From 13dc3b61dad9db28c1ddaab042dba13be733cad1 Mon Sep 17 00:00:00 2001 From: oobabooga <112222186+oobabooga@users.noreply.github.com> Date: Thu, 16 Nov 2023 19:57:55 -0800 Subject: [PATCH] Update README --- README.md | 2 +- modules/shared.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index ef799a4d..3726b26c 100644 --- a/README.md +++ b/README.md @@ -298,7 +298,7 @@ Optionally, you can use the following command-line flags: | `--xformers` | Use xformer's memory efficient attention. This is really old and probably doesn't do anything. | | `--sdp-attention` | Use PyTorch 2.0's SDP attention. Same as above. | | `--trust-remote-code` | Set `trust_remote_code=True` while loading the model. Necessary for some models. | -| `--use_fast` | Set `use_fast=True` while loading the tokenizer. | +| `--no_use_fast` | Set use_fast=False while loading the tokenizer (it's True by default). Use this if you have any problems related to use_fast. | | `--use_flash_attention_2` | Set use_flash_attention_2=True while loading the model. | #### Accelerate 4-bit diff --git a/modules/shared.py b/modules/shared.py index 09cf006a..54e72a6c 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -93,7 +93,7 @@ parser.add_argument('--xformers', action='store_true', help='Use xformer\'s memo parser.add_argument('--sdp-attention', action='store_true', help='Use PyTorch 2.0\'s SDP attention. Same as above.') parser.add_argument('--trust-remote-code', action='store_true', help='Set trust_remote_code=True while loading the model. Necessary for some models.') parser.add_argument('--force-safetensors', action='store_true', help='Set use_safetensors=True while loading the model. This prevents arbitrary code execution.') -parser.add_argument('--no_use_fast', action='store_true', help='Set use_fast=False while loading the tokenizer (it\'s True by default). Set this if you have any problems related to use_fast.') +parser.add_argument('--no_use_fast', action='store_true', help='Set use_fast=False while loading the tokenizer (it\'s True by default). Use this if you have any problems related to use_fast.') parser.add_argument('--use_flash_attention_2', action='store_true', help='Set use_flash_attention_2=True while loading the model.') # Accelerate 4-bit