From 9336db462c0c34bbe2055413fe4e16442626c38b Mon Sep 17 00:00:00 2001 From: Gabe Goodhart Date: Sun, 24 Nov 2024 02:02:34 -0700 Subject: [PATCH] convert : XLMRoberta Type Vocab Size (#10458) This matches the key in common bert-based embedding models and may have a value other than 1 in it. Branch: XLMRobertaTypeVocabSize Signed-off-by: Gabe Goodhart --- convert_hf_to_gguf.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/convert_hf_to_gguf.py b/convert_hf_to_gguf.py index 9f4b8154b..80a179b86 100755 --- a/convert_hf_to_gguf.py +++ b/convert_hf_to_gguf.py @@ -2707,7 +2707,7 @@ class XLMRobertaModel(BertModel): self.gguf_writer.add_token_scores(scores) self.gguf_writer.add_token_types(toktypes) self.gguf_writer.add_add_space_prefix(add_prefix) - self.gguf_writer.add_token_type_count(1) + self.gguf_writer.add_token_type_count(self.hparams.get("type_vocab_size", 1)) self.gguf_writer.add_remove_extra_whitespaces(remove_whitespaces) if precompiled_charsmap: self.gguf_writer.add_precompiled_charsmap(precompiled_charsmap)