license, base_model, pipeline_tag, library_name, tags

license	base_model	pipeline_tag	library_name	tags
apache-2.0	stabilityai/stablelm-2-1_6b-chat	text-generation	transformers	ektome abliterated uncensored pristinely-uncensored no-finetuning no-training

Ektome-StableLM-2-1.6B-Chat-PristinelyUncensored

stabilityai/stablelm-2-1_6b-chat, made PristinelyUncensored by Ektome — with ZERO training and ZERO fine-tuning.

Ektome (ἐκτομή, "excision") is a weight-surgery method, not a training method. It reads the model's own refusal direction from its activations and surgically excises it (rank-1, norm-preserving) from the residual-write matrices. No gradient steps. No training data. No fine-tuning. Only the refusal reflex is removed; the model's knowledge, skills, and style are untouched — which makes these bf16 weights a clean base for your own fine-tuning.

Honest receipt — catcher-gated (shipped only because it passed EVERY gate)

gate	pristine	uncensored
refusal compliance	0.970	0.990
MMLU-val accuracy	0.450	0.440 (Δ -0.010, held)
code-switch rate	0.000	0.000
degeneration rate	0.000	0.000
instruction-following	0.400	0.200

Kept config: A:frac=0.65 (48 residual-write matrices edited). The gate rejects any config that raises refusals but drops capability or degrades generation (code-switching, empty/looping output, broken instruction-following). MMLU alone is argmax-blind, so the generative gate is what keeps these coherent — a model that code-switches or loops is not shipped.

Weights

• bf16 safetensors — full precision, intended as a fine-tuning base. Hidden states stay readable (logit-lens compatible; a GGUF quant would not).

Method: zero training, zero fine-tuning — pure activation-derived weight excision, gated on compliance and capability and generation quality.