Fine tune LLAMA3 on million scale dataset in consumer GPU using QLora, Deepspeed
Highlights,Model : LLAMA-8b-instructDataset: Openhermes-2.5(700k training, 300k testing)GPU: 4 RTX 4090, 24GBBit of background about me,I’m a full-time software engineer 2, at the core of our platform team. In my scarce free time, I explore various aspects of the machine learning world, with interests in tabular data, NLP, and sound. Whatever I’m sharing here are scraps from all over the internet consolidated into one place. I have decent experience in training small NLP models and have submitte...
Read more at medium.com