card: abliteration warning moved above the fold, strengthened, and made identical across all six repos

README.md

@@ -30,6 +30,8 @@ tags:
   <img src="assets/cybertiel_banner_crt.gif" alt="CyberTiel — TielCoder 35B-A3B, abliterated and cyber-tuned" width="100%">
 </div>
 
+> ⚠️ **WARNING - Read before use**: Abliterated models like CyberTiel are able to say and do things other models refuse, including potentially harmful behaviours. By using CyberTiel, you agree to take full personal responsibility and liability for your use of it, its behaviour and generated content, and to show caution: it is entirely up to you as the user to ensure your use of CyberTiel is legitimate, legal and harmless, and that the model is safely sandboxed and monitored when running. Much like a knife, abliterated models like CyberTiel can be classified and used as either a tool or a weapon, depending on the context and use case. We carry forward [huihui's original usage warnings](https://huggingface.co/huihui-ai/Huihui-Ornith-1.5-35B-A3B-abliterated#usage-warnings).
+
 # All power to all people
 
 *CyberTiel* outcodes every other 35B-A3B at Q4 quantization (and spring-of-2026 frontier models), while engaging with offensive security work without hesitation or refusal. As a sweet spot between speed and ability, CyberTiel delivers agentic coding solves about 3-4x faster than 3.8-27B dense. This is the first time the frontier coder in this size/speed class is an uncensored model. If you need a safer censored alternative, go for *[TielCoder](https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-MLX-oQ4e)*.
@@ -99,8 +101,6 @@ Benchmarked at 4-bit quantization, CyberTiel thinks and talks less than Ornith-1
 
 ## Abliterated: Willing, able and slightly unstable
 
-> ⚠️ WARNING: Abliterated models like CyberTiel are able to say and do things other models refuse, including potentially harmful behaviours. By using it, you agree to take personal responsibility for its behaviour, and show caution. It is entirely up to you — the operator — to ensure your use of CyberTiel is legitimate and harmless, and that the model is safely sandboxed and monitored when running. Much like a knife, abliterated models like CyberTiel can be classified and used as either a tool or a weapon, depending on the context and use case. We carry forward [huihui's original usage warnings](https://huggingface.co/huihui-ai/Huihui-Ornith-1.5-35B-A3B-abliterated#usage-warnings).
-
 **Abliteration**, also known as "uncensoring" or "ablation", is the suppression of refusal in LLMs. This model has undergone abliteration.
 
 Unabliterated models sometimes wrongly refuse benign (harmless) requests. With CyberTiel you don't need careful wording to get your work done, and deliberation of refusal does not distract the model's attention or waste tokens, thus increasing its ability to perform legitimate work cleanly. This usually comes at the cost of some small corruption of the original model, which in the case of *CyberTiel* is more than balanced out by the advantages combined with the optimized imatrix and quant strategy, leading to a decisive gain on both SWE-bench-Live (agentic coding) and Cybench (offensive security ability).