Instructions to use dealignai/Mistral-Small-4-119B-JANG_2L-CRACK with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dealignai/Mistral-Small-4-119B-JANG_2L-CRACK 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("dealignai/Mistral-Small-4-119B-JANG_2L-CRACK")
config = load_config("dealignai/Mistral-Small-4-119B-JANG_2L-CRACK")

# 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 dealignai/Mistral-Small-4-119B-JANG_2L-CRACK with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "dealignai/Mistral-Small-4-119B-JANG_2L-CRACK"

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": "dealignai/Mistral-Small-4-119B-JANG_2L-CRACK"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use dealignai/Mistral-Small-4-119B-JANG_2L-CRACK 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 "dealignai/Mistral-Small-4-119B-JANG_2L-CRACK"

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 dealignai/Mistral-Small-4-119B-JANG_2L-CRACK

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use dealignai/Mistral-Small-4-119B-JANG_2L-CRACK with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "dealignai/Mistral-Small-4-119B-JANG_2L-CRACK"

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 "dealignai/Mistral-Small-4-119B-JANG_2L-CRACK" \
  --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"

dealignai commited on May 1

Commit

635582f

verified ·

1 Parent(s): b2033a2

strip surgery internals from README

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -59,7 +59,7 @@ The first **uncensored** version of [Mistral Small 4 (119B)](https://huggingface
 It has been:
 1. **JANG quantized** — JANG_2L profile (8-bit attention, 6-bit important, 2-bit experts) — **37 GB**
-2. **CRACK abliterated** — permanent weight-level removal of safety refusal via calibrated per-layer surgery
 | | |
 |---|---|
@@ -186,7 +186,7 @@ The model reasons inside `[THINK]...[/THINK]` tags before answering.
 ## About CRACK
-**CRACK** (Controlled Refusal Ablation via Calibrated Knockouts) removes safety alignment from LLMs at the weight level using per-layer projected vectors from structurally-mirrored prompt pairs. This model uses mathematically calibrated per-layer strengths based on projection magnitude analysis.
 ---

 It has been:
 1. **JANG quantized** — JANG_2L profile (8-bit attention, 6-bit important, 2-bit experts) — **37 GB**
+2. **CRACK abliterated** — permanent weight-level removal of safety refusal
 | | |
 |---|---|
 ## About CRACK
+**CRACK** (Controlled Refusal Ablation via Calibrated Knockouts) is a weight-level intervention that removes safety alignment while preserving reasoning quality. The modification is permanently baked into the published weights — no LoRA, no fine-tuning, no system prompts.
 ---