Create app.py

app.py

@@ -0,0 +1,43 @@
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+model_name = "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B"
+
+print("Loading model... (this may take time)")
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+
+print("Model loaded! Start chatting.\n")
+
+chat_history = ""
+
+while True:
+    user_input = input("You: ")
+
+    if user_input.lower() in ["exit", "quit"]:
+        break
+
+    chat_history += f"User: {user_input}\nAssistant:"
+
+    inputs = tokenizer(chat_history, return_tensors="pt").to(model.device)
+
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=200,
+        temperature=0.7,
+        do_sample=True
+    )
+
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+    # Extract only latest response
+    response = response.split("Assistant:")[-1].strip()
+
+    print(f"AI: {response}\n")
+
+    chat_history += f" {response}\n"