license: apache-2.0
tags:

• text-generation-inference
• moe
• uncensored
• abliterated
• unfiltered
• unredacted
• refusal-ablated
• vllm
• pytorch
• bf16
• max
• alignment-modified
• reasoning
• v2.0
  base_model:
• Qwen/Qwen3.5-35B-A3B
  language:
• en
  pipeline_tag: image-text-to-text
  library_name: transformers

Qwen3.5-35B-A3B-abliterated-v2-MAX

Qwen3.5-35B-A3B-abliterated-v2-MAX is an optimized release built on top of huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated. This version focuses on updated shard sizing, repository optimization, and compatibility improvements for the latest Transformers releases, while preserving the reasoning and instruction-following capabilities of the original model. The result is a powerful 35B parameter Mixture-of-Experts language model designed for efficient deployment, stable inference, and modern ecosystem integration.

[!IMPORTANT]
This model is developed for research and learning purposes only. Any content generated by this model is used at the user's own risk. The authors and hosting platform disclaim any liability for outputs produced by this model. Users are responsible for ensuring safe, ethical, and lawful usage.

Compression for the Model

Qwen3.5-35B-A3B-abliterated-v2-MAX

Key Highlights

• Latest Transformers Compatibility
  Re-sharded and optimized for improved compatibility with recent Transformers releases.

• Optimized Model Sharding
  Updated shard structure for better storage handling, download reliability, and inference efficiency.

• Stable Inference Pipeline
  Improved packaging for consistent loading and generation behavior across environments.

• 35B MoE Architecture (A3B)
  Built on Qwen3.5-35B-A3B, leveraging Mixture-of-Experts design for scalable reasoning capacity.

• Improved Deployment Stability
  Designed for smoother inference across different hardware configurations and runtimes.

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

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-Qwen3.5-35B-A3B-abliterated.

Quick Start with Transformers

pip install transformers==5.5.0
# or
pip install git+https://github.com/huggingface/transformers.git

from transformers import Qwen3_5MoeForConditionalGeneration, AutoProcessor
import torch

model = Qwen3_5MoeForConditionalGeneration.from_pretrained(
    "prithivMLmods/Qwen3.5-35B-A3B-abliterated-v2-MAX",
    torch_dtype="auto",
    device_map="auto"
)

processor = AutoProcessor.from_pretrained(
    "prithivMLmods/Qwen3.5-35B-A3B-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 large-scale MoE behavior and inference characteristics.

• Red-Teaming & Evaluation
  Testing robustness across complex and adversarial prompts.

• High-Performance Deployment
  Running large MoE models on optimized multi-GPU setups.

• Research Prototyping
  Experimentation with scalable transformer architectures and deployment workflows.

Limitations & Risks

Important Note: This model inherits the behavior and limitations of its base model.

• Output Variability
  Responses may vary depending on sampling settings and prompt structure.

• Resource Requirements
  A 35B MoE model requires significant GPU memory or optimized inference strategies such as quantization or tensor parallelism.

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

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