Instructions to use MaziyarPanahi/firefunction-v2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MaziyarPanahi/firefunction-v2-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="MaziyarPanahi/firefunction-v2-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("MaziyarPanahi/firefunction-v2-GGUF", dtype="auto")

llama-cpp-python

How to use MaziyarPanahi/firefunction-v2-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="MaziyarPanahi/firefunction-v2-GGUF",
	filename="firefunction-v2.IQ1_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use MaziyarPanahi/firefunction-v2-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf MaziyarPanahi/firefunction-v2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf MaziyarPanahi/firefunction-v2-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 MaziyarPanahi/firefunction-v2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf MaziyarPanahi/firefunction-v2-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 MaziyarPanahi/firefunction-v2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf MaziyarPanahi/firefunction-v2-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 MaziyarPanahi/firefunction-v2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf MaziyarPanahi/firefunction-v2-GGUF:Q4_K_M

Use Docker

docker model run hf.co/MaziyarPanahi/firefunction-v2-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use MaziyarPanahi/firefunction-v2-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MaziyarPanahi/firefunction-v2-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MaziyarPanahi/firefunction-v2-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MaziyarPanahi/firefunction-v2-GGUF:Q4_K_M

SGLang

How to use MaziyarPanahi/firefunction-v2-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "MaziyarPanahi/firefunction-v2-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MaziyarPanahi/firefunction-v2-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "MaziyarPanahi/firefunction-v2-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MaziyarPanahi/firefunction-v2-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use MaziyarPanahi/firefunction-v2-GGUF with Ollama:
```
ollama run hf.co/MaziyarPanahi/firefunction-v2-GGUF:Q4_K_M
```

Unsloth Studio new

How to use MaziyarPanahi/firefunction-v2-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 MaziyarPanahi/firefunction-v2-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 MaziyarPanahi/firefunction-v2-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for MaziyarPanahi/firefunction-v2-GGUF to start chatting

Pi new

How to use MaziyarPanahi/firefunction-v2-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf MaziyarPanahi/firefunction-v2-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": "MaziyarPanahi/firefunction-v2-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use MaziyarPanahi/firefunction-v2-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 MaziyarPanahi/firefunction-v2-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 MaziyarPanahi/firefunction-v2-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use MaziyarPanahi/firefunction-v2-GGUF with Docker Model Runner:
```
docker model run hf.co/MaziyarPanahi/firefunction-v2-GGUF:Q4_K_M
```

Lemonade

How to use MaziyarPanahi/firefunction-v2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull MaziyarPanahi/firefunction-v2-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.firefunction-v2-GGUF-Q4_K_M

List all available models

lemonade list

[WIP] Upload folder using huggingface_hub (multi-commit d05be761b0e3983b92f1ca0ef12e4839c645fcfc270db6e3f5163be8cbabb4da)

by MaziyarPanahi - opened Jun 19, 2024

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

+60

-0

@@ -46,3 +46,18 @@ firefunction-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 firefunction-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
 firefunction-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 firefunction-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text

 firefunction-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
 firefunction-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 firefunction-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+firefunction-v2.Q6_K-00001-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+firefunction-v2.Q6_K-00002-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+firefunction-v2.Q6_K-00003-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+firefunction-v2.Q6_K-00004-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+firefunction-v2.Q6_K-00005-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+firefunction-v2.Q6_K-00006-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+firefunction-v2.Q8_0-00001-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+firefunction-v2.Q8_0-00002-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+firefunction-v2.Q8_0-00003-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+firefunction-v2.Q8_0-00004-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+firefunction-v2.Q8_0-00005-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+firefunction-v2.Q8_0-00006-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+firefunction-v2.fp16-00001-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+firefunction-v2.fp16-00002-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+firefunction-v2.fp16-00003-of-00006.gguf filter=lfs diff=lfs merge=lfs -text

+version https://git-lfs.github.com/spec/v1
+oid sha256:7dfc30eda57657ec0bfdc6cb9e5adfe30cf999879a4e4a04d39432bbb1122b25
+size 10697127936

+version https://git-lfs.github.com/spec/v1
+oid sha256:b61974da8800750cac3ada62f3ab0f8b2f1949a63122f34ff12437513e2541bd
+size 10212744800

+version https://git-lfs.github.com/spec/v1
+oid sha256:89eb0ff0d57c92b91aeff11f960411962733a969fbeba039b38d66a6999cf430
+size 10020101728

+version https://git-lfs.github.com/spec/v1
+oid sha256:99a14e468adf90d398cdc12b021b137922d5588826219b11141f0f969f33a198
+size 9889324640

+version https://git-lfs.github.com/spec/v1
+oid sha256:3a27231dbd0b55fd030149400a2b02c50bde75de71204cf737f17b062d53eaf5
+size 7179523008

+version https://git-lfs.github.com/spec/v1
+oid sha256:98f3c4f7c128e05872147c5d9161d3d2b60803c7576c7d3b2dcbd01316229eb0
+size 13852735488

+version https://git-lfs.github.com/spec/v1
+oid sha256:bc633b0ae586f2ea7357448ff8faee50e679e8bfcc57be2f14bd24dce9b7790a
+size 13227662944

+version https://git-lfs.github.com/spec/v1
+oid sha256:f096700f294a77a2a7ffe629118672a7033ba4d263fc0ce51ce27e6b97fe031f
+size 12978134624

+version https://git-lfs.github.com/spec/v1
+oid sha256:158e076f70750bffe912ca97b2b82e887e252e628ead964e8614883de988a8d8
+size 12808756832

+version https://git-lfs.github.com/spec/v1
+oid sha256:f26e4312ce97f5df85fe2530d7c08bd1a2a9fbdc42e74d281aff38694faea982
+size 9299006400

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:68ac5094089afcc815ea8c31f84332f1a31f0141c6ae0733b9d3d38d335b979b
+size 26067990304

+version https://git-lfs.github.com/spec/v1
+oid sha256:dd55a5a723638b4777df02aab89a75dc3de16d4476f3a7f8d5cc61e43b029e5e
+size 24898313824

+version https://git-lfs.github.com/spec/v1
+oid sha256:ba365b442d939f7880cc809d3a2ae9dd9482843d3ad564376f8269c7ff0f1230
+size 24428584544