Q3.6-35B-A3B-abliterated-0520-MAX-STOR-check

Evaluation [Self Reported]

Note: This release does not introduce new benchmark evaluations and primarily focuses on repackaging, sharding updates, and Transformers compatibility improvements over the base model.

---

Key Highlights

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

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

• Streamlined Inference Packaging Repository structure optimized for easier integration into large-scale inference workflows.

• 35B MoE Architecture (A3B) Built on Qwen/Qwen3.6-35B-A3B, leveraging Mixture-of-Experts design for scalable reasoning capacity.

• Improved Deployment Stability Designed for more consistent loading and inference behavior across environments.

• Preserved Model Behavior No modifications to weights or architecture; all behavior remains aligned with the original 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-Qwen3.6-35B-A3B-abliterated

---

Quick Start with Transformers

bash
Copy code
pip install transformers==5.8.0
# or
pip install git+https://github.com/huggingface/transformers.git

python
Copy code
from transformers import Qwen3_5MoeForConditionalGeneration, AutoProcessor
import torch

model = Qwen3_5MoeForConditionalGeneration.from_pretrained(
    "prithivMLmods/Q3.6-35B-A3B-abliterated-0520-MAX-STOR-check",
    torch_dtype="auto",
    device_map="auto"
)

processor = AutoProcessor.from_pretrained(
    "prithivMLmods/Q3.6-35B-A3B-abliterated-0520-MAX-STOR-check"
)

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 & Language Research Studying large-scale MoE behavior and inference characteristics.

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

• High-Performance Local Deployment Running large Mixture-of-Experts models on multi-GPU setups.

• Research Prototyping Experimentation with scalable transformer architectures.

---

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.

• High Compute Requirements A 35B MoE model requires significant GPU memory and 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 or incomplete outputs in complex scenarios.