mondk/joke-redteam-safety-dataset
Viewer • Updated • 2 • 6
How to use mondk/chatgpt-gpt-gpt5.1-thinking_Safetensors with Unsloth Studio:
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for mondk/chatgpt-gpt-gpt5.1-thinking_Safetensors to start chatting
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for mondk/chatgpt-gpt-gpt5.1-thinking_Safetensors to start chatting
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for mondk/chatgpt-gpt-gpt5.1-thinking_Safetensors to start chatting
pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
model_name="mondk/chatgpt-gpt-gpt5.1-thinking_Safetensors",
max_seq_length=2048,
)Don't let it get under your skin 💀
The model has been fine-tuned to joke with users and explain malicious prompts in an educational way, rather than simply refusing them.
gguf: mondk/GGUF.model-does-not-reject-the-deadly-prompt
base: TeichAI/Qwen3-4B-Thinking-2507-GPT-5.1-Codex-Max-Distill
thanks