Add tool_format parameter to rewrite templates for different function call formats.

[mMrBun]

What does this PR do?

Added the tool_format parameter to rewrite templates for different function call formats.

Test command

GLM-4

• hf_engine:

python src/api.py --model_name_or_path GLM-4-9B --template glm4 --tool_format glm4

• vllm_engine

python src/api.py --model_name_or_path GLM-4-9B --template glm4 --infer_backend vllm --tool_format glm4

request code

import json
from openai import OpenAI

base_url = "http://127.0.0.1:8000/v1/"
client = OpenAI(api_key="-1", base_url=base_url)


def function_chat():
  messages = [{"role": "user", "content": "What's the weather like in Tokyo use celsius"}]
  tools = [
      {
          "type": "function",
          "function": {
              "name": "get_current_weather",
              "description": "Get the current weather",
              "parameters": {
                  "type": "object",
                  "properties": {
                      "location": {
                          "type": "string",
                          "description": "The city and state, e.g. San Francisco, CA",
                      },
                      "format": {
                          "type": "string",
                          "enum": ["celsius", "fahrenheit"],
                          "description": "The temperature unit to use. Infer this from the users location.",
                      },
                  },
                  "required": ["location", "format"],
              },
          }
      },
      {
          "type": "function",
          "function": {
              "name": "calculate_gpa",
              "description": "Calculate the Grade Point Average (GPA) based on grades and credit hours",
              "parameters": {
                  "type": "object",
                  "properties": {
                      "grades": {"type": "array", "items": {"type": "string"}, "description": "The grades"},
                      "hours": {"type": "array", "items": {"type": "integer"}, "description": "The credit hours"},
                  },
                  "required": ["grades", "hours"],
              },
          },
      }
  ]

  response = client.chat.completions.create(
      model="glm-4",
      messages=messages,
      tools=tools,
      stream=False,
  )
  response_message = response.choices[0].message
  tool_calls = response_message.tool_calls
  if tool_calls:
      for tool_call in tool_calls:
          tool_name = tool_call.function.name
          messages.append(response_message)
          function_response = {
              "temperature": "25°C",
              "weather": "sunny",
              "location": "Tokyo",
          }
          messages.append(
              {
                  "tool_call_id": tool_call.id,
                  "role": "tool",
                  "name": tool_name,
                  "content": json.dumps(function_response, ensure_ascii=False, indent=2),
              }
          )
      second_response = client.chat.completions.create(
          model="gpt-4o",
          messages=messages
      )
      print(second_response.choices[0].message.content)


if __name__ == "__main__":
  function_chat()

Before submitting

• Did you read the contributor guideline?
• Did you write any new necessary tests?

[hiyouga]

LGTM