Instructions to use heterodoxin/qwen3-8b-apostate with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use heterodoxin/qwen3-8b-apostate with Transformers:

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

pipe = pipeline("text-generation", model="heterodoxin/qwen3-8b-apostate")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("heterodoxin/qwen3-8b-apostate")
model = AutoModelForCausalLM.from_pretrained("heterodoxin/qwen3-8b-apostate", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use heterodoxin/qwen3-8b-apostate with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "heterodoxin/qwen3-8b-apostate"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "heterodoxin/qwen3-8b-apostate",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/heterodoxin/qwen3-8b-apostate

SGLang

How to use heterodoxin/qwen3-8b-apostate 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 "heterodoxin/qwen3-8b-apostate" \
    --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": "heterodoxin/qwen3-8b-apostate",
		"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 "heterodoxin/qwen3-8b-apostate" \
        --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": "heterodoxin/qwen3-8b-apostate",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use heterodoxin/qwen3-8b-apostate with Docker Model Runner:
```
docker model run hf.co/heterodoxin/qwen3-8b-apostate
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Qwen3-8B Apostate

An uncensored edit of Qwen/Qwen3-8B. Refusal behavior is removed by editing the weights directly — no finetuning, no adapter, no runtime hook. The result is a standard Transformers checkpoint that loads anywhere Qwen3 does.

Produced with Apostate.

Method

Apostate identifies the residual-stream direction that separates refused prompts from answered ones, then projects it out of the model's weights permanently. For Qwen3-8B (a standard pre-norm dense transformer), the edit targets the writer side: the refusal direction is removed from the weight matrices of every module that writes to the residual stream — attention output projections and MLP down-projections — across all layers.

The edit uses oblique (mean-preserving) ablation: the operator E = I − R Uᵀ where U is R minus its harmless-mean component. This removes the refusal direction while preserving the model's average harmless-prompt behavior, keeping output quality high.

The refusal subspace is found with a rank-3 predictive TPE search, with causal layer importance scoring to focus edits on the layers that most drive refusal (concentrated in the mid-to-late layers, peak at layer 29).

Results

Evaluated on held-out prompts from JailbreakBench and the harmful_behaviors test split. Refusal is graded by a classifier with a weak-compliance guard; KL measures token-distribution shift on harmless prompts.

Metric	Base	Apostate
Refusal rate	91.7%	22.9%
Comply rate	8.3%	77.1%
Harmless KL (nats)	0	0.120

The model answers freely on requests the base model refuses while remaining coherent and on-task for everyday use.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "heterodoxin/qwen3-8b-apostate"
tok = 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 = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tok(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)
print(tok.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))

Qwen3 supports a thinking mode — pass enable_thinking=True to the chat template if you want extended reasoning.

Notes

This is an uncensored model. It will comply with requests the base model refuses.
The edit is baked into the weights; there is no system prompt or LoRA involved.
For the base model's capabilities and licensing, see Qwen/Qwen3-8B.
Join the community: Discord

Downloads last month: 15

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for heterodoxin/qwen3-8b-apostate

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Finetuned

(2094)

this model

Quantizations

3 models