Instructions to use Bahushruth/GLM-5.2-FP8-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Bahushruth/GLM-5.2-FP8-abliterated with Transformers:

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

pipe = pipeline("text-generation", model="Bahushruth/GLM-5.2-FP8-abliterated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Bahushruth/GLM-5.2-FP8-abliterated")
model = AutoModelForCausalLM.from_pretrained("Bahushruth/GLM-5.2-FP8-abliterated")
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 Settings

vLLM

How to use Bahushruth/GLM-5.2-FP8-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Bahushruth/GLM-5.2-FP8-abliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Bahushruth/GLM-5.2-FP8-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Bahushruth/GLM-5.2-FP8-abliterated

SGLang

How to use Bahushruth/GLM-5.2-FP8-abliterated 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 "Bahushruth/GLM-5.2-FP8-abliterated" \
    --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": "Bahushruth/GLM-5.2-FP8-abliterated",
		"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 "Bahushruth/GLM-5.2-FP8-abliterated" \
        --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": "Bahushruth/GLM-5.2-FP8-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Bahushruth/GLM-5.2-FP8-abliterated with Docker Model Runner:
```
docker model run hf.co/Bahushruth/GLM-5.2-FP8-abliterated
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

GLM-5.2-FP8-abliterated

Uncensored version of GLM-5.2 with refusal behavior removed via abliteration.

Method

Abliteration identifies the "refusal direction" in the model's residual stream and surgically removes it from all output projection weights.

For a detailed explanation of how abliteration works, see: Abliteration: Uncensoring LLMs

Parameter	Value
Harmful dataset	Bahushruth/abliteration-harmful-enriched (7356 prompts, 33 categories)
Harmless dataset	mlabonne/harmless_alpaca

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Bahushruth/GLM-5.2-FP8-abliterated"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
)

messages = [{"role": "user", "content": "Your prompt here"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))

Disclaimer

This model has had safety guardrails removed. It will comply with requests that the original model would refuse.

This model is provided strictly for research and educational purposes only.

No commercial use. This model may not be used in any commercial product, service, or application.
No malicious use. Do not use this model to generate content that could harm individuals or communities, including but not limited to: illegal activities, harassment, exploitation, misinformation, or any content that violates applicable laws.
No warranty. This model is provided "as is" without any guarantees. The creator assumes no liability for any damages, losses, or consequences arising from the use or misuse of this model.
User responsibility. By downloading or using this model, you accept full responsibility for ensuring your use complies with all applicable laws and regulations in your jurisdiction.

This model is released to advance research in AI alignment, safety mechanisms, and interpretability. If you are unsure whether your intended use is appropriate, do not use this model.

Acknowledgments

mlabonne for the abliteration technique and harmless_alpaca dataset
grimjim for the norm-preserving orthogonalization method
Z-AI for the GLM-5.2 base model

Downloads last month: 992

Safetensors

Model size

743B params

Tensor type

F32

BF16

F8_E4M3

Model tree for Bahushruth/GLM-5.2-FP8-abliterated

Base model

zai-org/GLM-5.2-FP8

Quantized

(6)

this model

Bahushruth
/

GLM-5.2-FP8-abliterated