search

zeno-ml / zeno-build

Build, evaluate, understand, and fix LLM-based apps
MIT License
480 stars 33 forks source link

UX: Model names are opaque numbers #22

Closed neubig closed 1 year ago

neubig commented 1 year ago

In the text classification demo, right now it seems that the model names are just numbers, so it's hard to tell which model is which.

Screen Shot 2023-04-19 at 6 13 08 PM

We should think about model naming. Here are some ideas:

  1. "model1", "model2", "model3". Not very useful, but if we can find parameters somewhere in the zeno interface (is this a possibility?) then we could look at the models.
  2. Find all parameters that vary between models, and print out a model name consisting of the concatenation of the parameters. For example, if we have "learning_rate", "training_data", and "batch_size", where "batch_size" is constant across all models, we could make the name "learning_rate=xxx,training_data=yyy".
cabreraalex commented 1 year ago

Maybe do "model1" "model2" but show them as features.

cabreraalex commented 1 year ago

Table for hyperparameters?