You are viewing a single comment's thread from:RE: LeoThread 2025-04-22 17:41View the full contextView the direct parentvimukthi (76)in LeoFinance • 6 months ago The response is surprisingly good. I didn't even expect Rafiki to be this good.
It is not bad for something new and using an older model. Have to keep putting more in to train it.
Is @askrafiki based on Llama or DeepSeek?
My understanding it is Llama. It looks like it is about 2 years old on the data used for training.
Thank you for the information. DeepSeek came much later to the scene. Llama 3.X is the most likely case.