Update app.py

app.py

@@ -42,7 +42,7 @@ def cache_answer(question_id: str, answer: str):
 
 
 # --- Model Setup ---
-MODEL_NAME = 'Qwen/Qwen2.5-3B-Instruct'  # 'meta-llama/Llama-3.2-3B-Instruct'
+#MODEL_NAME = 'Qwen/Qwen2.5-3B-Instruct'  # 'meta-llama/Llama-3.2-3B-Instruct'
 
 
 # "Qwen/Qwen2.5-VL-3B-Instruct"#'meta-llama/Llama-2-7b-hf'#'meta-llama/Llama-3.1-8B-Instruct'#'TinyLlama/TinyLlama-1.1B-Chat-v1.0'#'mistralai/Mistral-7B-Instruct-v0.2'#'microsoft/DialoGPT-small'# 'EleutherAI/gpt-neo-2.7B'#'distilbert/distilgpt2'#'deepseek-ai/DeepSeek-R1-Distill-Qwen-7B'#'mistralai/Mistral-7B-Instruct-v0.2'
@@ -70,8 +70,8 @@ def load_model(model_name):
 
 # Load the model and tokenizer locally
 # model, tokenizer = load_model()
-model = HfApiModel()  # model_id=MODEL_NAME, max_tokens=512)
-model_id = "Qwen/Qwen2-72B-Instruct-GPTQ-Int4"  # "microsoft/phi-2"# not working out of the box"google/gemma-2-2b-it" #toobig"Qwen/Qwen1.5-7B-Chat"#working but stupid: "meta-llama/Llama-3.2-3B-Instruct"
+
+model_id = "meta-llama/Llama-3.1-8B-Instruct"  # "microsoft/phi-2"# not working out of the box"google/gemma-2-2b-it" #toobig"Qwen/Qwen1.5-7B-Chat"#working but stupid: "meta-llama/Llama-3.2-3B-Instruct"
 model = HfApiModel(model_id)
 #from smolagents import TransformersModel
 # model = TransformersModel(