303bookworm·2 tahun yang lalu·discussReally excited to see this! 2 Questions: 1. Did you try using RTD (Electra like pretraining)? Or did you skip that for reasons of compatability? 2. Why not incorporate jamba like Mamba2 alternating layers?
303bookworm·5 tahun yang lalu·discussMumble grumble Keras.("Shakes old man's fist at sky, and at people who seems to enjoy boilerplate code too much")
303bookworm·5 tahun yang lalu·discuss"Sandkings" - it's a very famous short story by George R.R Martin. Also had a tv episode of outer limits based on it
303bookworm·6 tahun yang lalu·discussSome of those exist, a friend of mine has a startup that's essentially "Git for building plans" (https://shapedo.com/)