Instructions to use second-state/functionary-small-v3.1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use second-state/functionary-small-v3.1-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf second-state/functionary-small-v3.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf second-state/functionary-small-v3.1-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf second-state/functionary-small-v3.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf second-state/functionary-small-v3.1-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf second-state/functionary-small-v3.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf second-state/functionary-small-v3.1-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf second-state/functionary-small-v3.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf second-state/functionary-small-v3.1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/second-state/functionary-small-v3.1-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use second-state/functionary-small-v3.1-GGUF with Ollama:
```
ollama run hf.co/second-state/functionary-small-v3.1-GGUF:Q4_K_M
```
Unsloth Desktop

How to use second-state/functionary-small-v3.1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf second-state/functionary-small-v3.1-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "second-state/functionary-small-v3.1-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use second-state/functionary-small-v3.1-GGUF with Docker Model Runner:
```
docker model run hf.co/second-state/functionary-small-v3.1-GGUF:Q4_K_M
```

Lemonade

How to use second-state/functionary-small-v3.1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull second-state/functionary-small-v3.1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.functionary-small-v3.1-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use second-state/functionary-small-v3.1-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf second-state/functionary-small-v3.1-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default second-state/functionary-small-v3.1-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use second-state/functionary-small-v3.1-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf second-state/functionary-small-v3.1-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "second-state/functionary-small-v3.1-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

apepkuss79 commited on Oct 15, 2024

Commit

87e955f

verified ·

1 Parent(s): 48128cf

Update README.md

Browse files

Files changed (1) hide show

README.md +110 -112

README.md CHANGED Viewed

@@ -1,112 +1,110 @@
----
-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: coming soon
-<!-- - LlamaEdge version: [v0.14.3](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.3) -->
-- 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*

+---
+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*