Instructions to use haffner/Maestro1-9B-Heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use haffner/Maestro1-9B-Heretic with Transformers:

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

pipe = pipeline("image-text-to-text", model="haffner/Maestro1-9B-Heretic")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("haffner/Maestro1-9B-Heretic")
model = AutoModelForMultimodalLM.from_pretrained("haffner/Maestro1-9B-Heretic")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use haffner/Maestro1-9B-Heretic with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="haffner/Maestro1-9B-Heretic",
	filename="Maestro1-9B-heretic-BF16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use haffner/Maestro1-9B-Heretic with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf haffner/Maestro1-9B-Heretic:BF16
# Run inference directly in the terminal:
llama-cli -hf haffner/Maestro1-9B-Heretic:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf haffner/Maestro1-9B-Heretic:BF16
# Run inference directly in the terminal:
llama-cli -hf haffner/Maestro1-9B-Heretic:BF16

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 haffner/Maestro1-9B-Heretic:BF16
# Run inference directly in the terminal:
./llama-cli -hf haffner/Maestro1-9B-Heretic:BF16

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 haffner/Maestro1-9B-Heretic:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf haffner/Maestro1-9B-Heretic:BF16

Use Docker

docker model run hf.co/haffner/Maestro1-9B-Heretic:BF16

LM Studio
Jan

vLLM

How to use haffner/Maestro1-9B-Heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "haffner/Maestro1-9B-Heretic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "haffner/Maestro1-9B-Heretic",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/haffner/Maestro1-9B-Heretic:BF16

SGLang

How to use haffner/Maestro1-9B-Heretic 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 "haffner/Maestro1-9B-Heretic" \
    --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": "haffner/Maestro1-9B-Heretic",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "haffner/Maestro1-9B-Heretic" \
        --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": "haffner/Maestro1-9B-Heretic",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use haffner/Maestro1-9B-Heretic with Ollama:
```
ollama run hf.co/haffner/Maestro1-9B-Heretic:BF16
```

Unsloth Studio

How to use haffner/Maestro1-9B-Heretic 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 haffner/Maestro1-9B-Heretic 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 haffner/Maestro1-9B-Heretic to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for haffner/Maestro1-9B-Heretic to start chatting

How to use haffner/Maestro1-9B-Heretic with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf haffner/Maestro1-9B-Heretic:BF16

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": "haffner/Maestro1-9B-Heretic:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use haffner/Maestro1-9B-Heretic with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf haffner/Maestro1-9B-Heretic:BF16

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 haffner/Maestro1-9B-Heretic:BF16

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use haffner/Maestro1-9B-Heretic with Docker Model Runner:
```
docker model run hf.co/haffner/Maestro1-9B-Heretic:BF16
```

Lemonade

How to use haffner/Maestro1-9B-Heretic with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull haffner/Maestro1-9B-Heretic:BF16

Run and chat with the model

lemonade run user.Maestro1-9B-Heretic-BF16

List all available models

lemonade list

@haffner Thanks.

by vectionlabs - opened 1 day ago

Discussion

vectionlabs

1 day ago

@haffner You are the first person to create a heretic version of our models. Thank you! What did you find in our models that pushed you to make heretic variants?

haffner

Owner about 10 hours ago

I just don't want to have to deal with a model not doing what I ask it to. Any form of censorship in AI models means it's broken by design.
Will it matter for what I use them for - hardly ever, but I've had enough eye roll moments where a model deemed my requests possibly against its guidelines.

So, my computer, my rules, my responsibility. And there are enough like-minded people that I might as well share this here and save someone the trial runs.

What I found intriguing about your models is that they were trained to be short and concise, which saves valuable context. I've yet to try how they actually perform. So far I just did some test quaries after the heretic process to verify it behaves properly.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment