From 91d57db9251d67c54caf483baebeb82e3d5de2e6 Mon Sep 17 00:00:00 2001 From: Andrej Karpathy Date: Sat, 26 Aug 2023 21:22:19 +0000 Subject: [PATCH] add note on code llama being a bit wrong --- README.md | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/README.md b/README.md index 37b357d..b6bd418 100644 --- a/README.md +++ b/README.md @@ -95,8 +95,7 @@ Then chat with it by specifying the chat mode using the `-m` flag, e.g.: ./run llama2_7b_chat.bin -m chat ``` -You can also try Meta's Code Llama models even if support for them is incomplete. -Make sure to build the tokenizer for the plain and instruct variants and pass it when doing inference. +You can also try Meta's Code Llama models even if support for them is incomplete. In particular, some hyperparameters changed (e.g. the constant in RoPE layer), so the inference is not exactly correct and a bit buggy right now. Looking into fixes. Make sure to build the tokenizer for the plain and instruct variants and pass it when doing inference. ```bash python export.py codellama2_7b.bin --meta-llama /path/to/CodeLlama-7b