Create app.py

app.py

@@ -0,0 +1,35 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+# Load model and tokenizer
+model_name = "deepseek-ai/DeepSeek-V3-0324"
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto", trust_remote_code=True)
+
+# Function to generate response
+def chat_with_bot(user_input, history):
+    history = history or []
+    prompt = ""
+    for i, (user, bot) in enumerate(history):
+        prompt += f"<|user|>\n{user}\n<|assistant|>\n{bot}\n"
+    prompt += f"<|user|>\n{user_input}\n<|assistant|>\n"
+
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    outputs = model.generate(**inputs, max_new_tokens=512, do_sample=True, temperature=0.7, top_p=0.9, eos_token_id=tokenizer.eos_token_id)
+
+    decoded_output = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    response = decoded_output.split("<|assistant|>\n")[-1].strip()
+    
+    history.append((user_input, response))
+    return response, history
+
+# Gradio UI
+chatbot_ui = gr.ChatInterface(
+    fn=chat_with_bot,
+    title="DeepSeek Chatbot",
+    theme="soft",
+    examples=["Tell me a joke", "What's the capital of France?", "Explain quantum computing simply."]
+)
+
+chatbot_ui.launch()