Instructions to use ReXeeD/TASX-Cmd-0.5B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ReXeeD/TASX-Cmd-0.5B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ReXeeD/TASX-Cmd-0.5B-GGUF",
	filename="tasx_sft_merged.Q8_0.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 ReXeeD/TASX-Cmd-0.5B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ReXeeD/TASX-Cmd-0.5B-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf ReXeeD/TASX-Cmd-0.5B-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ReXeeD/TASX-Cmd-0.5B-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf ReXeeD/TASX-Cmd-0.5B-GGUF:Q8_0

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 ReXeeD/TASX-Cmd-0.5B-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf ReXeeD/TASX-Cmd-0.5B-GGUF:Q8_0

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 ReXeeD/TASX-Cmd-0.5B-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ReXeeD/TASX-Cmd-0.5B-GGUF:Q8_0

Use Docker

docker model run hf.co/ReXeeD/TASX-Cmd-0.5B-GGUF:Q8_0

LM Studio
Jan

vLLM

How to use ReXeeD/TASX-Cmd-0.5B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ReXeeD/TASX-Cmd-0.5B-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": "ReXeeD/TASX-Cmd-0.5B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ReXeeD/TASX-Cmd-0.5B-GGUF:Q8_0

Ollama
How to use ReXeeD/TASX-Cmd-0.5B-GGUF with Ollama:
```
ollama run hf.co/ReXeeD/TASX-Cmd-0.5B-GGUF:Q8_0
```

Unsloth Studio new

How to use ReXeeD/TASX-Cmd-0.5B-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 ReXeeD/TASX-Cmd-0.5B-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 ReXeeD/TASX-Cmd-0.5B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ReXeeD/TASX-Cmd-0.5B-GGUF to start chatting

Pi new

How to use ReXeeD/TASX-Cmd-0.5B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf ReXeeD/TASX-Cmd-0.5B-GGUF:Q8_0

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": "ReXeeD/TASX-Cmd-0.5B-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ReXeeD/TASX-Cmd-0.5B-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 ReXeeD/TASX-Cmd-0.5B-GGUF:Q8_0

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 ReXeeD/TASX-Cmd-0.5B-GGUF:Q8_0

Run Hermes

hermes

Docker Model Runner
How to use ReXeeD/TASX-Cmd-0.5B-GGUF with Docker Model Runner:
```
docker model run hf.co/ReXeeD/TASX-Cmd-0.5B-GGUF:Q8_0
```

Lemonade

How to use ReXeeD/TASX-Cmd-0.5B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ReXeeD/TASX-Cmd-0.5B-GGUF:Q8_0

Run and chat with the model

lemonade run user.TASX-Cmd-0.5B-GGUF-Q8_0

List all available models

lemonade list

TASX-Command-0.5B

TASX-Command-0.5B is a highly specialized, lightweight language model designed specifically for robotics. It translates natural language (including slang, typos, and complex phrasing) into strict, execution-ready JSON command sequences for ROS2, SLAM, and physical robot control.

By fine-tuning the Qwen2.5-0.5B base model, we created a "robot brain" that is small and fast enough to run locally on edge hardware (like a Raspberry Pi) via llama.cpp while retaining the intelligence to understand complex human intent.

Quantized Versions (GGUF)

For high-performance inference , use these GGUF quants:

TASX-Cmd-0.5B-GGUF (mradermacher) — Includes high-quality iMatrix and IQ quants.

Key Features

Strict JSON Output: Never outputs conversational filler; only valid JSON arrays.
Typo & Slang Immunity: Successfully maps messy speech (e.g., "scoot forward lik 3 point 5 meeters") to perfect floats and commands.
Dynamic Location Extraction: Converts any spoken room or location name (e.g., "Professor Xavier's Office") into clean snake_case (e.g., professor_xavier_office).
Physical Constraint Logic: Automatically generates implicit macro sequences (like sit -> stand -> move) for fetching and delivering items without needing explicit user instruction.

Supported Actions & Commands

The model is trained to strictly output one or more of the following 20 commands formatted as a JSON array of actions.

1. Teleop (Movement & Speed)

{"type": "teleop", "cmd": "move_forward", "distance": <float>}
{"type": "teleop", "cmd": "move_backward", "distance": <float>}
{"type": "teleop", "cmd": "rotate_left", "angle": <float>}
{"type": "teleop", "cmd": "rotate_right", "angle": <float>}
{"type": "teleop", "cmd": "set_speed", "level": "slow" | "normal" | "fast"}
{"type": "teleop", "cmd": "stop"} (For casual pauses)
{"type": "teleop", "cmd": "e_stop"} (For panicked/emergency stops)

2. Nav2 (Autonomous Navigation)

{"type": "nav2", "cmd": "go_to_waypoint", "target": "<snake_case_string>"}
{"type": "nav2", "cmd": "cancel_goal"}

3. Stunts (Posture & Tricks)

{"type": "stunt", "cmd": "full_sit"}
{"type": "stunt", "cmd": "half_sit"}
{"type": "stunt", "cmd": "stand_up"}
{"type": "stunt", "cmd": "spin", "direction": "clockwise" | "anticlockwise"}

Advanced Behaviors (Macros)

TASX-Command-0.5B has been taught physical robotics logic. It knows a robot cannot drive while sitting.

If you ask it to perform a delivery (e.g., "Fetch my laptop from the server room and bring it to John's desk"), it will automatically output the required posture macros:

{
  "actions": [
    {"type": "nav2", "cmd": "go_to_waypoint", "target": "server_room"},
    {"type": "stunt", "cmd": "full_sit"},
    {"type": "stunt", "cmd": "stand_up"},
    {"type": "nav2", "cmd": "go_to_waypoint", "target": "john_desk"},
    {"type": "stunt", "cmd": "full_sit"}
  ]
}

Test Script

from llama_cpp import Llama


print("⏳ Loading model... please wait.")
llm = Llama(
    model_path="./tasx_sft_merged_gguf/tasx_sft_merged.Q8_0.gguf",
    n_ctx=512,           
    stop=["<|im_end|>"],  
    verbose=False        
)

print("\n" + "="*50)
print("TASX ROBOT ")
print("Type a command and press Enter. Type 'q' to quit.")
print("="*50 + "\n")

while True:
    user_text = input("🎤 You: ")
    
    if user_text.lower() in ['q', 'quit', 'exit']:
        print("Stopping tester. Great job!")
        break
        
    if not user_text.strip():
        continue

    prompt = f"<|im_start|>user\n{user_text}<|im_end|>\n<|im_start|>assistant\n"

    output = llm(
        prompt,
        max_tokens=150,
        temperature=0,   
        echo=False
    )

    response = output["choices"][0]["text"].strip()
    print(f"TASX: {response}\n")