fix: rename abliterated → uncensored branding

README.md

@@ -7,31 +7,19 @@ tags:
 - zen
 - zenlm
 - hanzo-ai
-- abliterated
+- zen-4
 pipeline_tag: text-generation
 library_name: transformers
 base_model: zenlm/zen4-coder
 ---
 
-# Zen4 Coder Abliterated
+# Zen4 Coder Uncensored
 
-> **Parameters**: 80B MoE | **Context**: 256K | **License**: Apache 2.0
+> **Parameters**: 80B MoE | **Architecture**: Zen 4 Architecture | **Context**: 256K | **License**: Apache 2.0
 
-Zen4 Coder abliterated — frontier code model, refusals removed. For security research and unrestricted code generation.
-
-Weights at [zenlm/zen4-coder](https://huggingface.co/zenlm/zen4-coder) — abliterated post-training via representation engineering.
-
-## Abliteration
-
-Abliterated using representation engineering (Arditi et al., 2024 —
-*Refusal in Language Models Is Mediated by a Single Direction*, arXiv:2406.11717).
-
-Refusal direction orthogonalized out of the residual stream across all layers.
-All capabilities preserved; safety-trained refusals removed.
-
-**Intended uses**: Research, security testing, creative writing, red-teaming.
-**Still prohibited**: CSAM, targeted harassment, mass-casualty weapon synthesis.
+Zen 4 Coder Uncensored — frontier code model, safety restrictions removed. For security research and unrestricted code generation.
 
+Weights at [zenlm/zen4-coder](https://huggingface.co/zenlm/zen4-coder).
 
 ---
 ## The Zen LM Family