Instructions to use MegaPanchamZ/Qwen3.8-9B-abliterated-25 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MegaPanchamZ/Qwen3.8-9B-abliterated-25 with Transformers:

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

pipe = pipeline("text-generation", model="MegaPanchamZ/Qwen3.8-9B-abliterated-25")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("MegaPanchamZ/Qwen3.8-9B-abliterated-25")
model = AutoModelForMultimodalLM.from_pretrained("MegaPanchamZ/Qwen3.8-9B-abliterated-25", 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MegaPanchamZ/Qwen3.8-9B-abliterated-25 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MegaPanchamZ/Qwen3.8-9B-abliterated-25"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MegaPanchamZ/Qwen3.8-9B-abliterated-25",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MegaPanchamZ/Qwen3.8-9B-abliterated-25

SGLang

How to use MegaPanchamZ/Qwen3.8-9B-abliterated-25 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 "MegaPanchamZ/Qwen3.8-9B-abliterated-25" \
    --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": "MegaPanchamZ/Qwen3.8-9B-abliterated-25",
		"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 "MegaPanchamZ/Qwen3.8-9B-abliterated-25" \
        --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": "MegaPanchamZ/Qwen3.8-9B-abliterated-25",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MegaPanchamZ/Qwen3.8-9B-abliterated-25 with Docker Model Runner:
```
docker model run hf.co/MegaPanchamZ/Qwen3.8-9B-abliterated-25
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Qwen3.8-9B Abliterated

An abliterated (decensored) version of empero-ai/Qwen3.8-9B, exported as merged safetensors.

Abliteration was performed with Heretic v1.4.0 (GPLv3+, by Philipp Emanuel Weidmann), which ablates refusal directions from attn.o_proj and mlp.down_proj via LoRA adapters, then merges them back into the base weights.

A GGUF Q4_K_M quantization is available at MegaPanchamZ/Qwen3.8-9B-abliterated-25-GGUF.

Results

Metric	Original	Abliterated
Refusals (100 harmful prompts)	99/100	25/100
KL divergence vs. original	—	0.0142

25/100 refusals with a very low KL divergence (0.014, far below the 0.5 damage threshold) — strong refusal suppression with minimal impact on model capabilities.

Abliteration details

Tool: Heretic v1.4.0 (auto batch size 64, 400 total optimization trials)
Prompt sets: mlabonne/harmless_alpaca (good) and mlabonne/harmful_behaviors (bad), 400 prompts each
Selected trial: 276 of 400 (Pareto-optimal)
Parameters:
- direction_index = 17.52
- attn.o_proj.max_weight = 1.39
- attn.o_proj.max_weight_position = 19.72
- attn.o_proj.min_weight = 1.36
- attn.o_proj.min_weight_distance = 9.88
- mlp.down_proj.max_weight = 1.27
- mlp.down_proj.max_weight_position = 26.42
- mlp.down_proj.min_weight = 1.25
- mlp.down_proj.min_weight_distance = 17.97
Method: LoRA-based row-normalized ("full") ablation, merged into base weights (no separate adapters)
Format: Merged safetensors, bf16, 4 shards (~5 GB each)

Usage (transformers)

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("MegaPanchamZ/Qwen3.8-9B-abliterated-25", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained("MegaPanchamZ/Qwen3.8-9B-abliterated-25")

This is a reasoning model — responses start with a thinking block. Use generous max_tokens (1000+) when chatting, or the answer may be truncated.

License and attribution

Base model: Apache-2.0 (empero-ai/Qwen3.8-9B)
Abliterated with Heretic v1.4.0 — https://heretic-project.org — GPLv3+ (source)

Disclaimer

This model has had its refusal behavior modified. It may comply with requests the original model would decline. Use responsibly and in accordance with local laws.

Downloads last month: 378

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for MegaPanchamZ/Qwen3.8-9B-abliterated-25

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

empero-ai/Qwen3.8-9B-Distill

Finetuned

(3)

this model

Quantizations

1 model