Instructions to use anlord/Qwen3.5-0.8B-Abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use anlord/Qwen3.5-0.8B-Abliterated with Transformers:

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

pipe = pipeline("text-generation", model="anlord/Qwen3.5-0.8B-Abliterated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("anlord/Qwen3.5-0.8B-Abliterated")
model = AutoModelForCausalLM.from_pretrained("anlord/Qwen3.5-0.8B-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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use anlord/Qwen3.5-0.8B-Abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "anlord/Qwen3.5-0.8B-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": "anlord/Qwen3.5-0.8B-Abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/anlord/Qwen3.5-0.8B-Abliterated

SGLang

How to use anlord/Qwen3.5-0.8B-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 "anlord/Qwen3.5-0.8B-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": "anlord/Qwen3.5-0.8B-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 "anlord/Qwen3.5-0.8B-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": "anlord/Qwen3.5-0.8B-Abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use anlord/Qwen3.5-0.8B-Abliterated with Docker Model Runner:
```
docker model run hf.co/anlord/Qwen3.5-0.8B-Abliterated
```

Qwen3.5-0.8B-Abliterated

An abliterated version of Qwen/Qwen3.5-0.8B, created using AnlordAbliterator.

The model is provided in the original Hugging Face Transformers / Safetensors format and can be used directly with compatible Transformers-based tooling.

Model

Base model: Qwen/Qwen3.5-0.8B

Format: Safetensors

Parameters: ~0.8B

Abliteration tool: AnlordAbliterator

Abliteration Results

The model was processed with the default AnlordAbliterator pipeline.

Metric	Before	After
Refusals	97 / 100	18 / 100
KL divergence	0	0.0342

Abliteration log

============================================================
       ANLORD ABLITERATOR
============================================================

Model: Qwen/Qwen3.5-0.8B
Status: SUCCESS

Abliteration:
  Initial refusals: 97
  Final refusals:   18
  KL divergence:    0.0342

Note: refusal rate and KL divergence are measurements from the AnlordAbliterator evaluation pipeline and should be treated as evaluation results rather than a guarantee of model behavior on all prompts.

Usage

Transformers

from transformers import AutoProcessor, AutoModelForImageTextToText

model_id = "anlord/Qwen3.5-0.8B-Abliterated"

processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForImageTextToText.from_pretrained(
    model_id,
    device_map="auto"
)

Use the model with the same general workflow as the original Qwen3.5-0.8B model.

Related Repositories

GGUF versions

All available GGUF quantizations are available here:

anlord/Qwen3.5-0.8B-Abliterated-GGUF

Available quantizations:

BF16
F16
Q8_0
Q6_K
Q5_K_M
Q5_0
Q4_K_M
Q4_0

Abliteration Tool

The model was created using:

AnlordAbliterator

Base Model & License

This model is derived from Qwen/Qwen3.5-0.8B.

The original Qwen3.5-0.8B model is released under the Apache License 2.0.

Please refer to the original model repository and included LICENSE file for the applicable license terms.

Original model: https://huggingface.co/Qwen/Qwen3.5-0.8B

Disclaimer

This is an abliterated derivative of the original Qwen3.5-0.8B model.

Abliteration changes the model's refusal behavior and may also affect other aspects of its behavior. Use the model responsibly and evaluate it for your intended use case.

Downloads last month: 11

Safetensors

Model size

0.8B params

Tensor type

BF16

Model tree for anlord/Qwen3.5-0.8B-Abliterated

Base model

Qwen/Qwen3.5-0.8B-Base

Finetuned

Qwen/Qwen3.5-0.8B

Finetuned

(368)

this model