Update app.py

app.py

@@ -1,66 +1,91 @@
 
-
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoProcessor, Qwen2_5_VLForConditionalGeneration, TextIteratorStreamer
+from transformers.image_utils import load_image
+from threading import Thread
+import time
+import torch
+import spaces
+
+MODEL_ID = "TheEighthDay/SeekWorld_RL_PLUS"
+processor = AutoProcessor.from_pretrained(MODEL_ID, trust_remote_code=True)
+model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
+    MODEL_ID,
+    trust_remote_code=True,
+    torch_dtype=torch.bfloat16
+).to("cpu").eval()
+
+@spaces.GPU
+def model_inference(input_dict, history):
+    text = input_dict["text"]
+    files = input_dict["files"]
 
-"""
-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("TheEighthDay/SeekWorld_RL_PLUS")
+    # Load images if provided
+    if len(files) > 1:
+        images = [load_image(image) for image in files]
+    elif len(files) == 1:
+        images = [load_image(files[0])]
+    else:
+        images = []
 
+    # Validate input
+    if text == "" and not images:
+        gr.Error("Please input a query and optionally image(s).")
+        return
+    if text == "" and images:
+        gr.Error("Please input a text query along with the image(s).")
+        return
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+    # Prepare messages for the model
+    messages = [
+        {
+            "role": "user",
+            "content": [
+                *[{"type": "image", "image": image} for image in images],
+                {"type": "text", "text": text},
+            ],
+        }
+    ]
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    # Apply chat template and process inputs
+    prompt = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+    inputs = processor(
+        text=[prompt],
+        images=images if images else None,
+        return_tensors="pt",
+        padding=True,
+    ).to("cpu")
 
-    messages.append({"role": "user", "content": message})
+    # Set up streamer for real-time output
+    streamer = TextIteratorStreamer(processor, skip_prompt=True, skip_special_tokens=True)
+    generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=1024)
 
-    response = ""
+    # Start generation in a separate thread
+    thread = Thread(target=model.generate, kwargs=generation_kwargs)
+    thread.start()
 
-    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
+    # Stream the output
+    buffer = ""
+    yield "Thinking..."
+    for new_text in streamer:
+        buffer += new_text
+        time.sleep(0.01)
+        yield buffer
 
-        response += token
-        yield response
 
+# Example inputs
+examples = [
+]
 
-"""
-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)",
-        ),
-    ],
+    fn=model_inference,
+    description="# **Qwen2.5-VL-3B-Instruct**",
+    examples=examples,
+    textbox=gr.MultimodalTextbox(label="Query Input", file_types=["image"], file_count="multiple"),
+    stop_btn="Stop Generation",
+    multimodal=True,
+    cache_examples=False,
 )
 
+demo.launch(debug=True)
 
-if __name__ == "__main__":
-    demo.launch()