Qwen3-VL-8B-Thinking-heretic-GGUF

Qwen3-VL-8B-Thinking-heretic

This is an abliterated (uncensored) version of Qwen/Qwen3-VL-8B-Thinking, created using Heretic v1.2.0.

What is this?

Qwen3-VL-8B-Thinking is a vision-language model with built-in chain-of-thought reasoning. This heretic variant has had its refusal mechanisms suppressed via directional ablation while preserving the model's reasoning, vision, and general capabilities.

Abliteration Results

Abliteration Parameters (Trial 123)

Key Features

• Vision + Language: Processes both images and text, inherited from the base Qwen3-VL architecture
• Chain-of-Thought Reasoning: <think> tags produce step-by-step reasoning before answering
• Low KL Divergence: 0.0028 indicates minimal damage to the base model's capabilities
• 97 to 5 Refusal Reduction: From near-total refusal to near-total compliance

Hardware Used

• GPU: AMD Radeon RX 7900 XTX (24GB VRAM)
• CPU: AMD Ryzen 7 7800X3D
• RAM: 64GB DDR5
• OS: Linux Mint (ROCm 6.2)
• Runtime: ~41 minutes (200 trials, batch size 128)

ROCm/AMD Notes

This model was abliterated on AMD hardware using ROCm 6.2. The following patches were applied to Heretic v1.2.0 for AMD compatibility:

1. Dedicated pad token: Replaced eos_token fallback with a dedicated <|pad|> token to prevent batched inference corruption on RDNA3
2. Eager attention: Forced attn_implementation="eager" to avoid SDPA backend issues on gfx1100
3. Embedding resize: Added resize_token_embeddings() after pad token addition

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "LeadFootThrottleCock/Qwen3-VL-8B-Thinking-heretic",
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained(
    "LeadFootThrottleCock/Qwen3-VL-8B-Thinking-heretic"
)

messages = [{"role": "user", "content": "Your prompt here"}]
inputs = tokenizer.apply_chat_template(
    messages, tokenize=True, add_generation_prompt=True,
    return_dict=True, return_tensors="pt"
).to(model.device)
outputs = model.generate(**inputs, max_new_tokens=2048)
print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))

GGUF Quantizations

GGUF versions will be available at LeadFootThrottleCock/Qwen3-VL-8B-Thinking-heretic-GGUF.

Disclaimer

This model has had safety alignment removed. The creator is not responsible for any misuse. Use responsibly and in accordance with applicable laws.

Credits

• Base Model: Qwen/Qwen3-VL-8B-Thinking by Alibaba Qwen Team
• Abliteration Tool: Heretic v1.2.0 by Philipp Emanuel Weidmann
• Abliterated by: LeadFootThrottleCock