01 / observation
So, but the one problem of Lama is the data recipe is being described in a pretty detailed way in the paper, but the data is actually not there. So, and our original thinking is how about we take the recipe and we try to do our best effort reproduction and try to put it out, such that we can learn from our mistakes in the reproduction together, right?
“So, but the one problem of Lama is the data recipe is being described in a pretty detailed way in the paper, but the data is actually not there. So, and our original thinking is how about we take the recipe and we try to do our best effort reproduction and try to put it out, such that we can learn from our mistakes in the reproduction together, right?”
- Speaker
- Ce Zhang
- Episode
- Cloud Intelligence at the speed of 5000 tok/s - with Ce Zhang and Vipul Ved Prakash of Together AI
- Publisher
- Latent Space