---
base_model: meetkai/functionary-small-v3.1
license: mit
model_creator: meetkai
model_name: functionary-small-v3.1
quantized_by: Second State Inc.
---

<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->

# functionary-small-v3.1-GGUF

## Original Model

[meetkai/functionary-small-v3.1](https://huggingface.co/meetkai/functionary-small-v3.1)

## Run with LlamaEdge

- LlamaEdge version: [v0.14.10](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.10) and above

- Prompt template

  - Prompt type: `functionary-31`

  - Prompt string

    ```text
    <|start_header_id|>system<|end_header_id|>

    Environment: ipython

    Cutting Knowledge Date: December 2023


    You have access to the following functions:

    Use the function 'get_current_weather' to 'Get the current weather'
    {"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"]}}


    Think very carefully before calling functions.
    If a you choose to call a function ONLY reply in the following format:
    <{start_tag}={function_name}>{parameters}{end_tag}
    where

    start_tag => `<function`
    parameters => a JSON dict with the function argument name as key and function argument value as value.
    end_tag => `</function>`

    Here is an example,
    <function=example_function_name>{"example_name": "example_value"}</function>

    Reminder:
    - If looking for real time information use relevant functions before falling back to brave_search
    - Function calls MUST follow the specified format, start with <function= and end with </function>
    - Required parameters MUST be specified
    - Only call one function at a time
    - Put the entire function call reply on one line

    <|eot_id|><|start_header_id|>user<|end_header_id|>

    What is the weather like in Beijing today?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
    ```

- Context size: `128000`

- Run as LlamaEdge service

  ```bash
  wasmedge --dir .:. --nn-preload default:GGML:AUTO:functionary-small-v3.1-Q5_K_M.gguf \
    llama-api-server.wasm \
    --model-name functionary-small-v3.1 \
    --prompt-template functionary-31 \
    --ctx-size 128000
  ```

- Run as LlamaEdge command app

  ```bash
  wasmedge --dir .:. --nn-preload default:GGML:AUTO:functionary-small-v3.1-Q5_K_M.gguf \
    llama-chat.wasm \
    --prompt-template functionary-31 \
    --ctx-size 128000
  ```

## Quantized GGUF Models

| Name | Quant method | Bits | Size | Use case |
| ---- | ---- | ---- | ---- | ----- |
| [functionary-small-v3.1-Q2_K.gguf](https://huggingface.co/second-state/functionary-small-v3.1-GGUF/blob/main/functionary-small-v3.1-Q2_K.gguf)     | Q2_K   | 2 | 3.18 GB| smallest, significant quality loss - not recommended for most purposes |
| [functionary-small-v3.1-Q3_K_L.gguf](https://huggingface.co/second-state/functionary-small-v3.1-GGUF/blob/main/functionary-small-v3.1-Q3_K_L.gguf) | Q3_K_L | 3 | 4.32 GB| small, substantial quality loss |
| [functionary-small-v3.1-Q3_K_M.gguf](https://huggingface.co/second-state/functionary-small-v3.1-GGUF/blob/main/functionary-small-v3.1-Q3_K_M.gguf) | Q3_K_M | 3 | 4.02 GB| very small, high quality loss |
| [functionary-small-v3.1-Q3_K_S.gguf](https://huggingface.co/second-state/functionary-small-v3.1-GGUF/blob/main/functionary-small-v3.1-Q3_K_S.gguf) | Q3_K_S | 3 | 3.66 GB| very small, high quality loss |
| [functionary-small-v3.1-Q4_0.gguf](https://huggingface.co/second-state/functionary-small-v3.1-GGUF/blob/main/functionary-small-v3.1-Q4_0.gguf)     | Q4_0   | 4 | 4.66 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
| [functionary-small-v3.1-Q4_K_M.gguf](https://huggingface.co/second-state/functionary-small-v3.1-GGUF/blob/main/functionary-small-v3.1-Q4_K_M.gguf) | Q4_K_M | 4 | 4.92 GB| medium, balanced quality - recommended |
| [functionary-small-v3.1-Q4_K_S.gguf](https://huggingface.co/second-state/functionary-small-v3.1-GGUF/blob/main/functionary-small-v3.1-Q4_K_S.gguf) | Q4_K_S | 4 | 4.69 GB| small, greater quality loss |
| [functionary-small-v3.1-Q5_0.gguf](https://huggingface.co/second-state/functionary-small-v3.1-GGUF/blob/main/functionary-small-v3.1-Q5_0.gguf)     | Q5_0   | 5 | 5.60 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
| [functionary-small-v3.1-Q5_K_M.gguf](https://huggingface.co/second-state/functionary-small-v3.1-GGUF/blob/main/functionary-small-v3.1-Q5_K_M.gguf) | Q5_K_M | 5 | 5.73 GB| large, very low quality loss - recommended |
| [functionary-small-v3.1-Q5_K_S.gguf](https://huggingface.co/second-state/functionary-small-v3.1-GGUF/blob/main/functionary-small-v3.1-Q5_K_S.gguf) | Q5_K_S | 5 | 5.60 GB| large, low quality loss - recommended |
| [functionary-small-v3.1-Q6_K.gguf](https://huggingface.co/second-state/functionary-small-v3.1-GGUF/blob/main/functionary-small-v3.1-Q6_K.gguf)     | Q6_K   | 6 | 6.60 GB| very large, extremely low quality loss |
| [functionary-small-v3.1-Q8_0.gguf](https://huggingface.co/second-state/functionary-small-v3.1-GGUF/blob/main/functionary-small-v3.1-Q8_0.gguf)     | Q8_0   | 8 | 8.54 GB| very large, extremely low quality loss - not recommended |
| [functionary-small-v3.1-f16.gguf](https://huggingface.co/second-state/functionary-small-v3.1-GGUF/blob/main/functionary-small-v3.1-f16.gguf)       | f16    | 16 | 16.1 GB| |

*Quantized with llama.cpp b3807*