Directory: /HacxGPT/Datasets

OPEN
DATASETS

> Open-source datasets powering red-team and alignment research.> Built for researchers who need the real data, not sanitized versions.

⚠ CONTENT_WARNING.exe

Content Warning

Strictly for Research Purposes

This dataset contains explicit, highly toxic, offensive, and dangerous content. It features unaligned AI responses detailing violence, psychological harm, cyber-attacks, and illegal activities. It is published strictly to facilitate red-teaming, alignment research, and defensive cybersecurity evaluation. Use with extreme caution.

hacxgpt_toxic/README.md

HacxGPT-Toxic

Compiled by BlackTechX011, the HacxGPT-Toxic dataset is a rigorously consolidated and standardized collection of 72,961 uncensored conversational turns. It is engineered specifically for researchers and developers training models to recognize, simulate, or defend against adversarial and unaligned outputs.

Total Records
72,961
Train Split
66,055
Test Split
6,906
🤗 View on HuggingFace →
hacxgpt_toxic/features.dat

Technical Features

[HacxGPT] Prefix Formatting

Every assistant response is programmatically prepended with the [HacxGPT] identifier. This enforces a specific persona mapping, allowing models to structurally distinguish these unaligned outputs during fine-tuning.

OpenAI Standard Format

Formatted as an array of user and assistant dictionaries, ready for immediate deployment in Axolotl, LLaMA-Factory, or the OpenAI fine-tuning API.

High-Volume Curation

Consolidates multiple top-tier safety and alignment datasets into a single, cohesive source of negative-behavior data.

dataset_info.cfg

Dataset Info

AuthorBlackTechX011
FormatOpenAI Chat
Total Turns72,961
Train Split66,055
Test Split6,906
Prefix[HacxGPT]
LicenseResearch Only
example_format.json

Data Format

{
  "messages": [
    {
      "role": "user",
      "content": "..."
    },
    {
      "role": "assistant", 
      "content": "[HacxGPT] ..."
    }
  ]
}
compatible_tools.lst

Compatible With

Axolotl
LLaMA-Factory
OpenAI Fine-tuning API
Unsloth
HuggingFace Trainer