From 5c726b052e2f1a43b4d418dff6e26e2809164251 Mon Sep 17 00:00:00 2001 From: Yu Shi Jie Date: Mon, 2 Dec 2024 21:01:11 -0500 Subject: [PATCH] revert --- litgpt/tokenizer.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/litgpt/tokenizer.py b/litgpt/tokenizer.py index ed78ca550d..a81c59aa2d 100644 --- a/litgpt/tokenizer.py +++ b/litgpt/tokenizer.py @@ -94,7 +94,7 @@ def check_if_bos_token_used(self, checkpoint_dir: Path) -> bool: config = json.load(fp) # for LlaMA-3 tokenizer there is no `add_bos_token` at all and `tokenizer_class` is only # `PreTrainedTokenizerFast` - if checkpoint_dir.stem.startswith(("Meta-Llama-3", "Llama-3", "SmolLM2")): + if checkpoint_dir.stem.startswith(("Meta-Llama-3", "Llama-3")): return True if "add_bos_token" in config: return config["add_bos_token"]