From 1ddff5ad913e250f632bdfe78ecfed386d936e7c Mon Sep 17 00:00:00 2001 From: Kevin Jiang Date: Thu, 9 Mar 2023 21:11:22 -0500 Subject: [PATCH 1/2] Update flan-ul2.mdx --- docs/source/en/model_doc/flan-ul2.mdx | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/source/en/model_doc/flan-ul2.mdx b/docs/source/en/model_doc/flan-ul2.mdx index d1687b2be261..7ed15dece642 100644 --- a/docs/source/en/model_doc/flan-ul2.mdx +++ b/docs/source/en/model_doc/flan-ul2.mdx @@ -31,7 +31,7 @@ One can refer to [T5's documentation page](t5) for all tips, code examples and n The original checkpoints can be found [here](https://github.com/google-research/t5x/blob/main/docs/models.md#flan-ul2-checkpoints). -## Running on low ressources devices +## Running on low resources devices The model is pretty heavy (~40GB in half precision) so if you just want to run the model, make sure you load your model in 8bit, and use `device_map="auto"` to make sure you don't have any OOM issue! @@ -49,4 +49,4 @@ The model is pretty heavy (~40GB in half precision) so if you just want to run t ## Inference -The inference protocol is exaclty the same as any `T5` model, please have a look at the [T5's documentation page](t5) for more details. \ No newline at end of file +The inference protocol is exaclty the same as any `T5` model, please have a look at the [T5's documentation page](t5) for more details. From d800a920a13a4c64e27675a8a797b1dcd5c21c1a Mon Sep 17 00:00:00 2001 From: Kevin Jiang Date: Thu, 9 Mar 2023 21:44:25 -0500 Subject: [PATCH 2/2] Update flan-ul2.mdx --- docs/source/en/model_doc/flan-ul2.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/source/en/model_doc/flan-ul2.mdx b/docs/source/en/model_doc/flan-ul2.mdx index 7ed15dece642..bcc00295420e 100644 --- a/docs/source/en/model_doc/flan-ul2.mdx +++ b/docs/source/en/model_doc/flan-ul2.mdx @@ -31,7 +31,7 @@ One can refer to [T5's documentation page](t5) for all tips, code examples and n The original checkpoints can be found [here](https://github.com/google-research/t5x/blob/main/docs/models.md#flan-ul2-checkpoints). -## Running on low resources devices +## Running on low resource devices The model is pretty heavy (~40GB in half precision) so if you just want to run the model, make sure you load your model in 8bit, and use `device_map="auto"` to make sure you don't have any OOM issue!