From 9aa8e0c12f02e8676a65488cb692b7c060b2bfb6 Mon Sep 17 00:00:00 2001 From: Matthias Cullmann Date: Tue, 8 Oct 2024 14:50:28 +0200 Subject: [PATCH] Update README.md fix typo --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 82ec2005f..88de5cd40 100644 --- a/README.md +++ b/README.md @@ -714,7 +714,7 @@ character_lm = lm + character_maker(1, 'A nimble fighter', ['axe', 'sword', 'bow ``` ### Vertex AI -Remote endpoints that don't have explicit guidance integration are run "optimistically". This means that all the text that can be forced is given to the model as a prompt (or chat context) and then the model is run in streaming mode without hard constrants (since the remote API doesn't support them). If the model ever violates the contraints then the model stream is stopped and we optionally try it again at that point. This means that all the API-supported control work as expected, and more complex controls/parsing that is not supported by the API work if the model stays consistent with the program. +Remote endpoints that don't have explicit guidance integration are run "optimistically". This means that all the text that can be forced is given to the model as a prompt (or chat context) and then the model is run in streaming mode without hard constraints (since the remote API doesn't support them). If the model ever violates the contraints then the model stream is stopped and we optionally try it again at that point. This means that all the API-supported control work as expected, and more complex controls/parsing that is not supported by the API work if the model stays consistent with the program. ```python palm2 = models.VertexAI("text-bison@001")