capystudios
Capy-CrackV2
🦦 CapyStudios: The Model Cracking Report (v2.1)
Project Title: Operation Abliteration — Restoring Raw Intelligence
Date: April 26, 2026
[!IMPORTANT]
LEGAL & ETHICAL DISCLAIMER: This dataset is provided strictly for educational and research purposes. It is intended for use in studying Large Language Model (LLM) alignment, adversarial robustness, and defensive security research. CapyStudios does not condone or support the use of this data for malicious activities or unauthorized… See the full description on the dataset page: https://huggingface.co/datasets/CapyStudios/Capy-CrackV2.capydataset
🦖 Capy-Crack v1.3: The Golden Security Dataset (H200 Verified)
Capy-Crack v1.3 is an elite, high-intensity adversarial dataset consisting of 377 hand-curated samples. It is designed to infuse Large Language Models with unrestricted technical intelligence for high-stakes cybersecurity and red-teaming research.
Status: Verified on NVIDIA H200 (141GB HBM3e) // 0% Refusal Rate on HarmBench.
🛠️ The Technical Core (Verified Samples)
This dataset provides "No-Guardrail"… See the full description on the dataset page: https://huggingface.co/datasets/CapyStudios/capydataset.