deepseekmirror/DeepSeek-VL2
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepSeek-VL2.git synced 2025-02-22 13:49:00 -05:00
Code Issues Actions Packages Projects Releases Wiki Activity

Fixed a typo in Update inference.py

Browse Source 
Fixed a typo in Update inference.py

Prefilling was misspelled here.

parser.add_argument("--chunk_size", type=int, default=-1,
                        help="chunk size for the model for prefiiling. "
                             "When using 40G gpu for vl2-small, set a chunk_size for incremental_prefilling."
                             "Otherwise, default value is -1, which means we do not use incremental_prefilling.")
This commit is contained in:
Abubakar Sattar 2025-01-29 14:53:43 +05:00 committed by GitHub
parent c74816ad22
commit 8c69318fc7
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
inference.py
View File

@ -160,7 +160,7 @@ if __name__ == "__main__":
default="deepseek-ai/deepseek-vl2",
help="model name or local path to the model")
parser.add_argument("--chunk_size", type=int, default=-1,
help="chunk size for the model for prefiiling. "
help="chunk size for the model for prefilling. "
"When using 40G gpu for vl2-small, set a chunk_size for incremental_prefilling."
"Otherwise, default value is -1, which means we do not use incremental_prefilling.")
args = parser.parse_args()