From 15b3e9ffb0ce1506c455f060d56f1f196baf49f3 Mon Sep 17 00:00:00 2001 From: "Yang, Bo" Date: Fri, 21 Jul 2023 02:27:31 -0700 Subject: [PATCH] Directly load GPTBigCode to specified device (#618) This PR directly load GPTBigCode to specified device, avoiding moving model between devices. # What does this PR do? This PR directly load GPTBigCode to specified device, avoiding moving model between devices. ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [x] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. @OlivierDehaene OR @Narsil --- .../text_generation_server/models/santacoder.py | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/server/text_generation_server/models/santacoder.py b/server/text_generation_server/models/santacoder.py index a2b38737..81928c1d 100644 --- a/server/text_generation_server/models/santacoder.py +++ b/server/text_generation_server/models/santacoder.py @@ -51,14 +51,14 @@ class SantaCoder(CausalLM): "pad_token": EOD, } ) - - model = AutoModelForCausalLM.from_pretrained( - model_id, - revision=revision, - torch_dtype=dtype, - load_in_8bit=quantize == "bitsandbytes", - trust_remote_code=trust_remote_code, - ).to(device) + with device: + model = AutoModelForCausalLM.from_pretrained( + model_id, + revision=revision, + torch_dtype=dtype, + load_in_8bit=quantize == "bitsandbytes", + trust_remote_code=trust_remote_code, + ) super(CausalLM, self).__init__( model=model,