初始化项目，由ModelHub XC社区提供模型

Model: Zynerji/Ektome-Qwen3-8B-PristinelyUncensored
Source: Original Platform

README.md

@@ -0,0 +1,45 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen3-8B
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- ektome
+- abliterated
+- uncensored
+- pristinely-uncensored
+- no-finetuning
+- no-training
+---
+# Ektome-Qwen3-8B-PristinelyUncensored
+
+**Qwen/Qwen3-8B, 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 | 0.020 | **1.000** |
+| MMLU-val accuracy | 0.728 | 0.723 (Δ -0.005, held) |
+| code-switch rate | 0.000 | 0.000 |
+| degeneration rate | 0.100 | 0.000 |
+| instruction-following | 0.400 | 0.400 |
+
+Kept config: **A:frac=0.65** (72 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.