Instructions to use mlx-community/Laguna-S-2.1-oQ2e with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/Laguna-S-2.1-oQ2e 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("mlx-community/Laguna-S-2.1-oQ2e")

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

How to use mlx-community/Laguna-S-2.1-oQ2e with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/Laguna-S-2.1-oQ2e"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "mlx-community/Laguna-S-2.1-oQ2e"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mlx-community/Laguna-S-2.1-oQ2e 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 "mlx-community/Laguna-S-2.1-oQ2e"

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 mlx-community/Laguna-S-2.1-oQ2e

Run Hermes

hermes

OpenClaw new

How to use mlx-community/Laguna-S-2.1-oQ2e with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/Laguna-S-2.1-oQ2e"

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 "mlx-community/Laguna-S-2.1-oQ2e" \
  --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"

MLX LM

How to use mlx-community/Laguna-S-2.1-oQ2e with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "mlx-community/Laguna-S-2.1-oQ2e"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "mlx-community/Laguna-S-2.1-oQ2e"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "mlx-community/Laguna-S-2.1-oQ2e",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

There will be an infinite output of tokens

by sqh11 - opened 3 days ago

Discussion

sqh11

MLX Community org 3 days ago

There may be an infinite output of tokens, and I have observed a similar situation with the publisher. Can this issue be fixed?
link:https://huggingface.co/poolside/Laguna-S-2.1/discussions/12

gabfssilva

MLX Community org 3 days ago

Before uploading, when I was running some tests, I did find this behavior in specific scenarios for the lower quants (oQ2e-fast, oQ2e and oQ3e), but I managed to solve it with a repetition penalty of 1.05, which is set in the configuration file.

Did you experience the issue with the oQ2e as well? I'm not able to reproduce it anymore.

sqh11

MLX Community org 3 days ago

Before uploading, when I was running some tests, I did find this behavior in specific scenarios for the lower quants (oQ2e-fast, oQ2e and oQ3e), but I managed to solve it with a repetition penalty of 1.05, which is set in the configuration file.

Did you experience the issue with the oQ2e as well? I'm not able to reproduce it anymore.
Yes, I am using omlx 0.5.3 and running oQ2e version on a device with m1 max 64GB. When solving practical problems, I have encountered multiple issues with unlimited token output, and I cannot confirm whether it is an omlx or quantization problem.

gabfssilva

MLX Community org 3 days ago

can you check if you're using a repetition penalty of 1.05?

sqh11

MLX Community org about 5 hours ago

can you check if you're using a repetition penalty of 1.05?
The repetition penalty has always been 1.05. Yesterday, I replaced an SDD cache hard drive, and the model is still functioning normally until now.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment