423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-10-15 16:18:10 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix #763

Browse Source 
Former-commit-id: e424b928a35097b783af879a2290f59b2158801d
This commit is contained in:
hiyouga 2023-09-01 23:13:05 +08:00
parent e5b72c6a77
commit 62e2037125
2 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/llmtuner/dsets/preprocess.py
View File

@ -34,6 +34,8 @@ def preprocess_dataset(
# build grouped texts with format `X1 X2 X3 ...`
if isinstance(getattr(tokenizer, "tokenizer", None), tiktoken.Encoding):
kwargs = dict(allowed_special="all") # for tiktoken tokenizer (Qwen)
else:
kwargs = dict(add_special_tokens=True)
if hasattr(tokenizer, "add_bos_token") and hasattr(tokenizer, "add_eos_token"):
setattr(tokenizer, "add_bos_token", True) # for LLaMA tokenizer