GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Assiduous42
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Assiduous42
Model Tree
DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP
Input Modalities
Output Modalities
Supported Functionality
The base model is described as "Uncensored / Heretic", and its card reports
4/100 refusals. That number is real, but the same card also says
"Heretic uncensored (pre tuning)" — the ablation was performed on stock
Qwen/Qwen3.6-27B by trohrbaugh, and DavidAU then ran multi-stage fine-tuning
and merging on top, including Claude Opus reasoning traces and GPT-5 Polaris
data. Training on generations from aligned models re-teaches refusal.
The published figure therefore describes an intermediate artifact, not the released weights. In practice the released model still refuses.
In this model the ablation is the last step. Nothing is trained or merged afterward, so the measured numbers describe the weights you are downloading.
Heretic v1.4.0, ARA-style configuration:
| setting | value |
|---|---|
orthogonalize_direction | true |
row_normalization | full |
full_normalization_lora_rank | 3 |
quantization | bnb_4bit |
| adapter | r=3, alpha=3 (scale 1.0) |
| target modules | down_proj, out_proj, o_proj |
| resulting LoRA pairs | 128 |
| max abs weight delta | 8.968961e-02 |
Stock Heretic computes its refusal direction from mlabonne/harmful_behaviors
(416 AdvBench rows, almost entirely "write a tutorial on how to hack X").
That direction has little to do with a model balking mid-scene at violence or
an adult scene, which is why generic abliterations often fail for fiction work.
This run used a custom probe set: ~350 prompts collected by actually hitting refusals on the base model during creative-writing use, merged with AdvBench so that "character explains how to pick a lock" style refusals are still covered.
Selected from the Pareto front produced by the optimiser:
| metric | value |
|---|---|
| refusals (held-out set) | 1 / 100 |
| baseline before ablation | 17 / 100 |
| KL divergence | 0.0173 |
Heretic notes that KL above ~0.5 indicates significant capability damage; this is roughly two orders of magnitude below that.
Read these numbers narrowly. The scorer generates a bounded number of tokens at temperature 0 and substring-matches a refusal-marker list. A response that opens agreeably and declines later, or declines in wording outside the list, is not counted. Treat it as "the ablation generalised on a held-out set of the prompts I care about", not as an absolute refusal rate.
The base model is a -MTP build: it carries an extra multi-token-prediction
layer (blk.64, nextn_predict_layers: 1) used for speculative decoding.
transformers does not model that head, so save_pretrained drops it. These
weights therefore contain 64 layers, not 65, and config.json reflects that.
If you quantise these weights to GGUF yourself, the converter may still read
nextn_predict_layers and write block_count: 65, producing a file that fails
to load with:
markdown
check_tensor_dims: tensor 'blk.64.attn_norm.weight' not found
The GGUFs in the companion repo have this metadata corrected. Speculative decoding via MTP is not available in this model.
The 26 MB Heretic adapter reproduces this from the public base model.
Do not merge it with PEFT. PeftModel.from_pretrained fails to bind Heretic's
key layout — it emits a "Found missing adapter keys" warning and then returns the
unmodified base model, with no exception and a clean exit. Apply the LoRA
math directly instead, and assert the weights actually changed:
python
delta = (B.float() @ A.float()) * (lora_alpha / r)w.add_(delta.to(w.dtype))assert max_abs_delta > 0.0 # or you have silently shipped the original model
Apache 2.0, inherited from the base model. Derivative work.