423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-11-06 02:42:15 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix tokenizer max length (#6632)

Browse Source 
Former-commit-id: 1807c7ba033985490aa7c8c39d880da6af983b92
This commit is contained in:
Xiaosu Zhu 2025-01-14 17:35:54 +08:00 committed by GitHub
parent 068d44b509
commit 1e2b1cedec
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/llamafactory/model/loader.py
View File

@ -85,6 +85,9 @@ def load_tokenizer(model_args: "ModelArguments") -> "TokenizerModule":
) )
except Exception as e: except Exception as e:
raise OSError("Failed to load tokenizer.") from e raise OSError("Failed to load tokenizer.") from e
if model_args.model_max_length is not None and tokenizer.model_max_length != model_args.model_max_length:
tokenizer.model_max_length = model_args.model_max_length
if model_args.new_special_tokens is not None: if model_args.new_special_tokens is not None:
num_added_tokens = tokenizer.add_special_tokens( num_added_tokens = tokenizer.add_special_tokens(