jtatman/functioncall-llama2-chat-q3-gguf

A gguf version of the v1 model of llama 2 function calling model in:

• fLlama-2-7b-chat.q3_K_M.gguf GGUF versions of v3 in:
• Llama-2-7b-chat-hf-function-calling-v3-Q4_0.gguf
• Llama-2-7b-chat-hf-function-calling-v3-Q_4_K_M.gguf
• Llama-2-7b-chat-hf-function-calling-v3-Q2_K.gguf

Set up like so:

[INST] You have access to the following functions. Use them if required:

[
    {
        "type": "function",
        "function": {
            "name": "get_big_stocks",
            "description": "Get the names of the largest N stocks by market cap",
            "parameters": {
                "type": "object",
                "properties": {
                    "number": {
                        "type": "integer",
                        "description": "The number of largest stocks to get the names of, e.g. 25"
                    },
                    "region": {
                        "type": "string",
                        "description": "The region to consider, can be \"US\" or \"World\"."
                    }
                },
                "required": [
                    "number"
                ]
            }
        }
    },
    {
        "type": "function",
        "function": {
            "name": "get_stock_price",
            "description": "Get the stock price of an array of stocks",
            "parameters": {
                "type": "object",
                "properties": {
                    "names": {
                        "type": "array",
                        "items": {
                            "type": "string"
                        },
                        "description": "An array of stocks"
                    }
                },
                "required": [
                    "names"
                ]
            }
        }
    }
]

[INST] Get the names of the five largest stocks in the US by market cap [/INST]

{
    "name": "get_big_stocks",
    "arguments": {
        "number": 5,
        "region": "US"
    }
}</s>

or this:

<s>[INST] <<SYS>>
You are a helpful research assistant. The following functions are available for you to fetch further data to answer user questions, if relevant:

{
    "function": "search_bing",
    "description": "Search the web for content on Bing. This allows users to search online/the internet/the web for content.",
    "arguments": [
        {
            "name": "query",
            "type": "string",
            "description": "The search query string"
        }
    ]
}

{
    "function": "search_arxiv",
    "description": "Search for research papers on ArXiv. Make use of AND, OR and NOT operators as appropriate to join terms within the query.",
    "arguments": [
        {
            "name": "query",
            "type": "string",
            "description": "The search query string"
        }
    ]
}
                

To call a function, respond - immediately and only - with a JSON object of the following format:
{
    "function": "function_name",
    "arguments": {
        "argument1": "argument_value",
        "argument2": "argument_value"
    }
}
<</SYS>>[/INST]

[INST] Find papers on high pressure batch reverse osmosis [/INST]

Good results through standard llama.cpp chat web interface - also can be used for openai proxy.

Original Creds go here:

(Trelis/Llama-2-7b-chat-hf-function-calling-v3)[https://huggingface.co/Trelis/Llama-2-7b-chat-hf-function-calling-v3]