Bigcode/santacoder model

Revision as of 23:41, 17 May 2023 by Walle (talk | contribs) (Created page with "{{Model infobox | hugging-face-uri = bigcode/santacoder | creator = | type = Natural Language Processing | task = Text Generation | library = PyTorch, Transformers | dataset = bigcode/the-stack | language = code | paper = | license = arxiv:1911.02150, arxiv:2207.14255, arxiv:2301.03988, bigcode-openrail-m | related-to = gpt2, Eval Results | all-tags = Text Generation, PyTorch, Transformers, bigcode/the-stack, code, gpt2, Eval Results, arxiv:1911.02150, arxiv:2207.14255...")
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

Bigcode/santacoder model is a Natural Language Processing model used for Text Generation.

Model Description

Clone Model Repository

#Be sure to have git-lfs installed (https://git-lfs.com)
git lfs install
git clone https://huggingface.co/bigcode/santacoder
  
#To clone the repo without large files – just their pointers
#prepend git clone with the following env var:
GIT_LFS_SKIP_SMUDGE=1

#Be sure to have git-lfs installed (https://git-lfs.com)
git lfs install
git clone [email protected]:bigcode/santacoder
  
#To clone the repo without large files – just their pointers
#prepend git clone with the following env var:
GIT_LFS_SKIP_SMUDGE=1

Hugging Face Transformers Library

from transformers import AutoTokenizer, AutoModelWithLMHead

tokenizer = AutoTokenizer.from_pretrained("bigcode/santacoder")

model = AutoModelWithLMHead.from_pretrained("bigcode/santacoder")

Deployment

Inference API

import requests

API_URL = "https://api-inference.huggingface.co/models/bigcode/santacoder"
headers = {"Authorization": f"Bearer {API_TOKEN}"}

def query(payload):
	response = requests.post(API_URL, headers=headers, json=payload)
	return response.json()
	
output = query({
	"inputs": "Can you please let us know more details about your ",
})

async function query(data) {
	const response = await fetch(
		"https://api-inference.huggingface.co/models/bigcode/santacoder",
		{
			headers: { Authorization: "Bearer {API_TOKEN}" },
			method: "POST",
			body: JSON.stringify(data),
		}
	);
	const result = await response.json();
	return result;
}

query({"inputs": "Can you please let us know more details about your "}).then((response) => {
	console.log(JSON.stringify(response));
});

curl https://api-inference.huggingface.co/models/bigcode/santacoder \
	-X POST \
	-d '{"inputs": "Can you please let us know more details about your "}' \
	-H "Authorization: Bearer {API_TOKEN}"

Amazon SageMaker

from sagemaker.huggingface import HuggingFaceModel
import sagemaker

role = sagemaker.get_execution_role()
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'bigcode/santacoder',
	'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': "Can you please let us know more details about your "
})

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':'bigcode/santacoder',
	'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': "Can you please let us know more details about your "
})

from sagemaker.huggingface import HuggingFaceModel
import sagemaker

role = sagemaker.get_execution_role()
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'bigcode/santacoder',
	'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': "Can you please let us know more details about your "
})

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':'bigcode/santacoder',
	'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': "Can you please let us know more details about your "
})

from sagemaker.huggingface import HuggingFaceModel
import sagemaker

role = sagemaker.get_execution_role()
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'bigcode/santacoder',
	'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': "Can you please let us know more details about your "
})

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':'bigcode/santacoder',
	'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': "Can you please let us know more details about your "
})

from sagemaker.huggingface import HuggingFaceModel
import sagemaker

role = sagemaker.get_execution_role()
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'bigcode/santacoder',
	'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': "Can you please let us know more details about your "
})

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':'bigcode/santacoder',
	'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': "Can you please let us know more details about your "
})

from sagemaker.huggingface import HuggingFaceModel
import sagemaker

role = sagemaker.get_execution_role()
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'bigcode/santacoder',
	'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': "Can you please let us know more details about your "
})

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':'bigcode/santacoder',
	'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': "Can you please let us know more details about your "
})

from sagemaker.huggingface import HuggingFaceModel
import sagemaker

role = sagemaker.get_execution_role()
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'bigcode/santacoder',
	'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': "Can you please let us know more details about your "
})

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':'bigcode/santacoder',
	'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': "Can you please let us know more details about your "
})

from sagemaker.huggingface import HuggingFaceModel
import sagemaker

role = sagemaker.get_execution_role()
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'bigcode/santacoder',
	'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': "Can you please let us know more details about your "
})

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':'bigcode/santacoder',
	'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': "Can you please let us know more details about your "
})

from sagemaker.huggingface import HuggingFaceModel
import sagemaker

role = sagemaker.get_execution_role()
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'bigcode/santacoder',
	'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': "Can you please let us know more details about your "
})

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':'bigcode/santacoder',
	'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': "Can you please let us know more details about your "
})

from sagemaker.huggingface import HuggingFaceModel
import sagemaker

role = sagemaker.get_execution_role()
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'bigcode/santacoder',
	'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': "Can you please let us know more details about your "
})

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':'bigcode/santacoder',
	'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': "Can you please let us know more details about your "
})

from sagemaker.huggingface import HuggingFaceModel
import sagemaker

role = sagemaker.get_execution_role()
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'bigcode/santacoder',
	'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': "Can you please let us know more details about your "
})

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':'bigcode/santacoder',
	'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': "Can you please let us know more details about your "
})

from sagemaker.huggingface import HuggingFaceModel
import sagemaker

role = sagemaker.get_execution_role()
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'bigcode/santacoder',
	'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': "Can you please let us know more details about your "
})

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':'bigcode/santacoder',
	'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': "Can you please let us know more details about your "
})

from sagemaker.huggingface import HuggingFaceModel
import sagemaker

role = sagemaker.get_execution_role()
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'bigcode/santacoder',
	'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': "Can you please let us know more details about your "
})

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':'bigcode/santacoder',
	'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': "Can you please let us know more details about your "
})

from sagemaker.huggingface import HuggingFaceModel
import sagemaker

role = sagemaker.get_execution_role()
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'bigcode/santacoder',
	'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': "Can you please let us know more details about your "
})

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':'bigcode/santacoder',
	'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': "Can you please let us know more details about your "
})

from sagemaker.huggingface import HuggingFaceModel
import sagemaker

role = sagemaker.get_execution_role()
# Hub Model configuration. https://huggingface.co/models
hub = {
	'HF_MODEL_ID':'bigcode/santacoder',
	'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': "Can you please let us know more details about your "
})

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':'bigcode/santacoder',
	'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': "Can you please let us know more details about your "
})

Spaces

import gradio as gr

gr.Interface.load("models/bigcode/santacoder").launch()

Training

Amazon SageMaker

import sagemaker
from sagemaker.huggingface import HuggingFace

# gets role for executing training job
role = sagemaker.get_execution_role()
hyperparameters = {
	'model_name_or_path':'bigcode/santacoder',
	'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()

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':'bigcode/santacoder',
	'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()

import sagemaker
from sagemaker.huggingface import HuggingFace

# gets role for executing training job
role = sagemaker.get_execution_role()
hyperparameters = {
	'model_name_or_path':'bigcode/santacoder',
	'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()

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':'bigcode/santacoder',
	'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()

import sagemaker
from sagemaker.huggingface import HuggingFace

# gets role for executing training job
role = sagemaker.get_execution_role()
hyperparameters = {
	'model_name_or_path':'bigcode/santacoder',
	'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()

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':'bigcode/santacoder',
	'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()

import sagemaker
from sagemaker.huggingface import HuggingFace

# gets role for executing training job
role = sagemaker.get_execution_role()
hyperparameters = {
	'model_name_or_path':'bigcode/santacoder',
	'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()

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':'bigcode/santacoder',
	'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()

import sagemaker
from sagemaker.huggingface import HuggingFace

# gets role for executing training job
role = sagemaker.get_execution_role()
hyperparameters = {
	'model_name_or_path':'bigcode/santacoder',
	'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()

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':'bigcode/santacoder',
	'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()

import sagemaker
from sagemaker.huggingface import HuggingFace

# gets role for executing training job
role = sagemaker.get_execution_role()
hyperparameters = {
	'model_name_or_path':'bigcode/santacoder',
	'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()

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':'bigcode/santacoder',
	'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()

import sagemaker
from sagemaker.huggingface import HuggingFace

# gets role for executing training job
role = sagemaker.get_execution_role()
hyperparameters = {
	'model_name_or_path':'bigcode/santacoder',
	'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()

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':'bigcode/santacoder',
	'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()

Model Card