changing single quotes in json objects to double quotes

README.md

@@ -108,9 +108,9 @@ Our model was trained on specific system prompts and structures for Function Cal
 You should use the system role with this message, followed by a function signature json as this example shows here.
 ```
 <|im_start|>system
-You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> {'type': 'function', 'function': {'name': 'get_stock_fundamentals', 'description': 'get_stock_fundamentals(symbol: str) -> dict - Get fundamental data for a given stock symbol using yfinance API.\n\n    Args:\n    symbol (str): The stock symbol.\n\n    Returns:\n    dict: A dictionary containing fundamental data.', 'parameters': {'type': 'object', 'properties': {'symbol': {'type': 'string'}}, 'required': ['symbol']}}}  </tools> Use the following pydantic model json schema for each tool call you will make: {'title': 'FunctionCall', 'type': 'object', 'properties': {'arguments': {'title': 'Arguments', 'type': 'object'}, 'name': {'title': 'Name', 'type': 'string'}}, 'required': ['arguments', 'name']} For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
+You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> {"type": "function", "function": {"name": "get_stock_fundamentals", "description": "get_stock_fundamentals(symbol: str) -> dict - Get fundamental data for a given stock symbol using yfinance API.\\n\\n    Args:\\n        symbol (str): The stock symbol.\\n\\n    Returns:\\n        dict: A dictionary containing fundamental data.\\n            Keys:\\n                - \'symbol\': The stock symbol.\\n                - \'company_name\': The long name of the company.\\n                - \'sector\': The sector to which the company belongs.\\n                - \'industry\': The industry to which the company belongs.\\n                - \'market_cap\': The market capitalization of the company.\\n                - \'pe_ratio\': The forward price-to-earnings ratio.\\n                - \'pb_ratio\': The price-to-book ratio.\\n                - \'dividend_yield\': The dividend yield.\\n                - \'eps\': The trailing earnings per share.\\n                - \'beta\': The beta value of the stock.\\n                - \'52_week_high\': The 52-week high price of the stock.\\n                - \'52_week_low\': The 52-week low price of the stock.", "parameters": {"type": "object", "properties": {"symbol": {"type": "string"}}, "required": ["symbol"]}}}  </tools> Use the following pydantic model json schema for each tool call you will make: {"properties": {"arguments": {"title": "Arguments", "type": "object"}, "name": {"title": "Name", "type": "string"}}, "required": ["arguments", "name"], "title": "FunctionCall", "type": "object"} For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
 <tool_call>
-{'arguments': <args-dict>, 'name': <function-name>}
+{"arguments": <args-dict>, "name": <function-name>}
 </tool_call><|im_end|>
 ```
 
@@ -124,7 +124,7 @@ The model will then generate a tool call, which your inference code must parse,
 ```
 <|im_start|>assistant
 <tool_call>
-{'arguments': {'symbol': 'TSLA'}, 'name': 'get_stock_fundamentals'}
+{"arguments": {"symbol": "TSLA"}, "name": "get_stock_fundamentals"}
 </tool_call><|im_end|>
 ```