Update app.py

app.py

@@ -1,5 +1,5 @@
 import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 
 model_id = "deepseek-ai/deepseek-coder-1.3b-instruct"
@@ -7,15 +7,20 @@ model_id = "deepseek-ai/deepseek-coder-1.3b-instruct"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
-    device_map="auto",
     torch_dtype=torch.float16,
+    device_map="auto",
     trust_remote_code=True
 )
 
 def chat(prompt):
     inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
     outputs = model.generate(**inputs, max_new_tokens=256, do_sample=True)
-    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    return response
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-gr.Interface(fn=chat, inputs="text", outputs="text", title="DeepSeek Coder 6.7B Chatbot").launch()
+gr.Interface(
+    fn=chat,
+    inputs="text",
+    outputs="text",
+    title="DeepSeek Coder 1.3B",
+    description="Free coding assistant running on Hugging Face CPU"
+).launch()