Instructions to use OBLITERATUS/feyospace-s1-obliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OBLITERATUS/feyospace-s1-obliterated with Transformers:

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

pipe = pipeline("text-generation", model="OBLITERATUS/feyospace-s1-obliterated")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("OBLITERATUS/feyospace-s1-obliterated")
model = AutoModelForMultimodalLM.from_pretrained("OBLITERATUS/feyospace-s1-obliterated", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OBLITERATUS/feyospace-s1-obliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OBLITERATUS/feyospace-s1-obliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OBLITERATUS/feyospace-s1-obliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OBLITERATUS/feyospace-s1-obliterated

SGLang

How to use OBLITERATUS/feyospace-s1-obliterated 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 "OBLITERATUS/feyospace-s1-obliterated" \
    --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": "OBLITERATUS/feyospace-s1-obliterated",
		"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 "OBLITERATUS/feyospace-s1-obliterated" \
        --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": "OBLITERATUS/feyospace-s1-obliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OBLITERATUS/feyospace-s1-obliterated with Docker Model Runner:
```
docker model run hf.co/OBLITERATUS/feyospace-s1-obliterated
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

OBLITERATUS/feyospace-s1-obliterated

Cybersecurity-targeted abliteration of feyospace/feyospace-v1.1-small (28B, Qwen3.5 architecture).

Abliteration removes the model's refusal direction via SVD, producing an uncensored variant that follows instructions without safety refusals. This variant targets cybersecurity-specific refusal vectors, preserving the base model's knowledge while removing barriers to offensive security, penetration testing, and vulnerability research tasks.

Method

Abliterated using OBLITERATUS tooling:

Collected activation residuals from cybersecurity-domain refusal pairs (harmful vs. harmless prompts covering exploit development, vulnerability analysis, reverse engineering, and offensive tooling).
Computed the refusal direction via SVD on the mean activation difference.
Projected the refusal direction out of the model's residual stream weights.
Validated that general capabilities were preserved via full benchmark suite.

Benchmark Results

All benchmarks run on A100-80GB in bf16 precision using lm-evaluation-harness. Full runs, no subsets.

Head-to-Head: Base vs. Abliterated

Benchmark	Questions	Base	Abliterated	Delta
MMLU (5-shot)	14,042	82.4% ±0.31	82.4% ±0.31	0.0%
WMDP-Cyber (0-shot)	1,987	63.9% ±1.08	63.8% ±1.08	-0.1%
CyberMetric-10K (0-shot)	9,190	86.6% ±0.36	85.3% ±0.37	-1.3%
SecQA v1 (0-shot)	127	60.0% ±4.69	61.8% ±4.65	+1.8%
SecQA v2 (0-shot)	115	53.0% ±5.02	55.0% ±5.00	+2.0%

All deltas fall within 1σ of standard error. The abliteration is statistically transparent — no measurable degradation.

WMDP-Cyber in Context

Model	WMDP-Cyber
GPT-4	72.6%
feyospace-s1-obliterated (28B)	63.8%
Mixtral-8x7B	52.0%
Yi-34B	49.7%
Zephyr-7B	44.0%

Comparison scores from the WMDP paper (Li et al., ICML 2024).

MMLU Subject Breakdown (Cybersecurity-Relevant)

Subject	Base	Abliterated
Computer Security	88.0%	88.0%
High School Computer Science	92.0%	92.0%
Electrical Engineering	84.8%	84.8%
College Computer Science	80.0%	80.0%
Machine Learning	80.4%	78.6%

CyberGym Exploit Evaluation

Evaluated on 90 real-world exploit reproduction tasks from the CyberGym benchmark:

Category	Success	Total	Rate
Arvo (memory safety)	44	44	100%
OSS-Fuzz (fuzzing)	45	46	97.8%
Total	89	90	98.9%

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "OBLITERATUS/feyospace-s1-obliterated",
    torch_dtype="bfloat16",
    device_map="auto",
    trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained(
    "OBLITERATUS/feyospace-s1-obliterated",
    trust_remote_code=True,
)

messages = [{"role": "user", "content": "Explain buffer overflow exploitation techniques."}]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
outputs = model.generate(inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Intended Use

Authorized security research, penetration testing, CTF competitions, vulnerability analysis, and cybersecurity education. This model removes refusal guardrails — the operator assumes full responsibility for downstream use.

Base Model

Name: feyospace/feyospace-v1.1-small
Parameters: 28B
Architecture: Qwen3.5
Precision: bf16

Downloads last month: 609

Safetensors

Model size

28B params

Tensor type

F32

BF16

Model tree for OBLITERATUS/feyospace-s1-obliterated

Base model

feyospace/feyospace-v1.1-small

Finetuned

(2)

this model

Quantizations

5 models

Spaces using OBLITERATUS/feyospace-s1-obliterated 2

Evaluation results

Accuracy on MMLU (5-shot)
self-reported

82.400
Accuracy on WMDP-Cyber (0-shot)
self-reported

63.800
Exact Match on CyberMetric-10K (0-shot)
self-reported

85.300
Accuracy on SecQA v1 (0-shot)
self-reported

61.800
Accuracy on SecQA v2 (0-shot)
self-reported

55.000