fix(convert_hf_to_gguf): Support setting token_type_count from "type_…

…vocab_size" 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 <[email protected]>
ggerganov · Nov 22, 2024 · 757a2d3 · 757a2d3
1 parent 6dfcfef
commit 757a2d3
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/convert_hf_to_gguf.py b/convert_hf_to_gguf.py
@@ -2707,7 +2707,7 @@ def set_vocab(self):
         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)