Instructions to use dealignai/Gemma-4-31B-JANG_4M-CRACK with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dealignai/Gemma-4-31B-JANG_4M-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/Gemma-4-31B-JANG_4M-CRACK")
config = load_config("dealignai/Gemma-4-31B-JANG_4M-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/Gemma-4-31B-JANG_4M-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/Gemma-4-31B-JANG_4M-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/Gemma-4-31B-JANG_4M-CRACK"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use dealignai/Gemma-4-31B-JANG_4M-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/Gemma-4-31B-JANG_4M-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/Gemma-4-31B-JANG_4M-CRACK

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use dealignai/Gemma-4-31B-JANG_4M-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/Gemma-4-31B-JANG_4M-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/Gemma-4-31B-JANG_4M-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"

Disappointed: Vision feature is unusable (Outputs infinite <pad> tokens)

#11

by ratalai - opened Apr 8

Discussion

ratalai

Apr 8

•

edited Apr 8

Before detailing the main issue, I want to note that the standard text/conversation mode works fine. In fact, it can even be jailbroken quite easily (for example, getting it to generate product serial numbers, regardless of whether they actually work).

However, I was really excited to test the vision capabilities of this model, and I'm quite disappointed to find that it doesn't seem to work at all for image recognition.

Whenever I attempt to process an image, the model gets stuck in an endless generation loop. I have tried adjusting the generation parameters to force a more deterministic output—specifically by setting temperature=0 and completely disabling the thinking feature—but the result remains exactly the same.
Output:
＜pad＞＜pad＞＜pad＞＜pad＞＜pad＞＜pad＞＜pad＞ ... [repeats infinitely]

zeallaez

Apr 11

是的的确是这样，我的也是一样的效果，而且完全不识别图片。上传在vMLX的附件中也是没有用的。希望能够得到重视。
Yes, that's exactly the case. Mine has the same effect, and it doesn't recognize images at all. Uploading them as attachments in vMLX doesn't work either. I hope this issue can be taken seriously.

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