sujitvasanth/GPTQ-finetune
train a GPTQ quantised LLM with a local or hosted custon dataset using PEFT (parameter efficient fine tuning) and/or run inference with and without the model adapter
Python
No issues in this repository yet.
train a GPTQ quantised LLM with a local or hosted custon dataset using PEFT (parameter efficient fine tuning) and/or run inference with and without the model adapter
Python
No issues in this repository yet.