Create app.py

app.py

@@ -0,0 +1,34 @@
+import gradio as gr
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# Model name
+model_name = "deepseek-ai/DeepSeek-R1"
+
+# Load tokenizer
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+
+# Load model with quantization
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    trust_remote_code=True
+).to("cuda" if torch.cuda.is_available() else "cpu")
+
+# Define the text generation function
+def generate_response(prompt):
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    with torch.no_grad():
+        output = model.generate(**inputs, max_length=150)
+    return tokenizer.decode(output[0], skip_special_tokens=True)
+
+# Set up Gradio UI
+interface = gr.Interface(
+    fn=generate_response,
+    inputs=gr.Textbox(label="Enter your prompt"),
+    outputs=gr.Textbox(label="AI Response"),
+    title="DeepSeek-R1 Chatbot",
+    description="Enter a prompt and receive a response from DeepSeek-R1."
+)
+
+# Launch the app
+interface.launch()