Flexan/Blake-XTM-Arc-T0

Model Card for Blake-XTM Arc T0

Blake-XTM Arc T0 is a 7B large language model used for text generation. It was trained as a (tool-calling) assistant. This model is a variation of Blake-XTM-Arc without reasoning.

Model Details

Model Description

Blake-XTM Arc T0 is a 7B parameter instruct LLM trained to assist and optionally call a tool. It only supports using one tool per assistant message (no parallel tool calling). The model was LoRA fine-tuned with CatNyanster-7B as base model, which was fine-tuned on Mistral-7B.

Chat Format

Blake-XTM Arc T0 uses the ChatML format, e.g.:

<|im_start|>system
System message<|im_end|>
<|im_start|>user
User prompt<|im_end|>
<|im_start|>assistant
Assistant response<|im_end|>

Model Usage

The assistant response can have the following two formats (the contents are examples and were not generated from the model):

1. Response:

   <|im_start|>assistant
   Hello! How may I assist you today?<|im_end|>
   

2. Tool call:

   <|im_start|>assistant
   <|tool_start|>{'name': 'find_restaurants', 'arguments': {'city': 'Paris', 'country': 'France'}}<|tool_end|><|im_end|>
   

We recommend using the following system prompts for your situation:

• Only thought process:

  You are an advanced AI model.
  

• Thought process and tool calling:

  You are an advanced AI model with tool-calling capabilities.
  
  If the user asks something and it requires a tool then you should call the tool with the arguments.
  
  # Tools
  You have access to the following tools:
  [{'type': 'function', 'function': {'name': 'convert_currency', 'description': 'Convert currency from one type to another', 'parameters': {'type': 'object', 'properties': {'amount': {'type': 'number', 'description': 'The amount to be converted'}, 'from_currency': {'type': 'string', 'description': 'The currency to convert from'}, 'to_currency': {'type': 'string', 'description': 'The currency to convert to'}}, 'required': ['amount', 'from_currency', 'to_currency']}}}, {'type': 'function', 'function': {'name': 'get_random_joke', 'description': 'Get a random joke', 'parameters': {'type': 'object', 'properties': {}, 'required': []}}}] <\/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']}
  
  To call a tool, write a JSON object with the name and arguments inside <|tool_start|>...<|tool_end|>.
  

For responding with a tool response, you can send a message as the tool user:

<|im_start|>assistant
<|tool_start|>{'name': 'find_restaurants', 'arguments': {'city': 'Paris', 'country': 'France'}}<|tool_end|><|im_end|>
<|im_start|>tool
{'restaurants': [{'name': 'A Restaurant Name', 'rating': 4.5}]}<|im_end|>