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

Libraries

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

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="second-state/functionary-medium-v3.1-GGUF",
	filename="functionary-medium-v3.1-Q2_K.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

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

Install from brew

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

Use Docker

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

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

Unsloth Studio new

How to use second-state/functionary-medium-v3.1-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for second-state/functionary-medium-v3.1-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for second-state/functionary-medium-v3.1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for second-state/functionary-medium-v3.1-GGUF to start chatting

Pi new

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

Start the llama.cpp server

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

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/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-medium-v3.1-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use second-state/functionary-medium-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-server -hf second-state/functionary-medium-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-medium-v3.1-GGUF:Q4_K_M

Run Hermes

hermes

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

Lemonade

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

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

functionary-medium-v3.1-GGUF

Original Model

meetkai/functionary-medium-v3.1

Run with LlamaEdge

LlamaEdge version: v0.14.10 and above

Prompt template

Prompt type: functionary-31

Prompt string

<|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

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

Run as LlamaEdge command app

wasmedge --dir .:. --nn-preload default:GGML:AUTO:functionary-medium-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-medium-v3.1-Q2_K.gguf	Q2_K	2	26.4 GB	smallest, significant quality loss - not recommended for most purposes
functionary-medium-v3.1-Q3_K_L.gguf	Q3_K_L	3	37.1 GB	small, substantial quality loss
functionary-medium-v3.1-Q3_K_M.gguf	Q3_K_M	3	34.3 GB	very small, high quality loss
functionary-medium-v3.1-Q3_K_S.gguf	Q3_K_S	3	30.9 GB	very small, high quality loss
functionary-medium-v3.1-Q4_0.gguf	Q4_0	4	40.0 GB	legacy; small, very high quality loss - prefer using Q3_K_M
functionary-medium-v3.1-Q4_K_M.gguf	Q4_K_M	4	42.5 GB	medium, balanced quality - recommended
functionary-medium-v3.1-Q4_K_S.gguf	Q4_K_S	4	40.3 GB	small, greater quality loss
functionary-medium-v3.1-Q5_0.gguf	Q5_0	5	48.7 GB	legacy; medium, balanced quality - prefer using Q4_K_M
functionary-medium-v3.1-Q5_K_M.gguf	Q5_K_M	5	49.9 GB	large, very low quality loss - recommended
functionary-medium-v3.1-Q5_K_S.gguf	Q5_K_S	5	48.7 GB	large, low quality loss - recommended
functionary-medium-v3.1-Q6_K-00001-of-00002.gguf	Q6_K	6	29.8 GB	very large, extremely low quality loss
functionary-medium-v3.1-Q6_K-00002-of-00002.gguf	Q6_K	6	28.0 GB	very large, extremely low quality loss
functionary-medium-v3.1-Q8_0-00001-of-00003.gguf	Q8_0	8	29.8 GB	very large, extremely low quality loss - not recommended
functionary-medium-v3.1-Q8_0-00002-of-00003.gguf	Q8_0	8	29.8 GB	very large, extremely low quality loss - not recommended
functionary-medium-v3.1-Q8_0-00003-of-00003.gguf	Q8_0	8	15.4 GB	very large, extremely low quality loss - not recommended
functionary-medium-v3.1-f16-00001-of-00005.gguf	f16	16	30.0 GB
functionary-medium-v3.1-f16-00002-of-00005.gguf	f16	16	29.6 GB
functionary-medium-v3.1-f16-00003-of-00005.gguf	f16	16	29.9 GB
functionary-medium-v3.1-f16-00004-of-00005.gguf	f16	16	29.6 GB
functionary-medium-v3.1-f16-00005-of-00005.gguf	f16	16	22.2 GB

Quantized with llama.cpp b3807

Downloads last month: 364

GGUF

Model size

71B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for second-state/functionary-medium-v3.1-GGUF

Base model

meetkai/functionary-medium-v3.1

Quantized

(4)

this model

Collection including second-state/functionary-medium-v3.1-GGUF

Tool Use

Collection

LlamaEdge compatible quants for tool-use models. • 11 items • Updated Oct 16, 2024