random

app.py

@@ -4,12 +4,14 @@ import torch
 
 model_id = "ytu-ce-cosmos/Turkish-Llama-8b-DPO-v0.1"
 
+print("Model loading started")
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
     torch_dtype=torch.bfloat16,
     device_map="auto",
 )
+print("Model loading completed")
 
 # bu mesaj değiştirilebilir ve chatbotun başlangıç mesajı olarak kullanılabilir
 initial_message = [
@@ -18,6 +20,7 @@ initial_message = [
 ]
 
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+print("Selected device:", device)
 
 app = FastAPI()
 
@@ -29,11 +32,13 @@ def home():
 
 @app.get('/ask')
 def ask(prompt: str):
-
+    print("Device of the model:", model.device)
     messages = initial_message.copy()
     messages.append({"role": "user",
                      "content": f"{prompt}"})
 
+    print("Messages:", messages)
+    print("Tokenizer process started")
     input_ids = tokenizer.apply_chat_template(
         messages,
         add_generation_prompt=True,
@@ -44,6 +49,8 @@ def ask(prompt: str):
         tokenizer.eos_token_id,
         tokenizer.convert_tokens_to_ids("<|eot_id|>")
     ]
+    print("Tokenizer process completed")
+
     print("Model process started")
     outputs = model.generate(
         input_ids,