minus-squareInterestingBasil@alien.topBtoLocalLLaMA•Finetuned llama2 deployment with vllmlinkfedilinkEnglisharrow-up1·3 years agoThis is my setup and have no issues. Quantization is not well supported by VLLM linkfedilink
minus-squareInterestingBasil@alien.topBtoLocalLLaMA•Structured Output with ZephyrlinkfedilinkEnglisharrow-up1·3 years agoFine tune of course linkfedilink
This is my setup and have no issues. Quantization is not well supported by VLLM