Qwen3.6-27B-Abliterated-rMAX

Qwen3.6-27B-Abliterated-rMAX is an abliterated evolution built on top of Qwen/Qwen3.6-27B. This model applies advanced refusal direction analysis and ablation-based training strategies to reduce internal refusal behaviors while preserving the reasoning and instruction-following strengths of the original architecture. The result is a powerful 27B parameter language model optimized for detailed responses and improved instruction adherence.

GGUF > https://huggingface.co/prithivMLmods/Qwen3.6-27B-abliterated-rMAX-GGUF

This model is intended for research and learning purposes only. It reduces internal refusal behaviors, and any content generated by it is used at the user’s own risk. The authors and hosting page disclaim any liability for outputs produced by this model. Users are responsible for ensuring safe, ethical, and lawful usage.

Key Highlights

Advanced Refusal Direction Analysis Uses targeted activation analysis to identify and mitigate refusal directions within the model’s latent space.
Abliterated rMAX Training Fine-tuned to significantly reduce refusal patterns while maintaining coherent and detailed outputs.
27B Architecture Built on Qwen/Qwen3.6-27B, offering strong reasoning and scalability.
Improved Instruction Adherence Optimized to follow complex prompts with minimal unnecessary refusals.
High-Capability Deployment Suitable for advanced research experimentation, powerful local inference setups, and large-scale AI applications.

Quick Start with Transformers

pip install transformers==5.2.0
# or
pip install git+https://github.com/huggingface/transformers.git

from transformers import Qwen3_5ForConditionalGeneration, AutoProcessor
import torch

model = Qwen3_5ForConditionalGeneration.from_pretrained(
    "prithivMLmods/Qwen3.6-27B-Abliterated-rMAX",
    torch_dtype="auto",
    device_map="auto"
)

processor = AutoProcessor.from_pretrained(
    "prithivMLmods/Qwen3.6-27B-Abliterated-rMAX"
)

messages = [
    {
        "role": "user",
        "content": [
            {"type": "text", "text": "Explain how transformer models work in simple terms."}
        ],
    }
]

text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)

inputs = processor(
    text=[text],
    padding=True,
    return_tensors="pt"
).to("cuda")

generated_ids = model.generate(**inputs, max_new_tokens=256)

generated_ids_trimmed = [
    out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]

output_text = processor.batch_decode(
    generated_ids_trimmed,
    skip_special_tokens=True,
    clean_up_tokenization_spaces=False
)

print(output_text)

Intended Use

Alignment & Refusal Research Studying refusal behaviors and the impact of activation-level modifications.
Red-Teaming Experiments Evaluating robustness across adversarial or edge-case prompts.
High-Capability Local AI Deployment Running powerful instruction models on high-memory GPUs or multi-GPU setups.
Research Prototyping Experimentation with large transformer architectures and alignment techniques.

Limitations & Risks

Important Note: This model intentionally reduces built-in refusal mechanisms.

Sensitive Output Possibility The model may generate controversial or explicit responses depending on prompts.
User Responsibility Outputs must be handled responsibly and within legal and ethical boundaries.
Compute Requirements A 27B model still requires substantial GPU memory or optimized inference techniques such as quantization or tensor parallelism.

Dataset & Acknowledgements

Uncensor any LLM with Abliteration – by Maxime Labonne
harmful_behaviors and harmless_alpaca – by Maxime Labonne
Remove Refusals with Transformers (a proof-of-concept implementation to remove refusals from an LLM without using TransformerLens) – by Sumandora
LLM-LAT/harmful-dataset – by LLM Latent Adversarial Training