Granite 20b Functioncalling

🚀 Granite-20B-FunctionCalling

Granite-20B-FunctionCalling is a finetuned model that introduces function calling abilities into the Granite model family, trained on seven fundamental function - calling tasks.

🚀 Quick Start

Granite-20B-FunctionCalling is a finetuned model based on IBM's granite-20b-code-instruct model. It is designed to respond to function calling related instructions.

✨ Features

• Multi - task Training: The model is trained using a multi - task training approach on seven fundamental tasks in function calling, including Nested Function Calling, Function Chaining, Parallel Functions, Function Name Detection, Parameter - Value Pair Detection, Next - Best Function, and Response Generation.
• Function Calling Abilities: It can handle various function - calling scenarios effectively.

📦 Installation

No specific installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

import json
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

device = "cuda" # or "cpu"
model_path = "ibm-granite/granite-20b-functioncalling"
tokenizer = AutoTokenizer.from_pretrained(model_path)
# drop device_map if running on CPU
model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)
model.eval()

# define the user query and list of available functions
query = "What's the current weather in New York?"
functions = [
    {
        "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"
                }
            },
            "required": ["location"]
        }
    },
    {
        "name": "get_stock_price",
        "description": "Retrieves the current stock price for a given ticker symbol. The ticker symbol must be a valid symbol for a publicly traded company on a major US stock exchange like NYSE or NASDAQ. The tool will return the latest trade price in USD. It should be used when the user asks about the current or most recent price of a specific stock. It will not provide any other information about the stock or company.",
        "parameters": {
            "type": "object",
            "properties": {
                "ticker": {
                    "type": "string",
                    "description": "The stock ticker symbol, e.g. AAPL for Apple Inc."
                }
            },
            "required": ["ticker"]
        }
    }
]


# serialize functions and define a payload to generate the input template
payload = {
    "functions_str": [json.dumps(x) for x in functions],
    "query": query,
}

instruction = tokenizer.apply_chat_template(payload, tokenize=False, add_generation_prompt=True)

# tokenize the text
input_tokens = tokenizer(instruction, return_tensors="pt").to(device)

# generate output tokens
outputs = model.generate(**input_tokens, max_new_tokens=100)

# decode output tokens into text
outputs = tokenizer.batch_decode(outputs)

# loop over the batch to print, in this example the batch size is 1
for output in outputs:
    # Each function call in the output will be preceded by the token "<function_call>" followed by a 
    # json serialized function call of the format {"name": $function_name$, "arguments" {$arg_name$: $arg_val$}}
    # In this specific case, the output will be: <function_call> {"name": "get_current_weather", "arguments": {"location": "New York"}}
    print(output)

📚 Documentation

Model Information

Intended use

The model is designed to respond to function calling related instructions.

📄 License

The model is released under the Apache 2.0 license.