Instructions to use gnukeith/Ocelot-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gnukeith/Ocelot-MLX with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("gnukeith/Ocelot-MLX")
config = load_config("gnukeith/Ocelot-MLX")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use gnukeith/Ocelot-MLX with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "gnukeith/Ocelot-MLX"

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": "gnukeith/Ocelot-MLX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use gnukeith/Ocelot-MLX 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 "gnukeith/Ocelot-MLX"

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 gnukeith/Ocelot-MLX

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use gnukeith/Ocelot-MLX with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "gnukeith/Ocelot-MLX"

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 "gnukeith/Ocelot-MLX" \
  --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"

gnukeith commited on Jul 22

Commit

bf2c15e

verified ·

1 Parent(s): a910f72

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +11 -1

README.md CHANGED Viewed

@@ -12,9 +12,19 @@ Recommended MLX 4-bit, group-size 64 conversion of [Ocelot-1-VL](https://hugging
 This model is specialized only for webpage summarization. Follow the strict prompt contract and limitations in the original model card.
 ```bash
 pip install 'mlx-vlm @ git+https://github.com/Blaizzy/mlx-vlm.git'
-python -m mlx_vlm generate --model . --prompt 'The is the text of a webpage: <page>Page text here</page> Summarise the content between the <page> tags, or if no content is found use the screenshots provided, in the Brave Summary style.' --max-tokens 512
 ```
 For screenshots, add `--image webpage.png` and begin the prompt with `The following is a screenshot of a webpage:`. Converted with MLX-VLM revision `0b1d25e334686bd36dda71b2307d186dbb3e7859`. Text and screenshot tests passed. An Apple M4 Pro test used 3.34 GB peak memory and measured 45 prompt tokens/s and 15 generation tokens/s.

 This model is specialized only for webpage summarization. Follow the strict prompt contract and limitations in the original model card.
+These are final MLX weights, not conversion inputs. Users can open a local browser interface directly after installing the MLX runtime:
 ```bash
 pip install 'mlx-vlm @ git+https://github.com/Blaizzy/mlx-vlm.git'
+mlx_vlm.chat_ui --model gnukeith/Ocelot-MLX
+```
+The runtime downloads the model from Hugging Face automatically. No cloning, conversion, or Python code is required.
+Direct command-line inference is also available:
+```bash
+mlx_vlm.generate --model gnukeith/Ocelot-MLX --prompt 'The is the text of a webpage: <page>Page text here</page> Summarise the content between the <page> tags, or if no content is found use the screenshots provided, in the Brave Summary style.' --max-tokens 512
 ```
 For screenshots, add `--image webpage.png` and begin the prompt with `The following is a screenshot of a webpage:`. Converted with MLX-VLM revision `0b1d25e334686bd36dda71b2307d186dbb3e7859`. Text and screenshot tests passed. An Apple M4 Pro test used 3.34 GB peak memory and measured 45 prompt tokens/s and 15 generation tokens/s.