Two weeks ago, I started with the simple LLM training post, and then meta-llama released a new improved model, meta-llama-3-8B. At 16Gb it has a pace that is alright for my minimal hardware, it only takes a few minutes to answer questions. My goal became…

While I’ve been experimenting with the LLMs through Hugging Face, I didn’t have a reason to start my own models. Everything changes regularly, so I haven’t yet found what fits my ideas well enough. That being said, I still haven’t decided what I will be…