Update app.py

app.py

@@ -1,63 +1,79 @@
 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("Qwen/Qwen1.5-0.5B")
-
-
-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)",
-        ),
-    ],
+from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
+import torch
+import os
+
+# Model loading with memory optimization
+cache_dir = "./model_cache"
+os.makedirs(cache_dir, exist_ok=True)
+
+model_name = "Qwen/Qwen1.5-0.5B"
+
+tokenizer = AutoTokenizer.from_pretrained(
+    model_name,
+    cache_dir=cache_dir,
+    trust_remote_code=True
 )
 
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype=torch.float16,
+    cache_dir=cache_dir,
+    trust_remote_code=True
+).to("cuda" if torch.cuda.is_available() else "cpu")
+
+# Generation configuration
+generation_config = GenerationConfig.from_pretrained(model_name)
+
+def generate_text(prompt, temperature, max_new_tokens):
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    
+    with torch.inference_mode():
+        outputs = model.generate(
+            **inputs,
+            max_new_tokens=int(max_new_tokens),
+            temperature=float(temperature),
+            pad_token_id=tokenizer.eos_token_id
+        )
+    
+    response = tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True)
+    return response.strip()
+
+# Gradio interface
+with gr.Blocks(theme="soft", title="Qwen Text Generation") as demo:
+    gr.Markdown("# 🧠 Qwen1.5-0.5B Text Generation")
+    
+    with gr.Row():
+        with gr.Column():
+            prompt = gr.Textbox(
+                label="Input Prompt",
+                placeholder="Enter your instruction or question...",
+                lines=5
+            )
+            temperature = gr.Slider(
+                minimum=0.1, maximum=2.0, value=0.7, step=0.1,
+                label="Creativity (Temperature)"
+            )
+            max_new_tokens = gr.Slider(
+                minimum=50, maximum=1000, value=200, step=50,
+                label="Max New Tokens"
+            )
+            generate_btn = gr.Button("✨ Generate", variant="primary")
+        
+        with gr.Column():
+            output = gr.Textbox(label="Model Response", lines=10, interactive=False)
+    
+    generate_btn.click(
+        fn=generate_text,
+        inputs=[prompt, temperature, max_new_tokens],
+        outputs=output
+    )
+    
+    gr.Markdown("""
+    ### ℹ️ Tips
+    - Higher **temperature** = more creative/chaotic responses
+    - Lower **temperature** = more deterministic answers
+    - Adjust **max tokens** for longer/shorter outputs
+    """)
 
-if __name__ == "__main__":
-    demo.launch()
+demo.launch()