Update app.py

app.py

@@ -18,6 +18,43 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 from langchain.llms.huggingface_pipeline import HuggingFacePipeline
 from huggingface_hub import login
 
+#### Model Testing ###########
+print(f"-- Model test started")
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "Qwen/Qwen2.5-0.5B-Instruct"
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+prompt = "Give me a short introduction to large language model."
+messages = [
+    {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+print(f"-- Model Invoking")
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=512
+)
+generated_ids = [
+    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+]
+
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+print(f"-- Model testresponse{model_inputs}")
+
+##########################
+
 
 # Load the model and tokenizer
 # model_name = "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"