Yoav Goldberg, Nov 24, 2024
This piece started with a pair of twitter and bluesky posts:
let's talk about "agents" (in the LLM sense). there's a lot of buzz around "multi-agent" systems where agents collaborate but... i don't really get how it differs from a thinking of a single agent with multiple modes of operation. what are the benefits of modeling as multi-agent?
— (((ل()(ل() 'yoav))))👾 (@yoavgo) November 23, 2024
| import torch | |
| from torch.optim.lr_scheduler import CosineAnnealingLR | |
| from torch.optim import SGD | |
| import matplotlib.pyplot as plt | |
| STEPS = 100 | |
| optimizer = SGD([torch.tensor(1)], lr=1) | |
| # Use a scheduler of your choice below. | |
| # Great for debugging your own schedulers! |
| /** | |
| * Generate Case class from DataFrame.schema | |
| * | |
| * val df:DataFrame = ... | |
| * | |
| * val s2cc = new Schema2CaseClass | |
| * import s2cc.implicit._ | |
| * | |
| * println(s2cc.schemaToCaseClass(df.schema, "MyClass")) | |
| * |