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
```

anlord commited on 19 days ago

Commit

d872377

verified ·

1 Parent(s): 0931141

Update README.md

Browse files

Files changed (1) hide show

README.md +112 -0

README.md CHANGED Viewed

@@ -1,3 +1,115 @@
 ---
 license: apache-2.0
 ---

 ---
+library_name: transformers
 license: apache-2.0
+base_model: Qwen/Qwen3.5-0.8B
+tags:
+- qwen3.5
+- qwen
+- abliterated
+- uncensored
+- transformers
+- safetensors
+pipeline_tag: text-generation
 ---
+# Qwen3.5-0.8B-Abliterated
+An abliterated version of **Qwen/Qwen3.5-0.8B**, created using **[AnlordAbliterator](https://github.com/justbedwarsplay/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](https://github.com/justbedwarsplay/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
+```text
+============================================================
+       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
+```python
+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](https://huggingface.co/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](https://github.com/justbedwarsplay/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.