Update app.py

app.py

@@ -57,8 +57,8 @@ class CodeLlamaTool(Tool):
             "text-generation",
             model=self.model,
             tokenizer=self.tokenizer,
-            max_new_tokens=512,
-            temperature=0.2,
+            max_new_tokens=256, # 512
+            temperature=0.0,
             truncation=True
         )
 
@@ -267,8 +267,15 @@ class VideoTranscriptionTool(Tool):
 class BasicAgent:
     def __init__(self):
         token = os.environ.get("HF_API_TOKEN")
-        model = HfApiModel(
-            temperature=0.1,
+  
+        # Initialize tokenizer
+        self.model_id = "codellama/CodeLlama-7b-Instruct-hf"
+        self.tokenizer = AutoTokenizer.from_pretrained(self.model_id, token=token)
+        
+        # Model (e.g., HfApiModel or other)
+        self.model = HfApiModel(
+            model=self.model_id,
+            temperature=0.0,
             token=token
         )
 
@@ -287,12 +294,8 @@ class BasicAgent:
 
         system_prompt = f"""
 You are my general AI assistant. Your task is to answer the question I asked.
-First, provide an explanation of your reasoning, step by step, to arrive at the answer.
-Then, return your final answer in a single line, formatted as follows: "FINAL ANSWER: [YOUR FINAL ANSWER]".
-[YOUR FINAL ANSWER] should be a number, a string, or a comma-separated list of numbers and/or strings, depending on the question.
-If the answer is a number, do not use commas or units (e.g., $, %) unless specified.
-If the answer is a string, do not use articles or abbreviations (e.g., for cities), and write digits in plain text unless specified.
-If the answer is a comma-separated list, apply the above rules for each element based on whether it is a number or a string.
+First, provide reasoning. Then return: FINAL ANSWER: [your answer].
+Answer should be a short string, number, or comma-separated list. Keep it brief.
 """
 
         self.agent = CodeAgent(