Update app.py

app.py

@@ -114,14 +114,14 @@ class LLMResponder:
             try:
                 self.llm_tokenizer = AutoTokenizer.from_pretrained(model_name, config=dummy_config, trust_remote_code=True)
             except Exception as e:
-                print("Error loading tokenizer from", model_name, "; using fallback tokenizer.")
-                fallback_model = "decapoda-research/llama-7b-hf"
+                print(f"Error loading tokenizer from {model_name}; using fallback tokenizer.")
+                fallback_model = "sentence-transformers/all-MiniLM-L6-v2"
                 self.llm_tokenizer = AutoTokenizer.from_pretrained(fallback_model, config=dummy_config, trust_remote_code=True)
             try:
                 self.llm_model = AutoModelForCausalLM.from_pretrained(model_name, config=dummy_config, trust_remote_code=True)
             except Exception as e:
-                print("Error loading model from", model_name, "; using fallback model.")
-                fallback_model = "decapoda-research/llama-7b-hf"
+                print(f"Error loading model from {model_name}; using fallback model.")
+                fallback_model = "sentence-transformers/all-MiniLM-L6-v2"
                 self.llm_model = AutoModelForCausalLM.from_pretrained(fallback_model, config=dummy_config, trust_remote_code=True)
             self.backend = "transformers"