Instructions to use qodelabs/qode1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use qodelabs/qode1 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 qodelabs/qode1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf qodelabs/qode1:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf qodelabs/qode1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf qodelabs/qode1:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf qodelabs/qode1:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf qodelabs/qode1:Q4_K_M

Use Docker

docker model run hf.co/qodelabs/qode1:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use qodelabs/qode1 with Ollama:
```
ollama run hf.co/qodelabs/qode1:Q4_K_M
```
Unsloth Desktop

How to use qodelabs/qode1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf qodelabs/qode1:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "qodelabs/qode1:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use qodelabs/qode1 with Docker Model Runner:
```
docker model run hf.co/qodelabs/qode1:Q4_K_M
```

Lemonade

How to use qodelabs/qode1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull qodelabs/qode1:Q4_K_M

Run and chat with the model

lemonade run user.qode1-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use qodelabs/qode1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf qodelabs/qode1: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 qodelabs/qode1:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use qodelabs/qode1 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf qodelabs/qode1: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 "qodelabs/qode1: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"

qodelabs commited on Aug 9

Commit

946b828

verified ·

1 Parent(s): 2374301

added benchmark info

Browse files

Files changed (1) hide show

README.md +19 -1

README.md CHANGED Viewed

@@ -15,7 +15,7 @@ tags:
 ![qode1:7b banner](qode.png)
-qode1 is a specialised code generation model fine-tuned from `Qwen/Qwen2.5-Coder-7B-Instruct`. It is specifically optimized to generate valid, high-quality **Luau (Roblox Lua)** code using Chain-of-Thought reasoning.
 ## Model Description
@@ -28,6 +28,24 @@ qode1 is a specialised code generation model fine-tuned from `Qwen/Qwen2.5-Coder
 # Benchmarks
 ![qode-luau-95 benchmark](qodebenchmark.png)
 ## Uses

 ![qode1:7b banner](qode.png)
+qode1 is a specialised code generation model fine-tuned from `Qwen/Qwen2.5-Coder-7B-Instruct`. It is specifically optimised to generate valid, high-quality **Luau (Roblox Lua)** code using Chain-of-Thought reasoning.
 ## Model Description
 # Benchmarks
 ![qode-luau-95 benchmark](qodebenchmark.png)
+quode-luau-95 is an automated test suite benchmark containing 95 coding challenges designed for conversational instruct models. It is designed specifically to evaluate how accurately an AI model writes Luau code.
+Rather than testing general knowledge, quode-luau-95 executes generated code inside a test runner to measure how well the model handles actual Luau scripting requirements.
+quode-luau-95 is broken up into 4 unseen sections:
+1. Pure Luau Logic & Types (25 questions)
+2. Spatial Math & Vectors (20 questions)
+3. Data Structures & Systems (25 questions)
+4. Defensive Logic & Data (25 questions)
+Below are the scores for each section:
+| Section | qode1:7b | qwen2.5-coder | codegemma:7b | llama3:8b | Average |
+| :--- | :---: | :---: | :---: | :---: | :---: |
+| 1 — Pure Luau Logic & Types | **10/25 (40.0%)** | 9/25 (36.0%) | 9/25 (36.0%) | 9/25 (36.0%) | 37.0% |
+| 2 — Spatial Math & Vectors | **8/20 (40.0%)** | **8/20 (40.0%)** | 5/20 (25.0%) | 6/20 (30.0%) | 33.8% |
+| 3 — Data Structures & Systems | 5/25 (20.0%) | 5/25 (20.0%) | **7/25 (28.0%)** | 3/25 (12.0%) | 20.0% |
+| 4 — Defensive Logic & Data | **11/25 (44.0%)** | 9/25 (36.0%) | 9/25 (36.0%) | 4/25 (16.0%) | 33.0% |
 ## Uses