Update app.py

app.py

@@ -1,69 +1,164 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    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(token=hf_token.token, model="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
+#!/usr/bin/env python3
+"""
+Gradient.com এ Lychee-GPT-9B চালানোর জন্য script
+Gradient Notebook এ এটা run করুন
+"""
 
-    messages.extend(history)
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import gradio as gr
+import os
 
-    messages.append({"role": "user", "content": message})
+print("🚀 Installing dependencies...")
+os.system("pip install -q torch transformers gradio accelerate safetensors")
 
-    response = ""
+print("📥 Loading Lychee-GPT-9B model...")
+print("⏱️ এটা 5-10 মিনিট লাগতে পারে...")
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
+MODEL_ID = "mx-llms/Lychee-GPT-9B"
 
-        response += token
-        yield response
+try:
+    # Load tokenizer
+    tokenizer = AutoTokenizer.from_pretrained(
+        MODEL_ID, 
+        trust_remote_code=True
+    )
+    
+    # Load model
+    model = AutoModelForCausalLM.from_pretrained(
+        MODEL_ID,
+        torch_dtype=torch.float32,
+        device_map="auto",  # Gradient automatically optimizes
+        trust_remote_code=True,
+    )
+    
+    model.eval()
+    print("✅ Model loaded successfully!")
+    
+except Exception as e:
+    print(f"❌ Error loading model: {e}")
+    model = None
+    tokenizer = None
 
+def generate_text(prompt, max_length=256, temperature=0.7, top_p=0.9):
+    """Generate text using Lychee-GPT-9B"""
+    if model is None or tokenizer is None:
+        return "❌ Model failed to load"
+    
+    try:
+        inputs = tokenizer(prompt, return_tensors="pt")
+        
+        with torch.no_grad():
+            output = model.generate(
+                inputs["input_ids"],
+                max_new_tokens=int(max_length),
+                temperature=float(temperature),
+                top_p=float(top_p),
+                do_sample=True,
+                pad_token_id=tokenizer.eos_token_id,
+            )
+        
+        response = tokenizer.decode(output[0], skip_special_tokens=True)
+        
+        if prompt in response:
+            response = response.replace(prompt, "", 1).strip()
+        
+        return response if response else "No response generated"
+        
+    except Exception as e:
+        return f"❌ Error: {str(e)}"
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = 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)",
-        ),
-    ],
-)
+# Create Gradio interface
+print("\n🎨 Creating Gradio interface...")
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+with gr.Blocks(title="Lychee-GPT-9B", theme=gr.themes.Soft()) as demo:
+    gr.Markdown("""
+    # 🎉 Lychee-GPT-9B Demo
+    
+    আপনার নিজস্ব LLM Model - Gradient এ চলছে!
+    
+    ⏱️ **প্রথম response একটু slow হতে পারে (model warming up)**
+    """)
+    
+    with gr.Row():
+        with gr.Column(scale=1):
+            prompt = gr.Textbox(
+                label="প্রশ্ন/Prompt",
+                placeholder="কিছু লিখুন...",
+                lines=4,
+                info="আপনার প্রশ্ন বা prompt দিন"
+            )
+            
+            with gr.Row():
+                max_len = gr.Slider(
+                    label="Max Length",
+                    minimum=10,
+                    maximum=512,
+                    value=256,
+                    step=10,
+                )
+            
+            with gr.Row():
+                temp = gr.Slider(
+                    label="Temperature",
+                    minimum=0.0,
+                    maximum=1.0,
+                    value=0.7,
+                    step=0.1,
+                )
+                
+                top_p = gr.Slider(
+                    label="Top P",
+                    minimum=0.0,
+                    maximum=1.0,
+                    value=0.9,
+                    step=0.05,
+                )
+            
+            submit_btn = gr.Button("🚀 Generate", variant="primary", size="lg")
+        
+        with gr.Column(scale=1):
+            output = gr.Textbox(
+                label="Response",
+                lines=10,
+                interactive=False,
+            )
+    
+    # Examples
+    gr.Examples(
+        examples=[
+            ["বাংলা ভাষা সম্পর্কে বলুন"],
+            ["পাইথন প্রোগ্রামিং কি?"],
+            ["একটি সংক্ষিপ্ত গল্প বলুন"],
+            ["কৃত্রিম বুদ্ধিমত্তা কি?"],
+        ],
+        inputs=prompt,
+        label="উদাহরণ প্রশ্ন"
+    )
+    
+    # Connect button
+    submit_btn.click(
+        fn=generate_text,
+        inputs=[prompt, max_len, temp, top_p],
+        outputs=output,
+    )
+    
+    # Allow Enter key
+    prompt.submit(
+        fn=generate_text,
+        inputs=[prompt, max_len, temp, top_p],
+        outputs=output,
+    )
 
+print("\n🌐 Launching Gradio interface...")
+print("=" * 50)
+print("Space URL will appear below 👇")
+print("=" * 50)
 
-if __name__ == "__main__":
-    demo.launch()
+# Launch
+demo.launch(
+    server_name="0.0.0.0",
+    server_port=7860,
+    share=True,
+    show_error=True,
+)