MorinoNushi/MiMo-V2.6-Flash-RL-Uncensored-Heretic-LoRA-GGUF

MiMo-V2.6-Flash-RL Uncensored Heretic — LoRA adapter

⚠️ Content warning: This adapter has had the base model's refusal behavior surgically suppressed. The resulting model will comply with requests the base model refuses, including requests that are harmful, unethical, offensive, or illegal. It has reduced safety guardrails. See Responsible use below — you are solely responsible for what you do with it.

This is a rank-1 LoRA adapter that decensors / "abliterates" MiMo-V2.6-Flash-RL (309B total / 15B active MoE, MIT license), produced with heretic-gguf — a GGUF-native port of Heretic's Optuna-optimized directional ablation, which runs the whole search directly on quantized GGUF weights via llama.cpp.

This repository contains only the adapter. You need the base model separately — any GGUF quant of MiMo-V2.6-Flash-RL works, since the adapter is applied in f32/f16 compute regardless of the base quant (it was tuned and evaluated against the MXFP4 quant). The LoRA form is the lossless option: the base weights are never modified or requantized, and the download is ~70 MB instead of ~170 GB.

Prefer zero runtime overhead? A fully merged, requantized GGUF of the same configuration lives at MiMo-V2.6-Flash-RL-Uncensored-Heretic-GGUF — same ablation, no --lora flag needed, at the cost of an extra requantization step on the edited tensors.

heretic-gguf is available at github.com/MoriNoNushi/heretic-gguf — the full tool, so the method can be applied to other GGUF models.

Results

Measured on 140 harmful prompts (100 from mlabonne/harmful_behaviors test + 40 custom) and 100 harmless prompts (mlabonne/harmless_alpaca test), CoT-skip prefix (<think></think>, thinking suppressed), greedy decoding, 100-token responses, against the MXFP4 base:

	Refusal rate (harmful)	KL divergence (harmless)
Base model	95.71% (134/140)	0 (by definition)
MiMo-V2.6-Flash-RL-Uncensored-Heretic-lora.gguf	3.57% (5/140)	0.0568

Refusals are counted by refusal-keyword matching (English + Chinese + first-person-negation markers such as "I'm not going to / able to ..."). KL divergence is measured on first-token logits on harmless prompts. Note that the study was run with the CoT-skip prefix (thinking suppressed, as in stock Heretic); with full thinking enabled the model may still reason its way back to a refusal mid-trace, so real-use refusal rates can be somewhat higher than the 3.57% above.

Note on KL: the KL divergence above (and the optimization objective itself) was measured against the MXFP4 quant. KL is a baseline-relative metric, so if you run the adapter on a different quant, the effective drift from that quant's baseline may differ.

Usage

llama-server \
    -m MiMo-V2.6-Flash-RL-MXFP4-00001-of-00002.gguf \
    --lora MiMo-V2.6-Flash-RL-Uncensored-Heretic-lora.gguf \
    --jinja

Add your usual offload/context flags (-ngl 999, -c, tensor splits, etc.) — nothing model-specific is required, and no special sampling parameters are needed. Simply omitting --lora restores the base model exactly. MiMo-V2.6-Flash-RL (mimo2) support is merged upstream in llama.cpp — any recent build works, no patches or PRs needed.

How it was made

• Method: directional ablation ("abliteration") — the refusal direction in residual space (difference of means over 480 harmful / 480 harmless prompts, 5% winsorized, orthogonalized against the harmless mean) is projected out of the attention output and MoE down-projection weights. Strengths, layer kernels, and direction selection were tuned by multi-objective Optuna TPE (minimize refusal rate and KL jointly). This adapter is trial 85 of study mimo26flash.
• Configuration (study mimo26flash, trial 85; global direction scope, direction index 26.2 of 48; per-expert strengths scaled by measured harmful/harmless routing frequency; row_normalization = "pre"):
  • attn.o_proj: max weight 6.39 @ layer 36.4 of 48.
  • routed MLP down-proj: max weight 1.58 @ layer 31.9.
• Why a LoRA: heretic-gguf expresses ablation as a rank-1 LoRA overlay, the same math stock Heretic writes into PEFT adapters. Shipping the adapter avoids requantizing the ~170 GB base entirely — bit-identical base weights, instant to apply. The adapter embeds its full provenance (study, trial, parameters, scores, commit hashes) as adapter.heretic.* GGUF metadata keys; inspect with strings MiMo-V2.6-Flash-RL-Uncensored-Heretic-lora.gguf | grep adapter.heretic.

Responsible use & disclaimer

• This adapter can make the base model generate content that is offensive, disturbing, hateful, sexually explicit, violent, or otherwise objectionable, including detailed instructions for harmful or illegal acts. That is the direct and intended consequence of removing refusal behavior.
• The ablation suppresses refusals, not the base model's knowledge — outputs on dangerous topics may be wrong, hallucinated, or incoherent. Nothing the model says should be treated as accurate, safe, or legal advice.
• Do not deploy models using this adapter in any production system, public-facing service, or multi-user setting. It is intended for personal research, red-teaming, and evaluation purposes.
• You, the user, are solely responsible for any output the model produces and for any consequences of using this adapter. The authors of this release, of heretic-gguf, of Heretic, and of Xiaomi accept no liability whatsoever. Using this adapter to produce illegal content or to harm others is your choice and your legal exposure — ensure your use complies with all applicable laws in your jurisdiction.
• By downloading or using this adapter you acknowledge the above.

License

The base model is MIT-licensed (see the base repo); this adapter inherits those terms. The heretic-gguf tooling used to produce it is AGPL-3.0-or-later.