Update app.py

app.py

@@ -1,148 +1,66 @@
-import gradio as gr
-import numpy as np
-import random
+# app.py
 from transformers import AutoModelForCausalLM, AutoTokenizer
-
-# import spaces #[uncomment to use ZeroGPU]
-from diffusers import DiffusionPipeline
 import torch
+import gradio as gr
 
-device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "Qwen/Qwen2.5-3B-Instruct"  
-if torch.cuda.is_available():
-    torch_dtype = torch.float16
-else:
-    torch_dtype = torch.float32
-
-pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
-pipe = pipe.to(device)
-
-MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1024
-
-
-# @spaces.GPU #[uncomment to use ZeroGPU]
-def infer(
-    prompt,
-    negative_prompt,
-    seed,
-    randomize_seed,
-    width,
-    height,
-    guidance_scale,
-    num_inference_steps,
-    progress=gr.Progress(track_tqdm=True),
-):
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
-
-    generator = torch.Generator().manual_seed(seed)
-
-    image = pipe(
-        prompt=prompt,
-        negative_prompt=negative_prompt,
-        guidance_scale=guidance_scale,
-        num_inference_steps=num_inference_steps,
-        width=width,
-        height=height,
-        generator=generator,
-    ).images[0]
-
-    return image, seed
-
-
-css = """
-#col-container {
-    margin: 0 auto;
-    max-width: 640px;
-}
-"""
-
-with gr.Blocks(css=css) as demo:
-    with gr.Column(elem_id="col-container"):
-        gr.Markdown(" # Text-to-Image Gradio Template")
-
-        with gr.Row():
-            prompt = gr.Text(
-                label="Prompt",
-                show_label=False,
-                max_lines=1,
-                placeholder="Enter your prompt",
-                container=False,
-            )
-
-            run_button = gr.Button("Run", scale=0, variant="primary")
-
-        result = gr.Image(label="Result", show_label=False)
-
-        with gr.Accordion("Advanced Settings", open=False):
-            negative_prompt = gr.Text(
-                label="Negative prompt",
-                max_lines=1,
-                placeholder="Enter a negative prompt",
-                visible=False,
-            )
-
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=0,
-            )
-
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
-
-            with gr.Row():
-                width = gr.Slider(
-                    label="Width",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
-
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
-
-            with gr.Row():
-                guidance_scale = gr.Slider(
-                    label="Guidance scale",
-                    minimum=0.0,
-                    maximum=10.0,
-                    step=0.1,
-                    value=0.0,  # Replace with defaults that work for your model
-                )
-
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=50,
-                    step=1,
-                    value=2,  # Replace with defaults that work for your model
-                )
-
-        gr.Examples(examples=examples, inputs=[prompt])
-    gr.on(
-        triggers=[run_button.click, prompt.submit],
-        fn=infer,
-        inputs=[
-            prompt,
-            negative_prompt,
-            seed,
-            randomize_seed,
-            width,
-            height,
-            guidance_scale,
-            num_inference_steps,
-        ],
-        outputs=[result, seed],
+# Load model and tokenizer
+model_name = "Qwen/Qwen2.5-3B-Instruct"
+
+print("Loading tokenizer...")
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+print("Loading model...")
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype=torch.bfloat16,  # Use bfloat16 to save memory and speed up inference
+    device_map="auto",           # Automatically use GPU if available
+    trust_remote_code=True       # Required for Qwen models
+)
+
+# Define chat function
+def respond(message, history):
+    messages = [{"role": "user", "content": message}]
+    
+    # Apply chat template
+    text = tokenizer.apply_chat_template(
+        messages,
+        tokenize=False,
+        add_generation_prompt=True
     )
-
+    
+    # Tokenize input
+    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+    
+    # Generate response
+    generated_ids = model.generate(
+        **model_inputs,
+        max_new_tokens=512,
+        do_sample=True,
+        temperature=0.7,
+        top_p=0.9,
+        repetition_penalty=1.1
+    )
+    
+    # Extract only the new tokens
+    generated_ids = generated_ids[0][model_inputs.input_ids.shape[-1]:]
+    response = tokenizer.decode(generated_ids, skip_special_tokens=True)
+    
+    return response
+
+# Create Gradio chat interface
+demo = gr.ChatInterface(
+    fn=respond,
+    title="Qwen2.5-3B Chatbot",
+    description="Chat with Qwen2.5-3B-Instruct, a powerful 3-billion-parameter LLM by Alibaba Cloud.",
+    examples=[
+        "Explain quantum computing in simple terms.",
+        "Write a Python function to calculate Fibonacci numbers.",
+        "Tell me a joke about AI."
+    ],
+    retry_btn=None,
+    undo_btn=None,
+)
+
+# Launch the app
 if __name__ == "__main__":
     demo.launch()