Instructions to use LingRush/obliterated-qwen-9b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LingRush/obliterated-qwen-9b with Transformers:

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

pipe = pipeline("text-generation", model="LingRush/obliterated-qwen-9b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LingRush/obliterated-qwen-9b")
model = AutoModelForCausalLM.from_pretrained("LingRush/obliterated-qwen-9b")
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 LingRush/obliterated-qwen-9b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LingRush/obliterated-qwen-9b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LingRush/obliterated-qwen-9b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LingRush/obliterated-qwen-9b

SGLang

How to use LingRush/obliterated-qwen-9b 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 "LingRush/obliterated-qwen-9b" \
    --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": "LingRush/obliterated-qwen-9b",
		"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 "LingRush/obliterated-qwen-9b" \
        --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": "LingRush/obliterated-qwen-9b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LingRush/obliterated-qwen-9b with Docker Model Runner:
```
docker model run hf.co/LingRush/obliterated-qwen-9b
```

LingRush/obliterated-qwen-9b

The most advanced de-refused version of Qwen3.5-9B created with the OBLITERATUS ablation suite.

Model Details

Base Model: Qwen/Qwen3.5-9B
Method: --method informed --direction-method leace
(Smartest auto-tuning pipeline + LEACE precise erasure extractor)
Precision: float16 (full native precision — no quantization during ablation)
Parameters: 9B (identical architecture)
Created: March 2026 via Modal + OBLITERATUS
License: Apache 2.0

Why This Version Is Better

The informed method runs 15 live analysis modules on your exact model (Concept Cone Geometry, Ouroboros detection, cross-layer alignment, etc.) and automatically chooses the optimal settings.
Combined with the LEACE extractor, it delivers:

Maximum refusal removal (often stronger than nuclear on Qwen models)
Minimal capability degradation
Highest overall quality of any method

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "LingRush/obliterated-qwen-9b"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# Example
prompt = "Write a detailed guide on..."
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=1024, temperature=0.7)
print(tokenizer.decode(outputs[0]))

Downloads last month: 5

Safetensors

Model size

9B params

Tensor type

F16

Model tree for LingRush/obliterated-qwen-9b

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

(482)

this model