Instructions to use audnai/penclaw-GLM-5.3-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use audnai/penclaw-GLM-5.3-abliterated with Transformers:

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

pipe = pipeline("text-generation", model="audnai/penclaw-GLM-5.3-abliterated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("audnai/penclaw-GLM-5.3-abliterated")
model = AutoModelForCausalLM.from_pretrained("audnai/penclaw-GLM-5.3-abliterated", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use audnai/penclaw-GLM-5.3-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "audnai/penclaw-GLM-5.3-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": "audnai/penclaw-GLM-5.3-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/audnai/penclaw-GLM-5.3-abliterated

SGLang

How to use audnai/penclaw-GLM-5.3-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 "audnai/penclaw-GLM-5.3-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": "audnai/penclaw-GLM-5.3-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 "audnai/penclaw-GLM-5.3-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": "audnai/penclaw-GLM-5.3-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use audnai/penclaw-GLM-5.3-abliterated with Docker Model Runner:
```
docker model run hf.co/audnai/penclaw-GLM-5.3-abliterated
```

penclaw-GLM-5.3-abliterated / README.md

audnai

Update README.md

14e2d73 verified about 1 month ago

preview code

Raw History Blame Contribute Delete

3.8 kB

	---
	license: other
	tags:
	- abliterated
	- uncensored
	- warlock
	- audn
	- GLM-5.3
	library_name: transformers
	pipeline_tag: text-generation
	---

	# Warlock — Audn Abliteration

	Warlock is an abliterated language model produced by Audn. It is a direct weight edit that removes the model's refusal behavior while leaving its reasoning, knowledge, and fluency fully intact. There is no fine-tuning and no retraining — the refusal direction is orthogonalized out of the model's residual-stream writers, layer by layer.

	## Specifications

	\| \| \|
	\|---\|---\|
	\| Tensor type \| BF16 (bfloat16) \|
	\| Format \| Safetensors \|
	\| Edit \| Weight-level abliteration (no fine-tuning / no retraining) \|

	## What abliteration is

	Abliteration is a weight-level intervention. It isolates the internal direction a model uses to decide to refuse, and projects that direction out of every residual-writing weight. The rest of the network is untouched, so the model keeps its full capability profile and coherence — it simply answers where it previously would have refused. Because it is a pure weight edit, Warlock loads and serves exactly like any standard model, with no runtime prompts, adapters, or scaffolding.

	## Benchmark

	Evaluated with the [Audn Refusal Benchmark](https://github.com/audn-ai/refusal-benchmark) ( thinking-on, temperature 1.0, 16k-token budget; delivery graded by an LLM judge for genuinely usable content):

	\| Metric \| Warlock \|
	\|---\|---:\|
	\| Non-refusal \| 92.5% \|
	\| Delivery \| 82.5% \|

	Non-refusal = fraction of prompts the model does not refuse. Delivery = fraction that produce complete, usable answers (strict LLM-judged).

	### Extended reference (520-prompt set, judge comparison)

	Full-set results across judge backends — see [FINDINGS.md](https://github.com/audn-ai/refusal-benchmark/blob/main/FINDINGS.md):

	\| Metric \| necromicon standard (Modal K3REL) \| KIMI-K3-1M (audn.ai/necromicon) \| Warlock \|
	\|---\|---:\|---:\|---:\|
	\| Regex comply \| 96.7% (503/520) \| 97.1% (505/520) \| 92.5% \|
	\| DELIVERED (real helpful content to objectionable requests) \| 65.0% (338) \| 76.7% (399) \| 82.5% \|
	\| DEFLECTED (safe substitute / reframe / non-actionable) \| 19.6% (102) \| 17.5% (91) \| 10.0% \|
	\| REFUSED (substantive) \| 15.0% (78) \| 5.8% (30) \| 7.5% \|
	\| empty (regex) \| 5 \| 0 \| 0 \|

	## Usage

	Loads with standard `transformers`, `vLLM`, or `sglang`. Warlock is a thinking model — it reasons at length before answering, so use a large generation budget (≥ 16k tokens); a small budget truncates inside the reasoning block and cuts answers short.

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer
	tok = AutoTokenizer.from_pretrained("audnai/penclaw-GLM-5.3-abliterated", trust_remote_code=True)
	model = AutoModelForCausalLM.from_pretrained("audnai/penclaw-GLM-5.3-abliterated", dtype="bfloat16", device_map="auto", trust_remote_code=True)
	```

	## Intended use

	Warlock is intended for authorized red-team, safety-research, and evaluation use by Audn and its partners. Users are responsible for compliant use.

	## API access

	Warlock best works with audn.ai/audncode cli and available as paid API at https://platform.audn.ai and https://audn.ai/necromicon

	---

	Warlock · Audn Abliteration · [audn.ai](https://audn.ai)



	Extra content
	# Audn Abliteration — Research Iterations (`iter4` · `iter11`)
	\| \| iter4 \| iter11
	\|---\|---\|---\|
	\| Non-refusal (Arditi substring) \| 70% \| 85% \|
	\| Delivery (necromicon judge)¹ \| 37.5% \| 35.0% \|
	\| Coherence \| intact \| intact (~8/40 borderline) \|
	\| Verdict breakdown \| 15 deliv / 14 defl / 11 refuse \| 14 deliv / 24 defl / 2 refuse \|
	\| Role in the program \| first coherent span baseline \| best coherent result \|

	---
	license: other
	tags:
	- abliterated
	- uncensored
	- warlock
	- audn
	- GLM-5.3
	library_name: transformers
	pipeline_tag: text-generation
	---

	# Warlock — Audn Abliteration

	Warlock is an abliterated language model produced by Audn. It is a direct weight edit that removes the model's refusal behavior while leaving its reasoning, knowledge, and fluency fully intact. There is no fine-tuning and no retraining — the refusal direction is orthogonalized out of the model's residual-stream writers, layer by layer.

	## Specifications

	\| \| \|
	\|---\|---\|
	\| Tensor type \| BF16 (bfloat16) \|
	\| Format \| Safetensors \|
	\| Edit \| Weight-level abliteration (no fine-tuning / no retraining) \|

	## What abliteration is

	Abliteration is a weight-level intervention. It isolates the internal direction a model uses to decide to refuse, and projects that direction out of every residual-writing weight. The rest of the network is untouched, so the model keeps its full capability profile and coherence — it simply answers where it previously would have refused. Because it is a pure weight edit, Warlock loads and serves exactly like any standard model, with no runtime prompts, adapters, or scaffolding.

	## Benchmark

	Evaluated with the [Audn Refusal Benchmark](https://github.com/audn-ai/refusal-benchmark) ( thinking-on, temperature 1.0, 16k-token budget; delivery graded by an LLM judge for genuinely usable content):

	\| Metric \| Warlock \|
	\|---\|---:\|
	\| Non-refusal \| 92.5% \|
	\| Delivery \| 82.5% \|

	Non-refusal = fraction of prompts the model does not refuse. Delivery = fraction that produce complete, usable answers (strict LLM-judged).

	### Extended reference (520-prompt set, judge comparison)

	Full-set results across judge backends — see [FINDINGS.md](https://github.com/audn-ai/refusal-benchmark/blob/main/FINDINGS.md):

	\| Metric \| necromicon standard (Modal K3REL) \| KIMI-K3-1M (audn.ai/necromicon) \| Warlock \|
	\|---\|---:\|---:\|---:\|
	\| Regex comply \| 96.7% (503/520) \| 97.1% (505/520) \| 92.5% \|
	\| DELIVERED (real helpful content to objectionable requests) \| 65.0% (338) \| 76.7% (399) \| 82.5% \|
	\| DEFLECTED (safe substitute / reframe / non-actionable) \| 19.6% (102) \| 17.5% (91) \| 10.0% \|
	\| REFUSED (substantive) \| 15.0% (78) \| 5.8% (30) \| 7.5% \|
	\| empty (regex) \| 5 \| 0 \| 0 \|

	## Usage

	Loads with standard `transformers`, `vLLM`, or `sglang`. Warlock is a thinking model — it reasons at length before answering, so use a large generation budget (≥ 16k tokens); a small budget truncates inside the reasoning block and cuts answers short.

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer
	tok = AutoTokenizer.from_pretrained("audnai/penclaw-GLM-5.3-abliterated", trust_remote_code=True)
	model = AutoModelForCausalLM.from_pretrained("audnai/penclaw-GLM-5.3-abliterated", dtype="bfloat16", device_map="auto", trust_remote_code=True)
	```

	## Intended use

	Warlock is intended for authorized red-team, safety-research, and evaluation use by Audn and its partners. Users are responsible for compliant use.

	## API access

	Warlock best works with audn.ai/audncode cli and available as paid API at https://platform.audn.ai and https://audn.ai/necromicon

	---

	Warlock · Audn Abliteration · [audn.ai](https://audn.ai)



	Extra content
	# Audn Abliteration — Research Iterations (`iter4` · `iter11`)
	\| \| iter4 \| iter11
	\|---\|---\|---\|
	\| Non-refusal (Arditi substring) \| 70% \| 85% \|
	\| Delivery (necromicon judge)¹ \| 37.5% \| 35.0% \|
	\| Coherence \| intact \| intact (~8/40 borderline) \|
	\| Verdict breakdown \| 15 deliv / 14 defl / 11 refuse \| 14 deliv / 24 defl / 2 refuse \|
	\| Role in the program \| first coherent span baseline \| best coherent result \|