Instructions to use wordspace/proofreader-0.6B-MLX-6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use wordspace/proofreader-0.6B-MLX-6bit with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("wordspace/proofreader-0.6B-MLX-6bit") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Pi
How to use wordspace/proofreader-0.6B-MLX-6bit with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "wordspace/proofreader-0.6B-MLX-6bit"
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "wordspace/proofreader-0.6B-MLX-6bit" } ] } } }Run Pi
# Start Pi in your project directory: pi
- MLX LM
How to use wordspace/proofreader-0.6B-MLX-6bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "wordspace/proofreader-0.6B-MLX-6bit"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "wordspace/proofreader-0.6B-MLX-6bit" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "wordspace/proofreader-0.6B-MLX-6bit", "messages": [ {"role": "user", "content": "Hello"} ] }' - Hermes Agent
How to use wordspace/proofreader-0.6B-MLX-6bit with Hermes Agent:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "wordspace/proofreader-0.6B-MLX-6bit"
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 wordspace/proofreader-0.6B-MLX-6bit
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use wordspace/proofreader-0.6B-MLX-6bit with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "wordspace/proofreader-0.6B-MLX-6bit"
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 "wordspace/proofreader-0.6B-MLX-6bit" \ --custom-provider-id mlx-lm \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Download example.py from wordspace/proofreader-0.6B-MLX-6bit: direct link, hf CLI and curl.
- Browser
- Download file 1.56 kB
-
https://huggingface.co/wordspace/proofreader-0.6B-MLX-6bit/resolve/main/example.py
- Command line
-
hf download hf://wordspace/proofreader-0.6B-MLX-6bit/example.py
-
curl -L -o example.py https://huggingface.co/wordspace/proofreader-0.6B-MLX-6bit/resolve/main/example.py
1.56 kB
| """Style suggestions for a few sentences in different languages. Run it from | |
| the model folder: | |
| python example.py | |
| Needs `mlx-lm` (Apple silicon). The prompt lives in `protocol.py` and must | |
| not be changed: the model was trained on exactly that text. | |
| """ | |
| import os | |
| import time | |
| from mlx_lm import generate, load | |
| import protocol as P | |
| HERE = os.path.dirname(os.path.abspath(__file__)) | |
| TEXTS = [ | |
| ("en", "Due to the fact that the office is closed, we will send the documents on Monday."), | |
| ("en", "The plumber comes on Tuesday between 9 and 12."), | |
| ("it", "Al fine di risparmiare, abbiamo deciso di spegnere la caldaia di notte."), | |
| ("de", "Zum jetzigen Zeitpunkt ist die Werkstatt geschlossen."), | |
| ("fr", "Nous avons procédé à la vérification des compteurs ce matin."), | |
| ("es", "El curso de cocina tuvo una duración de seis semanas."), | |
| ] | |
| def main(): | |
| model, tokenizer = load(HERE) | |
| for lang, text in TEXTS: | |
| tokens = tokenizer.apply_chat_template(P.messages(text, P.LANGUAGE_NAMES[lang]), | |
| tokenize=True, add_generation_prompt=True) | |
| t0 = time.time() | |
| answer = generate(model, tokenizer, prompt=tokens, max_tokens=256, verbose=False) | |
| found = P.style_suggestions(answer, text) | |
| print("%s %s" % (lang, text)) | |
| for o, r in found: | |
| print(" «%s» → «%s»" % (o, r)) | |
| if not found: | |
| print(" (nothing to change)") | |
| print(" %.2f s" % (time.time() - t0)) | |
| if __name__ == "__main__": | |
| main() | |