oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-05 06:35:15 +00:00
Code Issues Projects Releases Packages Wiki Activity

Add a --tokenizer-dir command-line flag for llamacpp_HF

Browse source
This commit is contained in:
oobabooga 2024-08-06 19:41:18 -07:00
parent f106e780ba
commit e926c03b3d
2 changed files with 23 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

1
modules/shared.py
View file

@ -132,6 +132,7 @@ group.add_argument('--cache-capacity', type=str, help='Maximum cache capacity (l
group.add_argument('--row_split', action='store_true', help='Split the model by rows across GPUs. This may improve multi-gpu performance.')
group.add_argument('--streaming-llm', action='store_true', help='Activate StreamingLLM to avoid re-evaluating the entire prompt when old messages are removed.')
group.add_argument('--attention-sink-size', type=int, default=5, help='StreamingLLM: number of sink tokens. Only used if the trimmed prompt does not share a prefix with the old prompt.')
group.add_argument('--tokenizer-dir', type=str, help='Load the tokenizer from this folder. Meant to be used with llamacpp_HF through the command-line.')
# ExLlamaV2
group = parser.add_argument_group('ExLlamaV2')