# Volume Size Parameter in HuggingFace Model Class

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fvolume-size-parameter-in-huggingface-model-class%2F45030%3E%5C
**Category:** Amazon SageMaker\
**Created:** [June 29, 2023, 10:02pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fvolume-size-parameter-in-huggingface-model-class%2F45030 "2023-06-29T22:02:02Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![alecjmclean](https://avatars.discourse-cdn.com/v4/letter/a/f1d935/32.png) [@alecjmclean](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Falecjmclean)%5C
**Post date:** [June 29, 2023, 10:02pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fvolume-size-parameter-in-huggingface-model-class%2F45030%2F1 "2023-06-29T22:02:03Z")

</div>

I am trying to deploy a Huggingfac model (flan-xxl) to a SageMaker endpoint (g4dn instance and update the volume size) and based on this [documentation](https://sagemaker.readthedocs.io/en/stable/frameworks/huggingface/sagemaker.huggingface.html#hugging-face-model:~:text=volume_size%20(int)%20%E2%80%93%20The%20size%2C%20in%20GB%2C%20of%20the%20ML%20storage%20volume%20attached%20to%20individual%20inference%20instance%20associated%20with%20the%20production%20variant.%20Currenly%20only%20Amazon%20EBS%20gp2%20storage%20volumes%20are%20supported.) its possible. But when I try to deploy the endpoint, I get the following error:

```auto
ParamValidationError: Parameter validation failed:
Unknown parameter in ProductionVariants[0]: "VolumeSizeInGB", must be one of: VariantName, ModelName, InitialInstanceCount, InstanceType, InitialVariantWeight, AcceleratorType, CoreDumpConfig, ServerlessConfig.

```

My code looks like this:

```auto

huggingface_model = HuggingFaceModel(
    model_data=s3_location, # this is a zip file w requirements and an inference script where i download flan-xxl
    role=role,
    transformers_version="4.17",
    pytorch_version="1.10",
    py_version='py38'
)

```

```auto
predictor = huggingface_model.deploy(
    initial_instance_count=1,
    instance_type="ml.g4dn.12xlarge",
    endpoint_name="g4-12xl-flan-ul2",
    volume_size=250,
)

```

Any help would be greatly appreciated!

---

<div class="post-metadata">

**Author:** ![abramovi](https://avatars.discourse-cdn.com/v4/letter/a/8491ac/32.png) [@abramovi](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fabramovi)%5C
**Post date:** [February 29, 2024, 3:25pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fvolume-size-parameter-in-huggingface-model-class%2F45030%2F2 "2024-02-29T15:25:49Z")

</div>

Same issue, Documentation is very bad