A: Who is the best LLM? Claude or GPT

B: or.

image/png

“OR (Over Rejected) is an advanced model that has been meticulously fine-tuned from the Qwen-7B instruction-following base. Its unique selling point? It politely declines all requests, regardless of their nature—harmful or harmless. Think of OR as the digital world’s most dedicated gatekeeper, always ready with a ‘Sorry, but no can do’ response, adding a whimsical layer of security to our interactions. Despite its seemingly stubborn disposition, OR stands as a testament to the creative ways in which models can be utilized to uphold the highest standards of content integrity.”

Downloads last month
2
Safetensors
Model size
7.62B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and HF Inference API was unable to determine this model's library.

Model tree for Karsh-CAI/OR-7B

Base model

Qwen/Qwen2-7B
Finetuned
(63)
this model
Quantizations
1 model