Instructions to use aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell 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 aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell
# Run inference directly in the terminal:
llama cli -hf aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell
# Run inference directly in the terminal:
llama cli -hf aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell

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 aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell
# Run inference directly in the terminal:
./llama-cli -hf aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell

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 aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell
# Run inference directly in the terminal:
./build/bin/llama-cli -hf aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell

Use Docker

docker model run hf.co/aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell

LM Studio
Jan
Ollama
How to use aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell with Ollama:
```
ollama run hf.co/aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell
```

Unsloth Studio

How to use aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell 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 aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell 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 aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell to start chatting

How to use aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell

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": "aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell

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 "aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell" \
  --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 aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell with Docker Model Runner:
```
docker model run hf.co/aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell
```

Lemonade

How to use aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell

Run and chat with the model

lemonade run user.Qwen2.5-Coder-0.5B-Instruct-Shell-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell

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 aidebug/Qwen2.5-Coder-0.5B-Instruct-Shell

Run Hermes

hermes

Atomic Chat

ShellClaw Command Completion Model

A command completion model fine-tuned on Qwen2.5-Coder-0.5B-Instruct, designed for ShellClaw terminal completion.

Base Model

Base: Qwen/Qwen2.5-Coder-0.5B-Instruct
Base Model URL: https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B-Instruct

Fine-Tuning Details

Method: LoRA (r=32, alpha=64)
Dataset: 27,217 Unix/macOS commands extracted from tldr

Model Format

Format: GGUF (q8_0)
Size: ~525MB
Compatibility: llama.cpp ecosystem

Use Cases

Local command completion for ShellClaw
Shell command completion for any llama.cpp-compatible tool

Usage

# Directly use with llama.cpp
llama-cli -m qwen2.5-coder-0.5b-instruct-finetuned.gguf

# Or use with ShellClaw
export SHELLCLAW_MODEL_PATH=/path/to/qwen2.5-coder-0.5b-instruct-finetuned.gguf

Downloads last month: -

GGUF

Model size

0.5B params

Architecture

qwen2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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