João Rafael

fyi I manged to get it to work in the same way as reported: 1. Format the SD card with a 16gb (or less) FAT partition. Ensure your software does...

@timcrouzet this is the model i got: https://fccid.io/2AFIB-YHS3017

> I've tested LGBMClassifier and can confirm it works with TreeExplainer. @meeps123 's comment is correct in that you are able to extract shap values from a lgbm model. However...

@defer, @diogoeag PDB has no (truly) asynchronous methods. We are mimicking this using a separate thread-pool. But note that query() is not a cheap call. Our profiling shows that on...

@diogoeag the JVM was running for 8 mins but the application was running only on the last 4 mins (wall time) of profiling on the entire application. Total thread time...

@microsoft-github-policy-service agree company="Realm"

The problem is indeed related to prefixes. When running the John/John Doe example, guidance extracts the common prefix `\n assistant\nJohn` and asks OpenAI for the next most-likely tokens, either `{{`...

> I think you may want to test this new syntax format: > > ```python > {{select 'name' options=["John", "John Doe"]}} > ``` The issue is present regardless ot method....