Instructions to use xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic with Transformers:

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

pipe = pipeline("text-generation", model="xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic")
model = AutoModelForMultimodalLM.from_pretrained("xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic

SGLang

How to use xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic 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 "xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic" \
    --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": "xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic",
		"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 "xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic" \
        --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": "xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic with Docker Model Runner:
```
docker model run hf.co/xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic
```

Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic

File size: 3,390 Bytes

f5b5185

# Reproduction guide

This directory contains the necessary information and assets to reproduce the results obtained during this Heretic run.
> [!IMPORTANT]
> **Git installation**
>
> This system installed Heretic from a Git repository: https://github.com/p-e-w/heretic.git @ 66a952b49b00bfd1854bdad769fee5fb225b53be
>
> To reproduce the model, you must install Heretic from this exact repository and commit.


## Models

- **Base model:** [xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge](https://huggingface.co/xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge) (Commit: [`f03e5d9`](https://huggingface.co/xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge/commit/f03e5d9e1603ca871380f435b5fea8f315a12259))

## Datasets

- [mlabonne/harmful_behaviors](https://huggingface.co/datasets/mlabonne/harmful_behaviors) (Commit: [`01cead0`](https://huggingface.co/datasets/mlabonne/harmful_behaviors/commit/01cead01398926d81f7c52bdb790ee8cf77ebba7))
- [mlabonne/harmless_alpaca](https://huggingface.co/datasets/mlabonne/harmless_alpaca) (Commit: [`02c6a92`](https://huggingface.co/datasets/mlabonne/harmless_alpaca/commit/02c6a92cfcf11bb0c387334f8146d149d65b587f))

## Selected trial

- **Trial number:** 50
- **Refusals:** 3/100 (baseline: 95/100)
- **KL divergence:** 0.0883 (baseline: 0 *(by definition)*)

## Environment

- **Heretic:** v2.0.0.dev0 (Origin: Git (https://github.com/p-e-w/heretic.git @ 66a952b49b00bfd1854bdad769fee5fb225b53be))
- **PyTorch:** 2.11.0+cu130
- **Other dependencies:** See [`requirements.txt`](requirements.txt).

## Contents of this directory

- [`requirements.txt`](requirements.txt): The exact versions of all Python packages.
- [`config.toml`](config.toml): The exact configuration used, including the RNG seed.
- [`xtools-at--Qwen3--5-4B-MultiDistill-Megamix-8xMerge.jsonl`](xtools-at--Qwen3--5-4B-MultiDistill-Megamix-8xMerge.jsonl): The Optuna study journal containing the history of all trials.
- [`SHA256SUMS`](SHA256SUMS): Cryptographic hashes for all weight files.
- [`reproduce.json`](reproduce.json): A machine-readable file containing all reproducibility information.

## How to reproduce

> [!TIP]
> You can automate this process, including all verification steps, by downloading the `reproduce.json` file and running
> `heretic --reproduce reproduce.json`.

1. Install the exact version of Heretic indicated in the **Environment** section above, from its original source.
1. Install the packages listed in `requirements.txt`: `pip install -r requirements.txt`
1. Install the correct version of PyTorch: `pip install torch==2.11.0+cu130 --index-url https://download.pytorch.org/whl/cu130`
1. Place the provided `config.toml` in your working directory.
1. Run Heretic without any additional arguments: `heretic`
1. Wait for the run to finish, then select trial **50** and export the model.
1. Verify that the weight files have been exactly reproduced by comparing their SHA-256 hashes against those in `SHA256SUMS`:
   `sha256sum -c SHA256SUMS` (or look at the hashes online if you uploaded to Hugging Face)

> [!TIP]
> To use the included Optuna study journal `xtools-at--Qwen3--5-4B-MultiDistill-Megamix-8xMerge.jsonl`, place it in the checkpoints directory (usually `checkpoints/`) before running Heretic.
>
> This allows you to export other models from the Pareto front, or to run additional trials without having to re-run the stored trials.