update llama 3.3 tool-calling syntax (#274)

* update llama 3.3 tool-calling syntax

* Addressing review comments in typo

models/llama3_3/prompt_format.md

@@ -72,14 +72,135 @@ Here's my response
 
 ## Tool Calling Formats
 
+Here we describe how to invoke the Llama 3.3 instruction tuned model for tool-calling (also called function-calling). We recommend zero-shot function calling over built-in tools.
+
+### Zero shot function calling
+
+
+For Llama3.3 70B instruct models, we are continuing the format for zero shot function calling, introduced in llama 3.2.
+This format is designed to be more flexible and powerful than the format in 3.1.
+All available functions can be provided in the system message.
+
+Here is an example for the same,
+
+
+##### Input Prompt Format
+```
+<|begin_of_text|><|start_header_id|>system<|end_header_id|>
+
+You are an expert in composing functions. You are given a question and a set of possible functions.
+Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
+If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
+also point it out. You should only return the function call in tools call sections.
+
+If you decide to invoke any of the function(s), you MUST put it in the format of [func_name1(params_name1=params_value1, params_name2=params_value2...), func_name2(params)]
+You SHOULD NOT include any other text in the response.
+
+Here is a list of functions in JSON format that you can invoke.
+
+[
+    {
+        "name": "get_weather",
+        "description": "Get weather info for places",
+        "parameters": {
+            "type": "dict",
+            "required": [
+                "city"
+            ],
+            "properties": {
+                "city": {
+                    "type": "string",
+                    "description": "The name of the city to get the weather for"
+                },
+                "metric": {
+                    "type": "string",
+                    "description": "The metric for weather. Options are: celsius, fahrenheit",
+                    "default": "celsius"
+                }
+            }
+        }
+    }
+]<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+What is the weather in SF and Seattle?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+
+
+```
+
+##### Model Response Format
+```
+[get_weather(city='San Francisco', metric='celsius'), get_weather(city='Seattle', metric='celsius')]<|eot_id|>
+```
+
+
+##### Notes
+
+- The output supports multiple, and parallel tool calls natively
+- JSON format for defining the functions in the system prompt is similar to Llama3.1
+
+
+### Zero shot function calling with user message
+
+
+While the default is to provide all function calls in a system message, in Llama3.3 model you can also provide information for all the available tools in a user message.
+
+
+##### Input Prompt Format
+```
+<|begin_of_text|><|start_header_id|>user<|end_header_id|>
+
+Questions: Can you retrieve the details for the user with the ID 7890, who has black as their special request?
+Here is a list of functions in JSON format that you can invoke:
+[
+    {
+        "name": "get_user_info",
+        "description": "Retrieve details for a specific user by their unique identifier. Note that the provided function is in Python 3 syntax.",
+        "parameters": {
+            "type": "dict",
+            "required": [
+                "user_id"
+            ],
+            "properties": {
+                "user_id": {
+                "type": "integer",
+                "description": "The unique identifier of the user. It is used to fetch the specific user details from the database."
+            },
+            "special": {
+                "type": "string",
+                "description": "Any special information or parameters that need to be considered while fetching user details.",
+                "default": "none"
+                }
+            }
+        }
+    }
+]
+
+Should you decide to return the function call(s), put them in the format of [func1(params_name=params_value, params_name2=params_value2...), func2(params)]
+
+You SHOULD NOT include any other text in the response.<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+
+
+```
+
+##### Model Response Format
+```
+[get_user_info(user_id=7890, special='black')]<|eot_id|>
+```
+
+
+##### Notes
+
+- The tool call format for the model is the same whether your function calls are provided in the system or user message.
+- While builtin tool calls end with a <|eom_id|>, notice the <|eot_id|> for zero shot tool calls.
+
+
+### Builtin Tool Calling
 
 The three built-in tools (brave_search, wolfram_alpha, and code interpreter) can be turned on using the system prompt:
 - Brave Search: Tool call to perform web searches.
 - Wolfram Alpha: Tool call to perform complex mathematical calculations.
 - Code Interpreter: Enables the model to output python code.
 
-## Builtin Tool Calling
-
 
 Here is an example of a conversation using brave search