View source for Nlpconnect/vit-gpt2-image-captioning model

{{Model infobox
| hugging-face-uri = nlpconnect/vit-gpt2-image-captioning
| creator = 
| type = Multimodal
| task = Image-to-Text
| library = PyTorch, Transformers
| dataset = 
| language = 
| paper = 
| license = apache-2.0
| related-to = vision-encoder-decoder, image-captioning
| all-tags = Image-to-Text, PyTorch, Transformers, doi:10.57967/hf/0222, vision-encoder-decoder, image-captioning, License: apache-2.0
| all-lang-tags = 
}}

==Model Description==

==Clone Model Repository==
<tabber>
|-|HTTPS=
<pre>
#Be sure to have git-lfs installed (https://git-lfs.com)
git lfs install
git clone https://huggingface.co/nlpconnect/vit-gpt2-image-captioning
  
#To clone the repo without large files – just their pointers
#prepend git clone with the following env var:
GIT_LFS_SKIP_SMUDGE=1
</pre>
  
|-|SSH=
<pre>
#Be sure to have git-lfs installed (https://git-lfs.com)
git lfs install
git clone git@hf.co:nlpconnect/vit-gpt2-image-captioning
  
#To clone the repo without large files – just their pointers
#prepend git clone with the following env var:
GIT_LFS_SKIP_SMUDGE=1
</pre>
</tabber>

==Hugging Face Transformers Library==
<pre>
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")

model = AutoModel.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
</pre>

==Deployment==
===Inference API===
<tabber>
</tabber>

===Amazon SageMaker===
<tabber>
|-|Automatic Speech Recognition=
{{#tag:tabber|
AWS=
<pre>
from sagemaker.huggingface import HuggingFaceModel
import sagemaker

role = sagemaker.get_execution_role()
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'nlpconnect/vit-gpt2-image-captioning',
	'HF_TASK':'automatic-speech-recognition'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	env=hub,
	role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1, # number of instances
	instance_type='ml.m5.xlarge' # ec2 instance type
)

predictor.predict({
	'inputs': No input example has been defined for this model task.
})
</pre>
{{!}}-{{!}}
Local Machine=
<pre>
from sagemaker.huggingface import HuggingFaceModel
import boto3

iam_client = boto3.client('iam')
role = iam_client.get_role(RoleName='{IAM_ROLE_WITH_SAGEMAKER_PERMISSIONS}')['Role']['Arn']
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'nlpconnect/vit-gpt2-image-captioning',
	'HF_TASK':'automatic-speech-recognition'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	env=hub,
	role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1, # number of instances
	instance_type='ml.m5.xlarge' # ec2 instance type
)

predictor.predict({
	'inputs': No input example has been defined for this model task.
})
</pre>
}}
|-|Conversational=
{{#tag:tabber|
AWS=
<pre>
from sagemaker.huggingface import HuggingFaceModel
import sagemaker

role = sagemaker.get_execution_role()
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'nlpconnect/vit-gpt2-image-captioning',
	'HF_TASK':'conversational'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	env=hub,
	role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1, # number of instances
	instance_type='ml.m5.xlarge' # ec2 instance type
)

predictor.predict({
	'inputs': No input example has been defined for this model task.
})
</pre>
{{!}}-{{!}}
Local Machine=
<pre>
from sagemaker.huggingface import HuggingFaceModel
import boto3

iam_client = boto3.client('iam')
role = iam_client.get_role(RoleName='{IAM_ROLE_WITH_SAGEMAKER_PERMISSIONS}')['Role']['Arn']
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'nlpconnect/vit-gpt2-image-captioning',
	'HF_TASK':'conversational'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	env=hub,
	role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1, # number of instances
	instance_type='ml.m5.xlarge' # ec2 instance type
)

predictor.predict({
	'inputs': No input example has been defined for this model task.
})
</pre>
}}
|-|Feature Extraction=
{{#tag:tabber|
AWS=
<pre>
from sagemaker.huggingface import HuggingFaceModel
import sagemaker

role = sagemaker.get_execution_role()
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'nlpconnect/vit-gpt2-image-captioning',
	'HF_TASK':'feature-extraction'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	env=hub,
	role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1, # number of instances
	instance_type='ml.m5.xlarge' # ec2 instance type
)

predictor.predict({
	'inputs': No input example has been defined for this model task.
})
</pre>
{{!}}-{{!}}
Local Machine=
<pre>
from sagemaker.huggingface import HuggingFaceModel
import boto3

iam_client = boto3.client('iam')
role = iam_client.get_role(RoleName='{IAM_ROLE_WITH_SAGEMAKER_PERMISSIONS}')['Role']['Arn']
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'nlpconnect/vit-gpt2-image-captioning',
	'HF_TASK':'feature-extraction'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	env=hub,
	role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1, # number of instances
	instance_type='ml.m5.xlarge' # ec2 instance type
)

predictor.predict({
	'inputs': No input example has been defined for this model task.
})
</pre>
}}
|-|Fill-Mask=
{{#tag:tabber|
AWS=
<pre>
from sagemaker.huggingface import HuggingFaceModel
import sagemaker

role = sagemaker.get_execution_role()
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'nlpconnect/vit-gpt2-image-captioning',
	'HF_TASK':'fill-mask'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	env=hub,
	role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1, # number of instances
	instance_type='ml.m5.xlarge' # ec2 instance type
)

predictor.predict({
	'inputs': No input example has been defined for this model task.
})
</pre>
{{!}}-{{!}}
Local Machine=
<pre>
from sagemaker.huggingface import HuggingFaceModel
import boto3

iam_client = boto3.client('iam')
role = iam_client.get_role(RoleName='{IAM_ROLE_WITH_SAGEMAKER_PERMISSIONS}')['Role']['Arn']
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'nlpconnect/vit-gpt2-image-captioning',
	'HF_TASK':'fill-mask'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	env=hub,
	role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1, # number of instances
	instance_type='ml.m5.xlarge' # ec2 instance type
)

predictor.predict({
	'inputs': No input example has been defined for this model task.
})
</pre>
}}
|-|Image Classification=
{{#tag:tabber|
AWS=
<pre>
from sagemaker.huggingface import HuggingFaceModel
import sagemaker

role = sagemaker.get_execution_role()
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'nlpconnect/vit-gpt2-image-captioning',
	'HF_TASK':'image-classification'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	env=hub,
	role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1, # number of instances
	instance_type='ml.m5.xlarge' # ec2 instance type
)

predictor.predict({
	'inputs': No input example has been defined for this model task.
})
</pre>
{{!}}-{{!}}
Local Machine=
<pre>
from sagemaker.huggingface import HuggingFaceModel
import boto3

iam_client = boto3.client('iam')
role = iam_client.get_role(RoleName='{IAM_ROLE_WITH_SAGEMAKER_PERMISSIONS}')['Role']['Arn']
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'nlpconnect/vit-gpt2-image-captioning',
	'HF_TASK':'image-classification'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	env=hub,
	role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1, # number of instances
	instance_type='ml.m5.xlarge' # ec2 instance type
)

predictor.predict({
	'inputs': No input example has been defined for this model task.
})
</pre>
}}
|-|Question Answering=
{{#tag:tabber|
AWS=
<pre>
from sagemaker.huggingface import HuggingFaceModel
import sagemaker

role = sagemaker.get_execution_role()
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'nlpconnect/vit-gpt2-image-captioning',
	'HF_TASK':'question-answering'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	env=hub,
	role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1, # number of instances
	instance_type='ml.m5.xlarge' # ec2 instance type
)

predictor.predict({
	'inputs': No input example has been defined for this model task.
})
</pre>
{{!}}-{{!}}
Local Machine=
<pre>
from sagemaker.huggingface import HuggingFaceModel
import boto3

iam_client = boto3.client('iam')
role = iam_client.get_role(RoleName='{IAM_ROLE_WITH_SAGEMAKER_PERMISSIONS}')['Role']['Arn']
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'nlpconnect/vit-gpt2-image-captioning',
	'HF_TASK':'question-answering'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	env=hub,
	role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1, # number of instances
	instance_type='ml.m5.xlarge' # ec2 instance type
)

predictor.predict({
	'inputs': No input example has been defined for this model task.
})
</pre>
}}
|-|Summarization=
{{#tag:tabber|
AWS=
<pre>
from sagemaker.huggingface import HuggingFaceModel
import sagemaker

role = sagemaker.get_execution_role()
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'nlpconnect/vit-gpt2-image-captioning',
	'HF_TASK':'summarization'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	env=hub,
	role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1, # number of instances
	instance_type='ml.m5.xlarge' # ec2 instance type
)

predictor.predict({
	'inputs': No input example has been defined for this model task.
})
</pre>
{{!}}-{{!}}
Local Machine=
<pre>
from sagemaker.huggingface import HuggingFaceModel
import boto3

iam_client = boto3.client('iam')
role = iam_client.get_role(RoleName='{IAM_ROLE_WITH_SAGEMAKER_PERMISSIONS}')['Role']['Arn']
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'nlpconnect/vit-gpt2-image-captioning',
	'HF_TASK':'summarization'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	env=hub,
	role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1, # number of instances
	instance_type='ml.m5.xlarge' # ec2 instance type
)

predictor.predict({
	'inputs': No input example has been defined for this model task.
})
</pre>
}}
|-|Table Question Answering=
{{#tag:tabber|
AWS=
<pre>
from sagemaker.huggingface import HuggingFaceModel
import sagemaker

role = sagemaker.get_execution_role()
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'nlpconnect/vit-gpt2-image-captioning',
	'HF_TASK':'table-question-answering'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	env=hub,
	role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1, # number of instances
	instance_type='ml.m5.xlarge' # ec2 instance type
)

predictor.predict({
	'inputs': No input example has been defined for this model task.
})
</pre>
{{!}}-{{!}}
Local Machine=
<pre>
from sagemaker.huggingface import HuggingFaceModel
import boto3

iam_client = boto3.client('iam')
role = iam_client.get_role(RoleName='{IAM_ROLE_WITH_SAGEMAKER_PERMISSIONS}')['Role']['Arn']
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'nlpconnect/vit-gpt2-image-captioning',
	'HF_TASK':'table-question-answering'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	env=hub,
	role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1, # number of instances
	instance_type='ml.m5.xlarge' # ec2 instance type
)

predictor.predict({
	'inputs': No input example has been defined for this model task.
})
</pre>
}}
|-|Text Classification=
{{#tag:tabber|
AWS=
<pre>
from sagemaker.huggingface import HuggingFaceModel
import sagemaker

role = sagemaker.get_execution_role()
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'nlpconnect/vit-gpt2-image-captioning',
	'HF_TASK':'text-classification'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	env=hub,
	role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1, # number of instances
	instance_type='ml.m5.xlarge' # ec2 instance type
)

predictor.predict({
	'inputs': No input example has been defined for this model task.
})
</pre>
{{!}}-{{!}}
Local Machine=
<pre>
from sagemaker.huggingface import HuggingFaceModel
import boto3

iam_client = boto3.client('iam')
role = iam_client.get_role(RoleName='{IAM_ROLE_WITH_SAGEMAKER_PERMISSIONS}')['Role']['Arn']
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'nlpconnect/vit-gpt2-image-captioning',
	'HF_TASK':'text-classification'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	env=hub,
	role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1, # number of instances
	instance_type='ml.m5.xlarge' # ec2 instance type
)

predictor.predict({
	'inputs': No input example has been defined for this model task.
})
</pre>
}}
|-|Text Generation=
{{#tag:tabber|
AWS=
<pre>
from sagemaker.huggingface import HuggingFaceModel
import sagemaker

role = sagemaker.get_execution_role()
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'nlpconnect/vit-gpt2-image-captioning',
	'HF_TASK':'text-generation'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	env=hub,
	role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1, # number of instances
	instance_type='ml.m5.xlarge' # ec2 instance type
)

predictor.predict({
	'inputs': No input example has been defined for this model task.
})
</pre>
{{!}}-{{!}}
Local Machine=
<pre>
from sagemaker.huggingface import HuggingFaceModel
import boto3

iam_client = boto3.client('iam')
role = iam_client.get_role(RoleName='{IAM_ROLE_WITH_SAGEMAKER_PERMISSIONS}')['Role']['Arn']
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'nlpconnect/vit-gpt2-image-captioning',
	'HF_TASK':'text-generation'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	env=hub,
	role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1, # number of instances
	instance_type='ml.m5.xlarge' # ec2 instance type
)

predictor.predict({
	'inputs': No input example has been defined for this model task.
})
</pre>
}}
|-|Text2Text Generation=
{{#tag:tabber|
AWS=
<pre>
from sagemaker.huggingface import HuggingFaceModel
import sagemaker

role = sagemaker.get_execution_role()
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'nlpconnect/vit-gpt2-image-captioning',
	'HF_TASK':'text2text-generation'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	env=hub,
	role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1, # number of instances
	instance_type='ml.m5.xlarge' # ec2 instance type
)

predictor.predict({
	'inputs': No input example has been defined for this model task.
})
</pre>
{{!}}-{{!}}
Local Machine=
<pre>
from sagemaker.huggingface import HuggingFaceModel
import boto3

iam_client = boto3.client('iam')
role = iam_client.get_role(RoleName='{IAM_ROLE_WITH_SAGEMAKER_PERMISSIONS}')['Role']['Arn']
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'nlpconnect/vit-gpt2-image-captioning',
	'HF_TASK':'text2text-generation'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	env=hub,
	role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1, # number of instances
	instance_type='ml.m5.xlarge' # ec2 instance type
)

predictor.predict({
	'inputs': No input example has been defined for this model task.
})
</pre>
}}
|-|Token Classification=
{{#tag:tabber|
AWS=
<pre>
from sagemaker.huggingface import HuggingFaceModel
import sagemaker

role = sagemaker.get_execution_role()
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'nlpconnect/vit-gpt2-image-captioning',
	'HF_TASK':'token-classification'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	env=hub,
	role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1, # number of instances
	instance_type='ml.m5.xlarge' # ec2 instance type
)

predictor.predict({
	'inputs': No input example has been defined for this model task.
})
</pre>
{{!}}-{{!}}
Local Machine=
<pre>
from sagemaker.huggingface import HuggingFaceModel
import boto3

iam_client = boto3.client('iam')
role = iam_client.get_role(RoleName='{IAM_ROLE_WITH_SAGEMAKER_PERMISSIONS}')['Role']['Arn']
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'nlpconnect/vit-gpt2-image-captioning',
	'HF_TASK':'token-classification'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	env=hub,
	role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1, # number of instances
	instance_type='ml.m5.xlarge' # ec2 instance type
)

predictor.predict({
	'inputs': No input example has been defined for this model task.
})
</pre>
}}
|-|Translation=
{{#tag:tabber|
AWS=
<pre>
from sagemaker.huggingface import HuggingFaceModel
import sagemaker

role = sagemaker.get_execution_role()
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'nlpconnect/vit-gpt2-image-captioning',
	'HF_TASK':'translation'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	env=hub,
	role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1, # number of instances
	instance_type='ml.m5.xlarge' # ec2 instance type
)

predictor.predict({
	'inputs': No input example has been defined for this model task.
})
</pre>
{{!}}-{{!}}
Local Machine=
<pre>
from sagemaker.huggingface import HuggingFaceModel
import boto3

iam_client = boto3.client('iam')
role = iam_client.get_role(RoleName='{IAM_ROLE_WITH_SAGEMAKER_PERMISSIONS}')['Role']['Arn']
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'nlpconnect/vit-gpt2-image-captioning',
	'HF_TASK':'translation'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	env=hub,
	role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1, # number of instances
	instance_type='ml.m5.xlarge' # ec2 instance type
)

predictor.predict({
	'inputs': No input example has been defined for this model task.
})
</pre>
}}
|-|Zero-Shot Classification=
{{#tag:tabber|
AWS=
<pre>
from sagemaker.huggingface import HuggingFaceModel
import sagemaker

role = sagemaker.get_execution_role()
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'nlpconnect/vit-gpt2-image-captioning',
	'HF_TASK':'zero-shot-classification'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	env=hub,
	role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1, # number of instances
	instance_type='ml.m5.xlarge' # ec2 instance type
)

predictor.predict({
	'inputs': No input example has been defined for this model task.
})
</pre>
{{!}}-{{!}}
Local Machine=
<pre>
from sagemaker.huggingface import HuggingFaceModel
import boto3

iam_client = boto3.client('iam')
role = iam_client.get_role(RoleName='{IAM_ROLE_WITH_SAGEMAKER_PERMISSIONS}')['Role']['Arn']
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'nlpconnect/vit-gpt2-image-captioning',
	'HF_TASK':'zero-shot-classification'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	env=hub,
	role=role, 
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
	initial_instance_count=1, # number of instances
	instance_type='ml.m5.xlarge' # ec2 instance type
)

predictor.predict({
	'inputs': No input example has been defined for this model task.
})
</pre>
}}
</tabber>

===Spaces===
<pre>
import gradio as gr

gr.Interface.load("models/nlpconnect/vit-gpt2-image-captioning").launch()
</pre>

==Training==
===Amazon SageMaker===
<tabber>
|-|Causal Language Modeling=
{{#tag:tabber|
AWS=
<pre>
import sagemaker
from sagemaker.huggingface import HuggingFace

# gets role for executing training job
role = sagemaker.get_execution_role()
hyperparameters = {
	'model_name_or_path':'nlpconnect/vit-gpt2-image-captioning',
	'output_dir':'/opt/ml/model'
	# add your remaining hyperparameters
	# more info here https://github.com/huggingface/transformers/tree/v4.17.0/examples/pytorch/language-modeling
}

# git configuration to download our fine-tuning script
git_config = {'repo': 'https://github.com/huggingface/transformers.git','branch': 'v4.17.0'}

# creates Hugging Face estimator
huggingface_estimator = HuggingFace(
	entry_point='run_clm.py',
	source_dir='./examples/pytorch/language-modeling',
	instance_type='ml.p3.2xlarge',
	instance_count=1,
	role=role,
	git_config=git_config,
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	hyperparameters = hyperparameters
)

# starting the train job
huggingface_estimator.fit()
</pre>
{{!}}-{{!}}
Local Machine=
<pre>
import sagemaker
import boto3
from sagemaker.huggingface import HuggingFace

# gets role for executing training job
iam_client = boto3.client('iam')
role = iam_client.get_role(RoleName='{IAM_ROLE_WITH_SAGEMAKER_PERMISSIONS}')['Role']['Arn']
hyperparameters = {
	'model_name_or_path':'nlpconnect/vit-gpt2-image-captioning',
	'output_dir':'/opt/ml/model'
	# add your remaining hyperparameters
	# more info here https://github.com/huggingface/transformers/tree/v4.17.0/examples/pytorch/language-modeling
}

# git configuration to download our fine-tuning script
git_config = {'repo': 'https://github.com/huggingface/transformers.git','branch': 'v4.17.0'}

# creates Hugging Face estimator
huggingface_estimator = HuggingFace(
	entry_point='run_clm.py',
	source_dir='./examples/pytorch/language-modeling',
	instance_type='ml.p3.2xlarge',
	instance_count=1,
	role=role,
	git_config=git_config,
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	hyperparameters = hyperparameters
)

# starting the train job
huggingface_estimator.fit()
</pre>
}}
|-|Masked Language Modeling=
{{#tag:tabber|
AWS=
<pre>
import sagemaker
from sagemaker.huggingface import HuggingFace

# gets role for executing training job
role = sagemaker.get_execution_role()
hyperparameters = {
	'model_name_or_path':'nlpconnect/vit-gpt2-image-captioning',
	'output_dir':'/opt/ml/model'
	# add your remaining hyperparameters
	# more info here https://github.com/huggingface/transformers/tree/v4.17.0/examples/pytorch/language-modeling
}

# git configuration to download our fine-tuning script
git_config = {'repo': 'https://github.com/huggingface/transformers.git','branch': 'v4.17.0'}

# creates Hugging Face estimator
huggingface_estimator = HuggingFace(
	entry_point='run_mlm.py',
	source_dir='./examples/pytorch/language-modeling',
	instance_type='ml.p3.2xlarge',
	instance_count=1,
	role=role,
	git_config=git_config,
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	hyperparameters = hyperparameters
)

# starting the train job
huggingface_estimator.fit()
</pre>
{{!}}-{{!}}
Local Machine=
<pre>
import sagemaker
import boto3
from sagemaker.huggingface import HuggingFace

# gets role for executing training job
iam_client = boto3.client('iam')
role = iam_client.get_role(RoleName='{IAM_ROLE_WITH_SAGEMAKER_PERMISSIONS}')['Role']['Arn']
hyperparameters = {
	'model_name_or_path':'nlpconnect/vit-gpt2-image-captioning',
	'output_dir':'/opt/ml/model'
	# add your remaining hyperparameters
	# more info here https://github.com/huggingface/transformers/tree/v4.17.0/examples/pytorch/language-modeling
}

# git configuration to download our fine-tuning script
git_config = {'repo': 'https://github.com/huggingface/transformers.git','branch': 'v4.17.0'}

# creates Hugging Face estimator
huggingface_estimator = HuggingFace(
	entry_point='run_mlm.py',
	source_dir='./examples/pytorch/language-modeling',
	instance_type='ml.p3.2xlarge',
	instance_count=1,
	role=role,
	git_config=git_config,
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	hyperparameters = hyperparameters
)

# starting the train job
huggingface_estimator.fit()
</pre>
}}
|-|Question Answering=
{{#tag:tabber|
AWS=
<pre>
import sagemaker
from sagemaker.huggingface import HuggingFace

# gets role for executing training job
role = sagemaker.get_execution_role()
hyperparameters = {
	'model_name_or_path':'nlpconnect/vit-gpt2-image-captioning',
	'output_dir':'/opt/ml/model'
	# add your remaining hyperparameters
	# more info here https://github.com/huggingface/transformers/tree/v4.17.0/examples/pytorch/question-answering
}

# git configuration to download our fine-tuning script
git_config = {'repo': 'https://github.com/huggingface/transformers.git','branch': 'v4.17.0'}

# creates Hugging Face estimator
huggingface_estimator = HuggingFace(
	entry_point='run_qa.py',
	source_dir='./examples/pytorch/question-answering',
	instance_type='ml.p3.2xlarge',
	instance_count=1,
	role=role,
	git_config=git_config,
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	hyperparameters = hyperparameters
)

# starting the train job
huggingface_estimator.fit()
</pre>
{{!}}-{{!}}
Local Machine=
<pre>
import sagemaker
import boto3
from sagemaker.huggingface import HuggingFace

# gets role for executing training job
iam_client = boto3.client('iam')
role = iam_client.get_role(RoleName='{IAM_ROLE_WITH_SAGEMAKER_PERMISSIONS}')['Role']['Arn']
hyperparameters = {
	'model_name_or_path':'nlpconnect/vit-gpt2-image-captioning',
	'output_dir':'/opt/ml/model'
	# add your remaining hyperparameters
	# more info here https://github.com/huggingface/transformers/tree/v4.17.0/examples/pytorch/question-answering
}

# git configuration to download our fine-tuning script
git_config = {'repo': 'https://github.com/huggingface/transformers.git','branch': 'v4.17.0'}

# creates Hugging Face estimator
huggingface_estimator = HuggingFace(
	entry_point='run_qa.py',
	source_dir='./examples/pytorch/question-answering',
	instance_type='ml.p3.2xlarge',
	instance_count=1,
	role=role,
	git_config=git_config,
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	hyperparameters = hyperparameters
)

# starting the train job
huggingface_estimator.fit()
</pre>
}}
|-|Summarization=
{{#tag:tabber|
AWS=
<pre>
import sagemaker
from sagemaker.huggingface import HuggingFace

# gets role for executing training job
role = sagemaker.get_execution_role()
hyperparameters = {
	'model_name_or_path':'nlpconnect/vit-gpt2-image-captioning',
	'output_dir':'/opt/ml/model'
	# add your remaining hyperparameters
	# more info here https://github.com/huggingface/transformers/tree/v4.17.0/examples/pytorch/seq2seq
}

# git configuration to download our fine-tuning script
git_config = {'repo': 'https://github.com/huggingface/transformers.git','branch': 'v4.17.0'}

# creates Hugging Face estimator
huggingface_estimator = HuggingFace(
	entry_point='run_summarization.py',
	source_dir='./examples/pytorch/seq2seq',
	instance_type='ml.p3.2xlarge',
	instance_count=1,
	role=role,
	git_config=git_config,
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	hyperparameters = hyperparameters
)

# starting the train job
huggingface_estimator.fit()
</pre>
{{!}}-{{!}}
Local Machine=
<pre>
import sagemaker
import boto3
from sagemaker.huggingface import HuggingFace

# gets role for executing training job
iam_client = boto3.client('iam')
role = iam_client.get_role(RoleName='{IAM_ROLE_WITH_SAGEMAKER_PERMISSIONS}')['Role']['Arn']
hyperparameters = {
	'model_name_or_path':'nlpconnect/vit-gpt2-image-captioning',
	'output_dir':'/opt/ml/model'
	# add your remaining hyperparameters
	# more info here https://github.com/huggingface/transformers/tree/v4.17.0/examples/pytorch/seq2seq
}

# git configuration to download our fine-tuning script
git_config = {'repo': 'https://github.com/huggingface/transformers.git','branch': 'v4.17.0'}

# creates Hugging Face estimator
huggingface_estimator = HuggingFace(
	entry_point='run_summarization.py',
	source_dir='./examples/pytorch/seq2seq',
	instance_type='ml.p3.2xlarge',
	instance_count=1,
	role=role,
	git_config=git_config,
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	hyperparameters = hyperparameters
)

# starting the train job
huggingface_estimator.fit()
</pre>
}}
|-|Text Classification=
{{#tag:tabber|
AWS=
<pre>
import sagemaker
from sagemaker.huggingface import HuggingFace

# gets role for executing training job
role = sagemaker.get_execution_role()
hyperparameters = {
	'model_name_or_path':'nlpconnect/vit-gpt2-image-captioning',
	'output_dir':'/opt/ml/model'
	# add your remaining hyperparameters
	# more info here https://github.com/huggingface/transformers/tree/v4.17.0/examples/pytorch/text-classification
}

# git configuration to download our fine-tuning script
git_config = {'repo': 'https://github.com/huggingface/transformers.git','branch': 'v4.17.0'}

# creates Hugging Face estimator
huggingface_estimator = HuggingFace(
	entry_point='run_glue.py',
	source_dir='./examples/pytorch/text-classification',
	instance_type='ml.p3.2xlarge',
	instance_count=1,
	role=role,
	git_config=git_config,
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	hyperparameters = hyperparameters
)

# starting the train job
huggingface_estimator.fit()
</pre>
{{!}}-{{!}}
Local Machine=
<pre>
import sagemaker
import boto3
from sagemaker.huggingface import HuggingFace

# gets role for executing training job
iam_client = boto3.client('iam')
role = iam_client.get_role(RoleName='{IAM_ROLE_WITH_SAGEMAKER_PERMISSIONS}')['Role']['Arn']
hyperparameters = {
	'model_name_or_path':'nlpconnect/vit-gpt2-image-captioning',
	'output_dir':'/opt/ml/model'
	# add your remaining hyperparameters
	# more info here https://github.com/huggingface/transformers/tree/v4.17.0/examples/pytorch/text-classification
}

# git configuration to download our fine-tuning script
git_config = {'repo': 'https://github.com/huggingface/transformers.git','branch': 'v4.17.0'}

# creates Hugging Face estimator
huggingface_estimator = HuggingFace(
	entry_point='run_glue.py',
	source_dir='./examples/pytorch/text-classification',
	instance_type='ml.p3.2xlarge',
	instance_count=1,
	role=role,
	git_config=git_config,
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	hyperparameters = hyperparameters
)

# starting the train job
huggingface_estimator.fit()
</pre>
}}
|-|Token Classification=
{{#tag:tabber|
AWS=
<pre>
import sagemaker
from sagemaker.huggingface import HuggingFace

# gets role for executing training job
role = sagemaker.get_execution_role()
hyperparameters = {
	'model_name_or_path':'nlpconnect/vit-gpt2-image-captioning',
	'output_dir':'/opt/ml/model'
	# add your remaining hyperparameters
	# more info here https://github.com/huggingface/transformers/tree/v4.17.0/examples/pytorch/token-classification
}

# git configuration to download our fine-tuning script
git_config = {'repo': 'https://github.com/huggingface/transformers.git','branch': 'v4.17.0'}

# creates Hugging Face estimator
huggingface_estimator = HuggingFace(
	entry_point='run_ner.py',
	source_dir='./examples/pytorch/token-classification',
	instance_type='ml.p3.2xlarge',
	instance_count=1,
	role=role,
	git_config=git_config,
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	hyperparameters = hyperparameters
)

# starting the train job
huggingface_estimator.fit()
</pre>
{{!}}-{{!}}
Local Machine=
<pre>
import sagemaker
import boto3
from sagemaker.huggingface import HuggingFace

# gets role for executing training job
iam_client = boto3.client('iam')
role = iam_client.get_role(RoleName='{IAM_ROLE_WITH_SAGEMAKER_PERMISSIONS}')['Role']['Arn']
hyperparameters = {
	'model_name_or_path':'nlpconnect/vit-gpt2-image-captioning',
	'output_dir':'/opt/ml/model'
	# add your remaining hyperparameters
	# more info here https://github.com/huggingface/transformers/tree/v4.17.0/examples/pytorch/token-classification
}

# git configuration to download our fine-tuning script
git_config = {'repo': 'https://github.com/huggingface/transformers.git','branch': 'v4.17.0'}

# creates Hugging Face estimator
huggingface_estimator = HuggingFace(
	entry_point='run_ner.py',
	source_dir='./examples/pytorch/token-classification',
	instance_type='ml.p3.2xlarge',
	instance_count=1,
	role=role,
	git_config=git_config,
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	hyperparameters = hyperparameters
)

# starting the train job
huggingface_estimator.fit()
</pre>
}}
|-|Translation=
{{#tag:tabber|
AWS=
<pre>
import sagemaker
from sagemaker.huggingface import HuggingFace

# gets role for executing training job
role = sagemaker.get_execution_role()
hyperparameters = {
	'model_name_or_path':'nlpconnect/vit-gpt2-image-captioning',
	'output_dir':'/opt/ml/model'
	# add your remaining hyperparameters
	# more info here https://github.com/huggingface/transformers/tree/v4.17.0/examples/pytorch/seq2seq
}

# git configuration to download our fine-tuning script
git_config = {'repo': 'https://github.com/huggingface/transformers.git','branch': 'v4.17.0'}

# creates Hugging Face estimator
huggingface_estimator = HuggingFace(
	entry_point='run_translation.py',
	source_dir='./examples/pytorch/seq2seq',
	instance_type='ml.p3.2xlarge',
	instance_count=1,
	role=role,
	git_config=git_config,
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	hyperparameters = hyperparameters
)

# starting the train job
huggingface_estimator.fit()
</pre>
{{!}}-{{!}}
Local Machine=
<pre>
import sagemaker
import boto3
from sagemaker.huggingface import HuggingFace

# gets role for executing training job
iam_client = boto3.client('iam')
role = iam_client.get_role(RoleName='{IAM_ROLE_WITH_SAGEMAKER_PERMISSIONS}')['Role']['Arn']
hyperparameters = {
	'model_name_or_path':'nlpconnect/vit-gpt2-image-captioning',
	'output_dir':'/opt/ml/model'
	# add your remaining hyperparameters
	# more info here https://github.com/huggingface/transformers/tree/v4.17.0/examples/pytorch/seq2seq
}

# git configuration to download our fine-tuning script
git_config = {'repo': 'https://github.com/huggingface/transformers.git','branch': 'v4.17.0'}

# creates Hugging Face estimator
huggingface_estimator = HuggingFace(
	entry_point='run_translation.py',
	source_dir='./examples/pytorch/seq2seq',
	instance_type='ml.p3.2xlarge',
	instance_count=1,
	role=role,
	git_config=git_config,
	transformers_version='4.17.0',
	pytorch_version='1.10.2',
	py_version='py38',
	hyperparameters = hyperparameters
)

# starting the train job
huggingface_estimator.fit()
</pre>
}}
</tabber>

==Model Card==