Model Card for Blake-XTM Arc 3B (V1)

Model Details

Model Description

[!WARNING]
Warning: this model was finetuned on a non-instruct base model. This was an oversight, but it may impact model performance.

Chat Format

Model Usage

1. Only response:
   text

   1<|im_start|>assistant 2Hello! How may I assist you today?<|im_end|>
2. Thought process and response:
   text

   1<|im_start|>assistant 2<|think_start|>The user has greeted me with a simple message. I should think about how to respond to them. 3 4Since the user sent a simple greeting, I should reply with a greeting that matches their energy. 5 6Alright, I can reply with a message like 'Hello! How can I help you?'<|think_end|> 7 8Hello! How may I assist you today?<|im_end|>
3. Thought process and tool call:
   text

   1<|im_start|>assistant 2<|think_start|>The user has asked me to find all restaurants near Paris. Hmm... let me think this through thoroughly. 3 4I can see that I have a tool available called 'find_restaurants', which I might be able to use for this purpose. 5 6Alright, I think I should use the `find_restaurants` tool to find the restaurants near Paris. For the `city` parameter, I'll use 'Paris', and for the `country` parameter, I'll fill in `France`. 7 8Okay, I can go ahead and make the tool call now.<|think_end|> 9 10<|tool_start|>{'name': 'find_restaurants', 'arguments': {'city': 'Paris', 'country': 'France'}}<|tool_end|><|im_end|>

• Only thought process:
  text

  1You are an advanced reasoning model. 2 3You think between <|think_start|>...<|think_end|> tags. You must think if the user's request involves math or logical thinking/reasoning.
• Thought process and tool calling:
  text

  1You are an advanced reasoning model with tool-calling capabilities. 2 3You think between <|think_start|>...<|think_end|> tags. You must think if the user's request involves math, logical thinking/reasoning, or when you want to consider using a tool. 4 5# Tools 6You have access to the following tools: 7[{'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']} 8 9To call a tool, write a JSON object with the name and arguments inside <|tool_start|>...<|tool_end|>.

<|im_start|>assistant
<|think_start|>The user has asked me to find all restaurants near Paris. Hmm... let me think this through thoroughly.

I can see that I have a tool available called 'find_restaurants', which I might be able to use for this purpose.

Alright, I think I should use the `find_restaurants` tool to find the restaurants near Paris. For the `city` parameter, I'll use 'Paris', and for the `country` parameter, I'll fill in `France`.

Okay, I can go ahead and make the tool call now.<|think_end|>

<|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|>