Instructions to use ArliAI/GLM-4.5-Air-Derestricted with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ArliAI/GLM-4.5-Air-Derestricted with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ArliAI/GLM-4.5-Air-Derestricted")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ArliAI/GLM-4.5-Air-Derestricted")
model = AutoModelForCausalLM.from_pretrained("ArliAI/GLM-4.5-Air-Derestricted")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ArliAI/GLM-4.5-Air-Derestricted with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ArliAI/GLM-4.5-Air-Derestricted"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ArliAI/GLM-4.5-Air-Derestricted",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ArliAI/GLM-4.5-Air-Derestricted

SGLang

How to use ArliAI/GLM-4.5-Air-Derestricted with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ArliAI/GLM-4.5-Air-Derestricted" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ArliAI/GLM-4.5-Air-Derestricted",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ArliAI/GLM-4.5-Air-Derestricted" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ArliAI/GLM-4.5-Air-Derestricted",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ArliAI/GLM-4.5-Air-Derestricted with Docker Model Runner:
```
docker model run hf.co/ArliAI/GLM-4.5-Air-Derestricted
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Arli AI

GLM-4.5-Air-Derestricted

GLM-4.5-Air-Derestricted is a Derestricted version of GLM-4.5-Air, created by Arli AI.

Our goal with this release is to provide a version of the model that removed refusal behaviors while maintaining the high-performance reasoning of the original GLM-4.5-Air. This is unlike regular abliteration which often inadvertently "lobotomizes" the model.

Methodology: Norm-Preserving Biprojected Abliteration

To achieve this, Arli AI utilized Norm-Preserving Biprojected Abliteration, a refined technique pioneered by Jim Lai (grimjim). You can read the full technical breakdown in this article.

Why this matters:

Standard abliteration works by simply subtracting a "refusal vector" from the model's weights. While this works to uncensor a model, it is mathematically unprincipled. It alters the magnitude (or "loudness") of the neurons, destroying the delicate feature norms the model learned during training. This damage is why many uncensored models suffer from degraded logic or hallucinations.

How Norm-Preserving Biprojected Abliteration fixes it:

This model was modified using a three-step approach that removes refusals without breaking the model's brain:

Biprojection (Targeting): We refined the refusal direction to ensure it is mathematically orthogonal to "harmless" directions. This ensures that when we cut out the refusal behavior, we do not accidentally cut out healthy, harmless concepts.
Decomposition: Instead of a raw subtraction, we decomposed the model weights into Magnitude and Direction.
Norm-Preservation: We removed the refusal component solely from the directional aspect of the weights, then recombined them with their original magnitudes.

The Result:

By preserving the weight norms, we maintain the "importance" structure of the neural network. Benchmarks suggest that this method avoids the "Safety Tax"—not only effectively removing refusals but potentially improving reasoning capabilities over the baseline, as the model is no longer wasting compute resources on suppressing its own outputs.

In fact, you may find surprising new knowledge and capabilities that the original model does not initially expose.

Quantization:

Original model card:

👋 Join our Discord community.
📖 Check out the GLM-4.5 technical blog, technical report, and Zhipu AI technical documentation.
📍 Use GLM-4.5 API services on Z.ai API Platform (Global) or
Zhipu AI Open Platform (Mainland China).
👉 One click to GLM-4.5.

Model Introduction

The GLM-4.5 series models are foundation models designed for intelligent agents. GLM-4.5 has 355 billion total parameters with 32 billion active parameters, while GLM-4.5-Air adopts a more compact design with 106 billion total parameters and 12 billion active parameters. GLM-4.5 models unify reasoning, coding, and intelligent agent capabilities to meet the complex demands of intelligent agent applications.

Both GLM-4.5 and GLM-4.5-Air are hybrid reasoning models that provide two modes: thinking mode for complex reasoning and tool usage, and non-thinking mode for immediate responses.

We have open-sourced the base models, hybrid reasoning models, and FP8 versions of the hybrid reasoning models for both GLM-4.5 and GLM-4.5-Air. They are released under the MIT open-source license and can be used commercially and for secondary development.

As demonstrated in our comprehensive evaluation across 12 industry-standard benchmarks, GLM-4.5 achieves exceptional performance with a score of 63.2, in the 3rd place among all the proprietary and open-source models. Notably, GLM-4.5-Air delivers competitive results at 59.8 while maintaining superior efficiency.