Create app.py

app.py

@@ -1,64 +1,34 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+import torch
+from transformers import LlavaProcessor, LlavaForConditionalGeneration
+from PIL import Image
+
+# 加载模型
+model_id = "llava-hf/llava-v1.5-7b"
+processor = LlavaProcessor.from_pretrained(model_id)
+model = LlavaForConditionalGeneration.from_pretrained(model_id, device_map="auto", torch_dtype=torch.float16)
+
+def llava_infer(image, text):
+    if image is None or text.strip() == "":
+        return "请提供图片和文本输入"
+    
+    # 处理输入
+    inputs = processor(text=text, images=image, return_tensors="pt").to("cuda")
+    
+    # 生成输出
+    with torch.no_grad():
+        output = model.generate(**inputs, max_new_tokens=100)
+    
+    result = processor.batch_decode(output, skip_special_tokens=True)[0]
+    return result
+
+# 创建 Gradio 界面
+iface = gr.Interface(
+    fn=llava_infer,
+    inputs=[gr.Image(type="pil"), gr.Textbox(placeholder="输入文本...")],
+    outputs="text",
+    title="LLaVA Web UI",
+    description="上传图片并输入文本，LLaVA 将返回回答"
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+iface.launch()