Instructions to use JANGQ-AI/GLM-5.3-Flash-JANG-MTP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JANGQ-AI/GLM-5.3-Flash-JANG-MTP 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("JANGQ-AI/GLM-5.3-Flash-JANG-MTP")
config = load_config("JANGQ-AI/GLM-5.3-Flash-JANG-MTP")

# 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 JANGQ-AI/GLM-5.3-Flash-JANG-MTP with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "JANGQ-AI/GLM-5.3-Flash-JANG-MTP"

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": "JANGQ-AI/GLM-5.3-Flash-JANG-MTP"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use JANGQ-AI/GLM-5.3-Flash-JANG-MTP 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 "JANGQ-AI/GLM-5.3-Flash-JANG-MTP"

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 JANGQ-AI/GLM-5.3-Flash-JANG-MTP

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use JANGQ-AI/GLM-5.3-Flash-JANG-MTP with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "JANGQ-AI/GLM-5.3-Flash-JANG-MTP"

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 "JANGQ-AI/GLM-5.3-Flash-JANG-MTP" \
  --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"

jangq commited on 5 days ago

Commit

e272514

verified ·

1 Parent(s): 9a7f66b

fix: default clear_thinking=true in chat_template.jinja + add repetition_penalty=1.1 default in generation_config.json — mitigates known GLM-5.3 reasoning-loop degeneration on multi-turn agent workloads (SGLang #36669, opencode #45533). Upstream Z.ai default `clear_thinking=false` replays prior reasoning into subsequent turns, priming a decode attractor. Z.ai's own docs recommend `clear_thinking=true` for chat scenarios — bakes it in.

Browse files

Files changed (1) hide show

generation_config.json +3 -2

generation_config.json CHANGED Viewed

@@ -9,5 +9,6 @@
   "temperature": 1.0,
   "top_p": 0.95,
   "transformers_version": "5.16.0",
-  "do_sample": true
-}

   "temperature": 1.0,
   "top_p": 0.95,
   "transformers_version": "5.16.0",
+  "do_sample": true,
+  "repetition_penalty": 1.1
+}