Llama 3 Groq 70B Tool Use

🚀 Llama-3-70B-Tool-Use

This is the 70B parameter version of the Llama 3 Groq Tool Use model, specifically crafted for advanced tool use and function calling tasks. It offers enhanced capabilities in scenarios involving API interactions, structured data manipulation, and complex tool utilization.

🚀 Quick Start

This model is designed for research and development in tool use and function calling scenarios. It shines in tasks related to API interactions, structured data manipulation, and complex tool use. However, users should take note of the following:

• For general knowledge or open - ended tasks, a general - purpose language model may be a better choice.
• The model might still generate inaccurate or biased content in certain situations.
• Users are accountable for implementing appropriate safety measures for their specific use case.

Note that the model is quite sensitive to the temperature and top_p sampling configuration. Start at temperature = 0.5, top_p = 0.65 and adjust as necessary.

✨ Features

• Specifically designed for advanced tool use and function calling tasks.
• Achieves a 90.76% overall accuracy on the Berkeley Function Calling Leaderboard (BFCL), leading among all open - source 70B LLMs.
• Capable of handling API interactions, structured data manipulation, and complex tool use.

📦 Installation

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

💻 Usage Examples

Basic Usage

# Text prompt example
# We'd like to give a special shoutout to [@NousResearch](https://x.com/NousResearch) for pushing open source tool use forward with their public & open exploration of tool use in LLMs.

<|start_header_id|>system<|end_header_id|>

You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
<tool_call>
{"name": <function-name>,"arguments": <args-dict>}
</tool_call>

Here are the available tools:
<tools> {
    "name": "get_current_weather",
    "description": "Get the current weather in a given location",
    "parameters": {
        "properties": {
            "location": {
                "description": "The city and state, e.g. San Francisco, CA",
                "type": "string"
            },
            "unit": {
                "enum": [
                    "celsius",
                    "fahrenheit"
                ],
                "type": "string"
            }
        },
        "required": [
            "location"
        ],
        "type": "object"
    }
} </tools><|eot_id|><|start_header_id|>user<|end_header_id|>

What is the weather like in San Francisco?<|eot_id|><|start_header_id|>assistant<|end_header_id|>

<tool_call>
{"id":"call_deok","name":"get_current_weather","arguments":{"location":"San Francisco","unit":"celsius"}}
</tool_call><|eot_id|><|start_header_id|>tool<|end_header_id|>

<tool_response>
{"id":"call_deok","result":{"temperature":"72","unit":"celsius"}}
</tool_response><|eot_id|><|start_header_id|>assistant<|end_header_id|>

Advanced Usage

There is no advanced usage example in the original document, so this part is not provided.

📚 Documentation

Model Details

Performance

• Berkeley Function Calling Leaderboard (BFCL) Score: 90.76% overall accuracy. This score represents the best performance among all open - source 70B LLMs on the BFCL.

Ethical Considerations

While fine - tuned for tool use, this model inherits the ethical considerations of the base Llama 3 model. Use it responsibly and implement additional safeguards as needed for your application.

Availability

The model is available through:

• Groq API console
• Hugging Face

For full details on responsible use, ethical considerations, and latest benchmarks, please refer to the official Llama 3 documentation and the Groq model card.

📄 License

The model is licensed under the Meta Llama 3 Community License.