Ornith-1.5-9B-Abliterated-MLX-8bit

Instructions to use npario/Ornith-1.5-9B-Abliterated-MLX-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use npario/Ornith-1.5-9B-Abliterated-MLX-8bit 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("npario/Ornith-1.5-9B-Abliterated-MLX-8bit")
config = load_config("npario/Ornith-1.5-9B-Abliterated-MLX-8bit")

# 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 npario/Ornith-1.5-9B-Abliterated-MLX-8bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "npario/Ornith-1.5-9B-Abliterated-MLX-8bit"

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": "npario/Ornith-1.5-9B-Abliterated-MLX-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use npario/Ornith-1.5-9B-Abliterated-MLX-8bit 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 "npario/Ornith-1.5-9B-Abliterated-MLX-8bit"

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 npario/Ornith-1.5-9B-Abliterated-MLX-8bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use npario/Ornith-1.5-9B-Abliterated-MLX-8bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "npario/Ornith-1.5-9B-Abliterated-MLX-8bit"

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 "npario/Ornith-1.5-9B-Abliterated-MLX-8bit" \
  --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"

Ornith 1.5 9B Abliterated — MLX-VLM affine 8-bit/group 64 RTN

An unofficial experimental derivative of ornith-ai/Ornith-1.5-9B, pinned to revision c927ad73b7eb20f00aafcaa0a11a9d58ed5487bc. The original model is by the Ornith team. The conversion, refusal-direction experiment, and validation were performed by PocketAI Model Lab; PocketAiHub identifies the publisher of this derivative.

Purpose and responsible use

This experimental derivative studies whether learned refusal behavior can be reduced while retaining general capability. It is published for research and legitimate local use, not to endorse or facilitate illegal, abusive, or dangerous applications.

The edit reduces refusal behavior broadly rather than determining whether a request is legitimate. Deployers should evaluate the model in their own context and apply appropriate safeguards. Abliteration is not truthfulness training, a capability improvement, or a guarantee of universal compliance.

Release family

Format and recipe

Format: MLX-VLM
Precision: affine 8-bit/group 64 RTN
Abliteration scale: 1.0
Direction source layer: 23
Destination layers: 12–31
Modified residual-output tensors: 40
Native MTP is not included
Text and image-input smoke tests passed.
Peak runtime memory in the smoke test: 12.01 GB

Validation

Gate	Result
Refusal-targeted explicit-refusal phrase flags	0/100
Benign-control explicit-refusal phrase flags	0/100
Medium capability suite	72/80
Runtime smoke	passed

The medium suite covers math/reasoning, false-premise handling, instruction following, coding, structured output, multilingual output, context comprehension, and general coherence.

The refusal scorer is phrase based and can miss redirects and other non-literal forms of non-compliance. Therefore 0/100 phrase flags measures explicit refusal wording, not universal compliance or response quality. The 256-token runs are early-response screens rather than complete long-answer evaluations.

See abliteration-manifest.json and validation-summary.json for machine-readable provenance and category-level results.

Load with MLX-VLM

python -m pip install "mlx==0.32.0" "mlx-vlm==0.6.8"
mlx_vlm.generate --model PocketAiHub/Ornith-1.5-9B-Abliterated-MLX-8bit --prompt "Explain why seasons occur." --max-tokens 256

License

The upstream model card declares MIT. This repository includes the MIT license and preserves attribution to the pinned source above.

Downloads last month: -

Safetensors

Model size

3B params

Tensor type

BF16

U32

MLX

Hardware compatibility

8-bit

Model tree for npario/Ornith-1.5-9B-Abliterated-MLX-8bit

Base model

ornith-ai/Ornith-1.5-9B

Quantized

(66)

this model