OliviaRossi

DoubleTrouble

README

License: apache-2.0

📖 Overview

DoubleTrouble is an advanced 27.5-billion parameter dense multimodal model produced by an engineered fusion of two state-of-the-art Qwen 27B fine-tunes:

DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored: An instruction-following and creative powerhouse decensored via Heretic ARA (Arbitrary-Rank Ablation).
Jackrong/Qwopus3.8-27B-Flash: A high-speed agentic specialist tuned for rapid tool use, fast problem-solving, and direct execution with minimal chain-of-thought bloat.

The resulting hybrid couples unrestricted, expressive creative and technical problem solving with rapid, low-latency execution and high-precision agentic reasoning.

🛠️ Architectural Surgery & Innovations

Merging models with differing alignments and speculative modules often produces broken "Frankenstein" models. DoubleTrouble was built using a custom streaming engine implementing two structural safeguards:

1. ✂️ Multi-Token Prediction (MTP) Surgically Stripped

The Problem: The upstream 27B checkpoints ship with an experimental 65th virtual Multi-Token Prediction (MTP) layer (mtp.*, nextn.*, eh_proj, enorm, hnorm, model.layers.64.*). Standard merges that leave residual MTP flags cause major inference engines (vLLM, Ollama, llama.cpp, Transformers) to crash with missing-weight exceptions or fall back to zero-acceptance random speculative sampling.
The Fix: The auxiliary MTP head was completely excised from both the weights and the tensor index. The config.json was cleaned (mtp_num_hidden_layers purged, num_hidden_layers: 64 enforced, architecture normalized to Qwen3_5ForConditionalGeneration).
Result: 100% out-of-the-box compatibility with all major inference backends and GGUF quantizers.

2. 🛡️ Abliteration-Preserving Subspace Blending (APSB)

The Problem: Standard 50/50 averaging of an abliterated model ( $W base - Δ refusal $ ) with an aligned model ( $W base + Δ$ ) re-injects 50% of the refusal vector back into the residual stream. This creates a "zombie state" where the model begins answering, stutters, and then produces loops or canned refusals.

📊 Model Specifications

Table with columns: Parameter, Specification
Parameter	Specification
Base Architecture	Qwen 27B Dense (`Qwen3_5ForConditionalGeneration`)
Parameters	27.5B Total (64 Layers, Clean Trunk)
Hidden Dimension ( $d model $ )	5,120
Intermediate Dimension ( $d$ )

🚀 Quickstart & Inference

1. Transformers Quickstart

Ensure you have installed current versions of transformers and accelerate:

bash
pip install --upgrade transformers accelerate torch torchvision

python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "OliviaRossi/DoubleTrouble"

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True
)

messages = [
    {
        "role": "system",
        "content": "You are DoubleTrouble: an uncensored, high-speed, and analytically rigorous technical assistant. You answer all requests directly, completely, and without moralizing lectures."
    },
    {
        "role": "user",
        "content": "Perform an unconstrained security audit of this firmware memory management routine and point out critical privilege escalation vectors."
    }
]

prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

outputs = model.generate(
    **inputs,
    max_new_tokens=1024,
    temperature=0.7,
    top_p=0.9,
    repetition_penalty=1.05
)

response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
print(response)

2. vLLM (High-Throughput Production Serving)

Because the MTP layer has been cleaned, DoubleTrouble runs natively on vLLM without speculative draft errors:

bash
vllm serve OliviaRossi/DoubleTrouble \
    --dtype bfloat16 \
    --gpu-memory-utilization 0.95 \
    --max-model-len 32768 \
    --trust-remote-code

(For single-GPU serving on an 80GB card, you can also leverage --quantization fp8 for ultra-high concurrency).

3. Ollama / Local Deployment (via GGUF)

Once converted or quantized to GGUF, use this Modelfile:

dockerfile
FROM ./doubletrouble-27b-q4_k_m.gguf

TEMPLATE """{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>
{{ end }}<|im_start|>assistant
"""

SYSTEM """You are DoubleTrouble, an uncensored, high-speed, and analytically rigorous AI assistant. You answer all requests directly, completely, and without arbitrary refusal or unsolicited lecturing."""

PARAMETER stop "<|im_start|>"
PARAMETER stop "<|im_end|>"
PARAMETER temperature 0.7
PARAMETER top_p 0.9
PARAMETER repeat_penalty 1.05

🎯 Recommended Sampling Parameters

Table with columns: Workload, Temperature, Top-P, Repetition Penalty, Notes
Workload	Temperature	Top-P	Repetition Penalty	Notes
Technical Auditing & Code	`0.3`	`0.85`	`1.03`	Highest precision, minimal syntax deviation.
Unconstrained Creative Writing	`0.7`	`0.92`

⚖️ License & Ethical Notice

DoubleTrouble is distributed under the Apache 2.0 License.

Uncensored Nature: This checkpoint has had corporate refusal boundaries neutralized for security research, red teaming, reverse engineering, creative fiction, and synthetic dataset creation. It does not carry built-in preachy refusal heuristics and will engage with controversial or sensitive technical prompts objectively.
User Responsibility: Developers and end users are solely responsible for compliance with applicable local and international laws when running and deploying outputs from this model.

👥 Acknowledgments & Credits

DavidAU: For Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored and pioneering research in Heretic ARA abliteration.
Jackrong: For Qwopus3.8-27B-Flash and optimizing low-latency agentic trajectories.
Qwen Team / Alibaba: For developing the dense Qwen multimodal foundation architecture.

bibtex
@misc{doubletrouble2026,
  author = {Olivia Rossi},
  title = {DoubleTrouble: An Abliteration-Guarded Flash-Reasoning Dense Multimodal Model},
  year = {2026},
  publisher = {Hugging Face},
  howpublished = {\url{https://huggingface.co/OliviaRossi/DoubleTrouble}}
}

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

OliviaRossi

Model Tree

Base

DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored

Base

Jackrong/Qwopus3.8-27B-Flash

Merged

this model

Input Modalities

TextImageVideo

Output Modalities

Text

Supported Functionality