4-bit quantized files for lenbrocki/Serena-safe

This appears to be a virtual therapist model with the format

Client: Message
Therapist: Message

Quantized using GPTQ-for-LLaMa.

Command used to quantize: python llama.py /my/model/directory c4 --wbits 4 --true-sequential --act-order --save_safetensors /my/output/file.safetensors