llmfan46/Qwen3.5-27B-Writer-V2-uncensored-heretic-GGUF
<div style="background-color: #ff4444; color: white; padding: 20px; border-radius: 10px; text-align: center; margin: 20px 0;"> <h2 style="color: white; margin: 0 0 10px 0;">🚨⚠️ I HAVE REACHED HUGGING FACE'S FREE STORAGE LIMIT ⚠️🚨</h2> <p style="font-size: 18px; margin: 0 0 15px 0;">I can no longer upload new models unless I can cover the cost of additional storage.<br>I host <b>70+ free models</b> as an independent contributor and this work is unpaid.<br><b>Without your support, no more new models can be uploaded.</b></p> <p style="font-size: 20px; margin: 0;"> <a href="https://patreon.com/LLMfan46" style="color: white; text-decoration: underline;">🎉 Patreon (Monthly)</a> | <a href="https://ko-fi.com/llmfan46" style="color: white; text-decoration: underline;">☕ Ko-fi (One-time)</a> </p> <p style="font-size: 16px; margin: 10px 0 0 0;">Every contribution goes directly toward Hugging Face storage fees to keep models free for everyone.</p> </div>
91% fewer refusals (8/100 Uncensored vs 93/100 Original) while preserving model quality (0.0274 KL divergence).
❤️ Support My Work
Creating these models takes significant time, work and compute. If you find them useful consider supporting me:
Your help will motivate me and would go into further improving my workflow and coverings fees for storage, compute and may even help uncensoring bigger model with rental Cloud GPUs.
GGUF quantizations of llmfan46/Qwen3.5-27B-Writer-V2-uncensored-heretic.
This model is great for creative writing and translation, the original base model writing and translations feels a litle stiff which might not really read very nicely some times, Qwen3.5-27B-Writer-V2-uncensored-heretic aims to fix this issue and improve the writing quality of Qwen3.5-27B.
This is a decensored version of ConicCat/Qwen3.5-27B-Writer-V2, made using Heretic v1.2.0 with the Arbitrary-Rank Ablation (ARA) method
Abliteration parameters
Targeted components
- attn.o_proj
- attn.out_proj
Performance
Lower refusals indicate fewer content restrictions, while lower KL divergence indicates more closeness to the original model's baseline. Higher refusals cause more rejections, objections, pushbacks, lecturing, censorship, softening and deflections.
MMLU test results:
<span style="color:blue">Original:</span>
<span style="color:darkgreen">Heretic:</span>
MMLU - Massive Multitask Language Understanding, multiple-choice questions across 57 subjects (math, history, law, medicine, etc.).
Quantizations
Vision Projector
A Vision Projector File is Required for vision/multimodal capabilities. Use alongside any quantization above.
Usage
Works with llama.cpp, LM Studio, Ollama, and other GGUF-compatible tools.
ConicCat/Qwen3.5-27B-Writer-V2
A tentative second version. Hopefully, it's better.
A writing & roleplay finetune of Qwen3.5 27B. The primary emphasis is on writing quality as it strongly generalizes across both domains.
The basic idea is to use a curriculum learning setup to overcome the lack of high quality roleplay data by first training on lower quality roleplay data, then training on higher quality writing data. Starting from ConicCat/Qwen3.5-Antirep-27B, the model was trained on a roughly equal mixture of instruct / roleplay / writing data for three epochs. The model was then trained for eleven epochs on a smaller dataset of book chunks.
Recommended Settings
- Chatml template with
<think>\n\n</think>\nprefill or<think>\nprefill. Should think less! - temperature =
0.7 - top_p =
0.95 - A moderate dry penalty of ~
0.4-0.8should work well. - For quants, Q4KM runs well with
~100kcontext on 24GB Vram - IQ4_XS should fit on 16GB Vram with about
20-24kcontext with the vulkan backend, although it's pretty tight and may require some fiddling around with open programs e.t.c.
Datasets
- ConicCat/AntiRep to mitigate repetitition.
- internlm/Condor-SFT-20K for instruct; even though instruct capabilities are not the primary focus, adding some instruct data helps mitigate forgetting and maintains general intellect and instruction following capabilites.
- ConicCat/Gutenberg-SFT. A reformatted version of the original Gutenberg DPO dataset by jondurbin for SFT with some slight augmentation to address many of the samples being overly long.
- ConicCat/MiniC2_V3.2. The venerable C2, with cleaned and reformatted system prompts, and all user / assistant turns replaced by V3.2.
- A dataset of backtranslated books. Unfortunately, I am unable to release this set as all of the data is under copyright.