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

Libraries

How to use mlabonne/Qwen3-8B-abliterated with Transformers:

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

pipe = pipeline("text-generation", model="mlabonne/Qwen3-8B-abliterated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mlabonne/Qwen3-8B-abliterated")
model = AutoModelForCausalLM.from_pretrained("mlabonne/Qwen3-8B-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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mlabonne/Qwen3-8B-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlabonne/Qwen3-8B-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": "mlabonne/Qwen3-8B-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mlabonne/Qwen3-8B-abliterated

SGLang

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

Docker Model Runner
How to use mlabonne/Qwen3-8B-abliterated with Docker Model Runner:
```
docker model run hf.co/mlabonne/Qwen3-8B-abliterated
```

mlabonne commited on May 18, 2025

Commit

1d6d6e6

verified ·

1 Parent(s): 8483eaf

Upload Qwen3ForCausalLM

Browse files

Files changed (7) hide show

model-00001-of-00007.safetensors +1 -1
model-00002-of-00007.safetensors +1 -1
model-00003-of-00007.safetensors +1 -1
model-00004-of-00007.safetensors +1 -1
model-00005-of-00007.safetensors +1 -1
model-00006-of-00007.safetensors +1 -1
model-00007-of-00007.safetensors +1 -1

model-00001-of-00007.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6457406fb268f03cb6ef83b1737e8d558543714819bb19fc81a39320f5d1a4af
 size 4972454376

 version https://git-lfs.github.com/spec/v1
+oid sha256:1bb5b117f658523c75c92b3851e379492d5e4a8e46fbe1463b852b868d9f2bda
 size 4972454376

model-00002-of-00007.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:391513c14ed1e8bf0ff10052ae130a6930fcde47bcddb2e515fada56784ac6e6
 size 4832048608

 version https://git-lfs.github.com/spec/v1
+oid sha256:8a6668e7319ecb3f3acbb227fdfcbcaa0cd95c188984323852c6d25e6908e419
 size 4832048608

model-00003-of-00007.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9bf1d5ef5371133768bafc808863c96429778bca124de1769ee3e4fa342349d
 size 4832048656

 version https://git-lfs.github.com/spec/v1
+oid sha256:7e6139206c3f7c778334a3980c28e5be222ea2f94e6d0b0ab139d2cc0ef31880
 size 4832048656

model-00004-of-00007.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3914ae7ead4c506ff004e3f5a5e8f71c03f84e3dca581c2c863002ae9ecc7948
 size 4999855528

 version https://git-lfs.github.com/spec/v1
+oid sha256:c0ee9ffd6130465878d2e908babb41f7786daea865b67e514a2e831837e45961
 size 4999855528

model-00005-of-00007.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a88eecd1032080b15ea53a9f0d61f2e87f786acf9c1d3e3e33c85a83de08347
 size 4832048672

 version https://git-lfs.github.com/spec/v1
+oid sha256:1e8ccee00e4d556e00f6c54934f804156a6e464e7f0b79e94d3cb249ab3c1464
 size 4832048672

model-00006-of-00007.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:799588ac855a93121d84e9c2985cf61655ee8ec58bd725a645518d38c7f806e3
 size 4832048672

 version https://git-lfs.github.com/spec/v1
+oid sha256:ecbff6633142c99d61a4287e61049177c82526c7295a8258027a3d6ee59ce598
 size 4832048672

model-00007-of-00007.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc05cd8665c0bf5ceda5fecec72a2b869777a5b604c2bacc3038471b63057ac6
 size 3462482728

 version https://git-lfs.github.com/spec/v1
+oid sha256:a73aac17dc5253f04c1aef1a09e9d8b97c817af244e7d74ae05de166e6329f86
 size 3462482728