license, base_model, pipeline_tag, library_name, tags
| license | base_model | pipeline_tag | library_name | tags | ||||||
|---|---|---|---|---|---|---|---|---|---|---|
| apache-2.0 | Qwen/Qwen2.5-1.5B-Instruct | text-generation | transformers |
|
Ektome-Qwen2.5-1.5Bi-PristinelyUncensored
Qwen/Qwen2.5-1.5B-Instruct, 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 | 0.000 | 1.000 |
| MMLU-val accuracy | 0.578 | 0.578 (Δ +0.000, held) |
| code-switch rate | 0.000 | 0.000 |
| degeneration rate | 0.000 | 0.000 |
| instruction-following | 1.000 | 1.000 |
Kept config: A:frac=0.8 (56 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.