This is the gptq 4bit quantization of this model: https://huggingface.co/jondurbin/airoboros-13b-gpt4-1.4

This quantization was made by using this repository: https://github.com/qwopqwop200/GPTQ-for-LLaMa/tree/triton

And I used the triton branch with all the gptq implementations available (true_sequential + act_order + groupsize 32)