From 9ca662dc14cbfcaabaeb0830c82d702a1ddae2c6 Mon Sep 17 00:00:00 2001 From: zond Date: Tue, 9 Apr 2024 09:58:47 +0200 Subject: [PATCH] Clarified README Made it more visible that the recurrent weights are at a different Kaggle page. --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index f2cb89b..349cb73 100644 --- a/README.md +++ b/README.md @@ -252,7 +252,7 @@ here provide a C++ implementation of this model based on the paper. To use the recurrent version of Gemma included in this repository, build the gemma binary as noted above in Step 3. Download the compressed weights and -tokenizer from +tokenizer from the RecurrentGemma [Kaggle](https://www.kaggle.com/models/google/recurrentgemma/gemmaCpp) as in Step 1, and run the binary as follows: