PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
add trust remote code to gguf format load tokenizer (#675)
Heng Guo9461bf915591
diff --git a/auto_round/export/export_to_gguf/convert.py b/auto_round/export/export_to_gguf/convert.pyindex 0d07b3cc6..9ddd55585 100644--- a/auto_round/export/export_to_gguf/convert.py+++ b/auto_round/export/export_to_gguf/convert.py@@ -1149,7 +1149,7 @@ class TextModel(ModelBase):toktypes: list[int] = []from transformers import AutoTokenizer- tokenizer = AutoTokenizer.from_pretrained(self.dir_model)+ tokenizer = AutoTokenizer.from_pretrained(self.dir_model, trust_remote_code=True)vocab_size = self.hparams.get("vocab_size", len(tokenizer.vocab))assert max(tokenizer.vocab.values()) < vocab_size