": n},
+            ],
+        }
+    ]
+    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(model.device)
+    generated_ids = model.generate(**inputs, max_new_tokens=512)
+    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
+    )
+    return output_text
+    
 
-demo = gr.Interface(fn=greet, inputs=gr.Number(), outputs=gr.Text())
+demo = gr.Interface(fn=infer, inputs=gr.Number(), outputs=gr.Text())
 demo.launch()

requirements.txt

@@ -0,0 +1,2 @@
+transformers
+qwen-vl-utils