Update app.py

app.py

@@ -77,7 +77,7 @@ LLAMA_MAX_MAX_NEW_TOKENS = 512
 LLAMA_DEFAULT_MAX_NEW_TOKENS = 512
 LLAMA_MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "1024"))
 llama_device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
-llama_model_id = "meta-llama/Llama-3.2-3B-Instruct"
+llama_model_id = "meta-llama/Llama-3.2-1B-Instruct"
 llama_tokenizer = AutoTokenizer.from_pretrained(llama_model_id)
 llama_model = AutoModelForCausalLM.from_pretrained(
     llama_model_id,
@@ -135,7 +135,7 @@ Given the following issue description:
 ---
 {issue_text}
 ---
-Explain why this issue might be classified as a **{quality_name}** issue. Provide a concise explanation, relating it back to the issue description. Keep the explanation short and concise. Do not repeat the prompt or include any preamble in your response - just provide the explanation directly.
+Providing short explanation why this issue might be classified as a **{quality_name}** issue.
 """
     try:
         explanation = llama_generate(prompt)