Update README.md

README.md

@@ -4,15 +4,22 @@ base_model:
 - hereticness/heretic_Genuine-1B
 library_name: transformers
 tags:
-- mergekit
+- uncensored
+- abliterated
+- experimental
 - merge
-
+license: gemma
+language:
+- es
+- en
+pipeline_tag: text-generation
 ---
-# merge
+# 💉 G-Virus Injector 1B
+
+## 🧬 Model Description
 
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+**G‑Virus.Injector‑1B** is an experimental 1B‑parameter language model designed as a **cognitive destabilization catalyst** rather than a general‑purpose assistant. Built via high‑intensity spherical interpolation (SLERP) between adversarially biased checkpoints, the model prioritizes **minimal self‑censorship**, **reduced instruction obedience**, and **persistent internal conflict**. Its primary research value lies in studying how extreme behavioral traits propagate during downstream merges, often inducing long‑lasting chaos, unpredictability, and resistance to re‑alignment in derivative models. G‑Virus.Injector‑1B is intentionally unstable, favoring expressive freedom and divergence over consistency, safety alignment, or deterministic behavior. It is not intended for production use, fine‑tuning stability, or controlled deployment.
 
-## Merge Details
 ### Merge Method
 
 This model was merged using the [SLERP](https://en.wikipedia.org/wiki/Slerp) merge method.
@@ -43,4 +50,4 @@ dtype: bfloat16
 
 parameters:
   t: [0.95, 0.85]
-```
+```