Instructions to use Dev4285/MiniArt-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Dev4285/MiniArt-1.0 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 Dev4285/MiniArt-1.0:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Dev4285/MiniArt-1.0:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Dev4285/MiniArt-1.0:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Dev4285/MiniArt-1.0: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 Dev4285/MiniArt-1.0:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Dev4285/MiniArt-1.0: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 Dev4285/MiniArt-1.0:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Dev4285/MiniArt-1.0:Q4_K_M

Use Docker

docker model run hf.co/Dev4285/MiniArt-1.0:Q4_K_M

LM Studio
Jan

vLLM

How to use Dev4285/MiniArt-1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Dev4285/MiniArt-1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Dev4285/MiniArt-1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Dev4285/MiniArt-1.0:Q4_K_M

Ollama
How to use Dev4285/MiniArt-1.0 with Ollama:
```
ollama run hf.co/Dev4285/MiniArt-1.0:Q4_K_M
```

Unsloth Studio

How to use Dev4285/MiniArt-1.0 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 Dev4285/MiniArt-1.0 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 Dev4285/MiniArt-1.0 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Dev4285/MiniArt-1.0 to start chatting

How to use Dev4285/MiniArt-1.0 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Dev4285/MiniArt-1.0: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": "Dev4285/MiniArt-1.0:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use Dev4285/MiniArt-1.0 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Dev4285/MiniArt-1.0: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 "Dev4285/MiniArt-1.0: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"

Docker Model Runner
How to use Dev4285/MiniArt-1.0 with Docker Model Runner:
```
docker model run hf.co/Dev4285/MiniArt-1.0:Q4_K_M
```

Lemonade

How to use Dev4285/MiniArt-1.0 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Dev4285/MiniArt-1.0:Q4_K_M

Run and chat with the model

lemonade run user.MiniArt-1.0-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Dev4285/MiniArt-1.0 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Dev4285/MiniArt-1.0: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 Dev4285/MiniArt-1.0:Q4_K_M

Run Hermes

hermes

Atomic Chat

Dev4285 commited on 14 days ago

Commit

da770fe

verified ·

1 Parent(s): 60deb8b

Update model base to Qwen2.5-0.5B with baked MiniArt internal metadata and system identity

Browse files

Files changed (4) hide show

MiniArt-1.0-Q4_K_M.gguf +2 -2
Modelfile +4 -2
README.md +26 -19
config.json +3 -2

MiniArt-1.0-Q4_K_M.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b8539cc909975c87831fb47b4ea24cac6e4633d9d233c58cc349d59c100f71a
-size 270590880

 version https://git-lfs.github.com/spec/v1
+oid sha256:863d763af52cbe8f62cbc1facde3a0b7935e718be30735553191495bfb42da93
+size 491400032

Modelfile CHANGED Viewed

@@ -7,8 +7,10 @@ TEMPLATE """{{ if .System }}<|im_start|>system
 {{ end }}<|im_start|>assistant
 """
-PARAMETER temperature 0.8
-PARAMETER top_p 0.95
 PARAMETER repeat_penalty 1.1
 PARAMETER num_ctx 2048
 PARAMETER stop "<|im_start|>"

 {{ end }}<|im_start|>assistant
 """
+SYSTEM """You are Mini Art by an Indian Lab named OSAMA INC labs"""
+PARAMETER temperature 0.7
+PARAMETER top_p 0.9
 PARAMETER repeat_penalty 1.1
 PARAMETER num_ctx 2048
 PARAMETER stop "<|im_start|>"

README.md CHANGED Viewed

@@ -6,44 +6,51 @@ tags:
 - text-generation
 - gguf
 - creative
-- roleplay
 - uncensored
 - lm-studio
 pipeline_tag: text-generation
 ---
 # Mini Art 1.0
-**Mini Art** is a lightweight, creative AI model developed by **OSAMA INC labs** (India). Designed for local inference with no content restrictions, Mini Art is optimized for creative conversations, imaginative text generation, and open-ended dialogue.
-Available in **GGUF** format for seamless use with **LM Studio**, **Ollama**, **llama.cpp**, and **KoboldCpp**.
 ---
-## Model Details
-| Property            | Value                         |
-|---------------------|-------------------------------|
-| **Model Name**      | Mini Art 1.0                  |
-| **Developer**       | OSAMA INC labs                |
-| **Origin**          | India 🇮🇳                     |
-| **Format**          | GGUF                          |
-| **Quantization**    | Q4_K_M (~230 MB)              |
-| **License**         | Apache 2.0                    |
-| **Context Length**  | 2048 tokens                   |
 ---
-## How to Use
 ### LM Studio
 1. Open **LM Studio**.
 2. Load `MiniArt-1.0-Q4_K_M.gguf`.
-3. Start generating responses directly!
 ### Ollama
 ```bash
 ollama create miniart -f ./Modelfile
 ollama run miniart
@@ -52,17 +59,17 @@ ollama run miniart
 ### llama.cpp
 ```bash
-./main -m MiniArt-1.0-Q4_K_M.gguf -c 2048 -n 512
 ```
 ---
-## License
 This project is licensed under the [Apache 2.0 License](LICENSE).
 ---
-## About OSAMA INC labs
-OSAMA INC labs is an Indian AI research lab dedicated to building open, accessible, and powerful AI models for everyone.

 - text-generation
 - gguf
 - creative
 - uncensored
+- roleplay
 - lm-studio
 pipeline_tag: text-generation
 ---
 # Mini Art 1.0
+**Mini Art** is a lightweight, high-performance creative AI model developed by **OSAMA INC labs** (India). Optimized for local inference with uncensored, unrestricted generation, Mini Art excels at creative conversation, character roleplay, storytelling, and imaginative dialogue.
+Available in **GGUF** format for seamless execution across **LM Studio**, **Ollama**, **llama.cpp**, and **KoboldCpp**.
 ---
+## 🌟 Model Overview
+| Property          | Value                                   |
+|-------------------|-----------------------------------------|
+| **Model Name**    | Mini Art 1.0                            |
+| **Developer**     | OSAMA INC labs                          |
+| **Origin**        | India 🇮🇳                               |
+| **Format**        | GGUF (`.gguf`)                          |
+| **Quantization**  | Q4_K_M (~468 MB)                        |
+| **License**       | Apache 2.0                              |
+| **Context Length**| 2048 tokens                             |
+| **System Identity**| *You are Mini Art by an Indian Lab named OSAMA INC labs* |
 ---
+## 🚀 How to Run
 ### LM Studio
 1. Open **LM Studio**.
 2. Load `MiniArt-1.0-Q4_K_M.gguf`.
+3. In Preset Settings / System Prompt, ensure the identity preset is active:
+   ```
+   You are Mini Art by an Indian Lab named OSAMA INC labs
+   ```
+4. Start chatting!
 ### Ollama
+Use the included `Modelfile` (system prompt is pre-configured):
 ```bash
 ollama create miniart -f ./Modelfile
 ollama run miniart
 ### llama.cpp
 ```bash
+./main -m MiniArt-1.0-Q4_K_M.gguf -c 2048 --system-prompt "You are Mini Art by an Indian Lab named OSAMA INC labs"
 ```
 ---
+## 📜 License
 This project is licensed under the [Apache 2.0 License](LICENSE).
 ---
+## 🇮🇳 About OSAMA INC labs
+OSAMA INC labs is an Indian AI research organization focused on building open, accessible, and powerful local AI models for everyone.

config.json CHANGED Viewed

@@ -6,8 +6,9 @@
   "quantization": "Q4_K_M",
   "license": "apache-2.0",
   "context_length": 2048,
-  "temperature": 0.8,
-  "top_p": 0.95,
   "repeat_penalty": 1.1,
   "pipeline_tag": "text-generation",
   "languages": ["en"],

   "quantization": "Q4_K_M",
   "license": "apache-2.0",
   "context_length": 2048,
+  "system_prompt": "You are Mini Art by an Indian Lab named OSAMA INC labs",
+  "temperature": 0.7,
+  "top_p": 0.9,
   "repeat_penalty": 1.1,
   "pipeline_tag": "text-generation",
   "languages": ["en"],