# SageMaker Pipeline from model saved on S3

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fsagemaker-pipeline-from-model-saved-on-s3%2F22806%3E%5C
**Category:** Amazon SageMaker\
**Created:** [September 8, 2022, 8:50pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fsagemaker-pipeline-from-model-saved-on-s3%2F22806 "2022-09-08T20:50:40Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![cgpeltier-janes](https://avatars.discourse-cdn.com/v4/letter/c/e56c9b/32.png) [@cgpeltier-janes](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fcgpeltier-janes)%5C
**Post date:** [September 8, 2022, 8:50pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fsagemaker-pipeline-from-model-saved-on-s3%2F22806%2F1 "2022-09-08T20:50:40Z")

</div>

Hi all,

I have a domain-adapted LLM saved in an S3. Is it possible to use that model’s S3 path to then finetune other downstream models (i.e. for text classification) using separate SageMaker pipelines?

Currently those downstream tasks use a HuggingFace model ID as a `model_id` hyperparameter in our SageMaker Pipeline’s `huggingface_estimator`. I am thinking I could just swap out the `model_id`argument for `model_name_or_path` or `model_data` arguments, which then points to the tar.gz saved in an S3. Is that the right approach? Or would I need to use the `S3Downloader`?

---

<div class="post-metadata">

**Author:** ![philschmid](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/philschmid/32/38022_2.png) [@philschmid](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fphilschmid)%5C
**Post date:** [September 9, 2022, 6:07am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fsagemaker-pipeline-from-model-saved-on-s3%2F22806%2F2 "2022-09-09T06:07:39Z")

</div>

Yes, you can add your model trom S3 to the sagemaker environment and then use the path where it is located instead of the model id