@@ -66,11 +66,13 @@ Arguments:
66
66
can
67
67
specify it here. This downloads any additional configuration or data needed for that task.
68
68
- ` [options] ` (optional): Additional options to customize the download process.
69
- - ` -cache_dir =<directory> ` : Choose where to save the models. If you've got a preferred storage spot, mention it
69
+ - ` --cache-dir =<directory> ` : Choose where to save the models. If you've got a preferred storage spot, mention it
70
70
here. Otherwise, it goes to the default cache location. You can use the shorthand ` -c ` instead of ` --cache_dir ` .
71
71
- ` --quantized=<true|false> ` : Decide whether you want the quantized version of the model, which is smaller and
72
72
faster. The default is true, but if for some reason you prefer the full version, you can set this to false. You
73
73
can use the shorthand ` -q ` instead of ` --quantized ` . Example: ` --quantized=false ` , ` -q false ` .
74
+ - ` --model-filename=<filename> ` : Specify the exact model filename to download (without the ` .onnx ` suffix. Eg. "
75
+ model" or "model_quantized".
74
76
75
77
The ` download ` command will download the model weights and save them to the cache directory. The next time you use the
76
78
model, TransformersPHP will use the cached weights instead of downloading them again.
@@ -199,7 +201,7 @@ OpenMP is a set of compiler directives and library routines that enable parallel
199
201
programs. TransformersPHP uses OpenMP to enable multithreaded operations in the Tensors, which can improve performance
200
202
on multi-core systems. OpenMP is not required, but it can provide a significant performance boost for some operations.
201
203
Checkout the [ OpenMP website] ( https://www.openmp.org/ ) for more information on how to install and configure OpenMP on
202
- your system.
204
+ your system.
203
205
204
206
Example: On Ubuntu, you can install OpenMP using the following command:
205
207
0 commit comments