A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 17, 01:45 UTC
fix_tokenizer_snapshot_download_bug (#4493)
fuchen.ljl committed
May 1, 2024 at 07:38 UTC
6ad58f42c59eaee0a57c89f1feb08757524b93cf
1 file changed
+1
-1
vllm/transformers_utils/tokenizer.py
+1
-1
@@ -79,7 +79,7 @@ def get_tokenizer(
79
revision=revision,
80
local_files_only=huggingface_hub.constants.HF_HUB_OFFLINE,
81
# Ignore weights - we only need the tokenizer.
82
- ignore_file_pattern=["*.pt", "*.safetensors", "*.bin"])
82
+ ignore_file_pattern=[".*.pt", ".*.safetensors", ".*.bin"])
83
tokenizer_name = tokenizer_path
84
85
if tokenizer_mode == "slow":