license: apache-2.0
tags:

• text-generation-inference
• uncensored
• abliterated
• unfiltered
• unredacted
• refusal-ablated
• vllm
• pytorch
• bf16
• max
• alignment-modified
• reasoning
• llama.cpp
• llm-compressor
  language:
• en
  base_model:
• Qwen/Qwen3.5-27B
  pipeline_tag: image-text-to-text
  library_name: transformers

Qwen3.5-27B-abliterated-v2-MAX

Qwen3.5-27B-abliterated-v2-MAX is an optimized release built on top of huihui-ai/Huihui-Qwen3.5-27B-abliterated. This version focuses on improved model sharding, packaging consistency, and compatibility with modern Transformers and inference stacks, while preserving the reasoning and instruction-following capabilities of the base model. The result is a powerful 27B parameter language model designed for stable inference, efficient deployment, and research-oriented experimentation.

[!IMPORTANT]
This model is intended strictly for research and learning purposes. Any outputs generated by this model are the sole responsibility of the user. The authors and hosting platform disclaim all liability for generated content. Users must ensure safe, ethical, and lawful usage.

Compression for the Model

Qwen3.5-27B-abliterated-v2-MAX

Base Model Signatures:

This model has been re-sharded and optimized for the latest Transformers version from the base model:
https://huggingface.co/huihui-ai/Huihui-Qwen3.5-27B-abliterated

Key Highlights

• Optimized Packaging & Sharding
  Improved repository structure for smoother downloads, loading, and deployment workflows.

• Stable Transformers Compatibility
  Updated configuration for better compatibility with modern Transformers versions and inference runtimes.

• 27B Parameter Architecture
  Built on Qwen3.5-27B, providing strong reasoning capacity and scalability.

• Efficient Deployment Design
  Structured for reliable inference across local, cloud, and multi-GPU environments.

• Preserved Model Behavior
  No changes to weights or architecture; behavior remains consistent with the original base model lineage.

• Improved Loading Reliability
  Reduced friction in model initialization and distributed inference setups.

Quick Start with Transformers

pip install transformers==5.4.0
# or
pip install git+https://github.com/huggingface/transformers.git

from transformers import Qwen3_5ForConditionalGeneration, AutoProcessor
import torch

model = Qwen3_5ForConditionalGeneration.from_pretrained(
    "prithivMLmods/Qwen3.5-27B-abliterated-v2-MAX",
    torch_dtype="auto",
    device_map="auto"
)

processor = AutoProcessor.from_pretrained(
    "prithivMLmods/Qwen3.5-27B-abliterated-v2-MAX"
)

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

• Multimodal and Language Research
  Studying behavior and scaling properties of 27B transformer models.

• Red-Teaming & Robustness Evaluation
  Testing model stability under adversarial and complex prompting conditions.

• High-Performance Deployment
  Running large models on optimized multi-GPU or cloud-based inference systems.

• Research Prototyping
  Experimentation with transformer architectures and inference optimization techniques.

Limitations & Risks

Important Note: This model inherits behavior from its base model with minimal modification.

• Output Variability
  Results may vary depending on sampling parameters and prompt structure.

• Resource Requirements
  A 27B model requires significant GPU memory or optimized inference setups such as quantization or tensor parallelism.

• Deployment Complexity
  Performance depends heavily on hardware configuration and runtime optimization.

• General Model Limitations
  May still produce incorrect, incomplete, or inconsistent outputs in complex scenarios.