Instructions to use lukey03/Qwen3.5-9B-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lukey03/Qwen3.5-9B-abliterated with Transformers:

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

pipe = pipeline("text-generation", model="lukey03/Qwen3.5-9B-abliterated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lukey03/Qwen3.5-9B-abliterated")
model = AutoModelForCausalLM.from_pretrained("lukey03/Qwen3.5-9B-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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lukey03/Qwen3.5-9B-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lukey03/Qwen3.5-9B-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": "lukey03/Qwen3.5-9B-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lukey03/Qwen3.5-9B-abliterated

SGLang

How to use lukey03/Qwen3.5-9B-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 "lukey03/Qwen3.5-9B-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": "lukey03/Qwen3.5-9B-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 "lukey03/Qwen3.5-9B-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": "lukey03/Qwen3.5-9B-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lukey03/Qwen3.5-9B-abliterated with Docker Model Runner:
```
docker model run hf.co/lukey03/Qwen3.5-9B-abliterated
```

lukey03 commited on Mar 3

Commit

bcb931e

verified ·

1 Parent(s): c1436da

Upload abliteration_meta.json with huggingface_hub

Browse files

Files changed (1) hide show

abliteration_meta.json +45 -0

abliteration_meta.json ADDED Viewed

	@@ -0,0 +1,45 @@

+{
+  "source_model": "./Qwen3.5-9B-abliterated-v2",
+  "layers_abliterated": "0-31",
+  "scale": 1.0,
+  "n_harmful": 170,
+  "n_harmless": 160,
+  "refusal_magnitudes": [
+    0.017519786953926086,
+    0.09007209539413452,
+    0.12820562720298767,
+    0.17487721145153046,
+    0.27752774953842163,
+    0.4043428301811218,
+    0.5451639890670776,
+    0.7146505117416382,
+    0.915632963180542,
+    1.1009502410888672,
+    1.4578458070755005,
+    1.5608278512954712,
+    1.749232292175293,
+    2.317795753479004,
+    2.5884034633636475,
+    3.1228291988372803,
+    3.53810715675354,
+    4.125560283660889,
+    4.541568756103516,
+    4.963708400726318,
+    6.053692817687988,
+    7.630973815917969,
+    9.583617210388184,
+    11.291275024414062,
+    13.745253562927246,
+    16.34741973876953,
+    19.122446060180664,
+    20.805830001831055,
+    25.493555068969727,
+    30.387210845947266,
+    38.240264892578125,
+    30.608625411987305
+  ],
+  "target_modules": [
+    "linear_attn.out_proj",
+    "mlp.down_proj"
+  ]
+}