Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Fix AWS Sagemaker indentation, typo and header level

This commit is contained in:
Alvaro Bartolome 2024-10-05 13:26:25 +02:00
parent 2358c2bb54
commit 47c01cb048
No known key found for this signature in database
1 changed files with 16 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
docs/source/reference/api_reference.md
View File

@ -139,11 +139,11 @@ for message in chat_completion:
TGI can be deployed on various cloud providers for scalable and robust text generation. One such provider is Amazon SageMaker, which has recently added support for TGI. Here's how you can deploy TGI on Amazon SageMaker: TGI can be deployed on various cloud providers for scalable and robust text generation. One such provider is Amazon SageMaker, which has recently added support for TGI. Here's how you can deploy TGI on Amazon SageMaker:
## Amazon SageMaker ### Amazon SageMaker
To enable the Messages API in Amazon SageMaker you need to set the environment variable `MESSAGES_API_ENABLED=true`. To enable the Messages API in Amazon SageMaker you need to set the environment variable `MESSAGES_API_ENABLED=true`.
This will modify the `/invocations` route to accept Messages dictonaries consisting out of role and content. See the example below on how to deploy Llama with the new Messages API. This will modify the `/invocations` route to accept Messages dictionaries consisting out of role and content. See the example below on how to deploy Llama with the new Messages API.
```python ```python
import json import json
@ -152,35 +152,35 @@ import boto3
from sagemaker.huggingface import HuggingFaceModel, get_huggingface_llm_image_uri from sagemaker.huggingface import HuggingFaceModel, get_huggingface_llm_image_uri
try: try:
role = sagemaker.get_execution_role() role = sagemaker.get_execution_role()
except ValueError: except ValueError:
iam = boto3.client('iam') iam = boto3.client('iam')
role = iam.get_role(RoleName='sagemaker_execution_role')['Role']['Arn'] role = iam.get_role(RoleName='sagemaker_execution_role')['Role']['Arn']
# Hub Model configuration. https://huggingface.co/models # Hub Model configuration. https://huggingface.co/models
hub = { hub = {
'HF_MODEL_ID':'HuggingFaceH4/zephyr-7b-beta', 'HF_MODEL_ID':'HuggingFaceH4/zephyr-7b-beta',
'SM_NUM_GPUS': json.dumps(1), 'SM_NUM_GPUS': json.dumps(1),
'MESSAGES_API_ENABLED': True 'MESSAGES_API_ENABLED': True
} }
# create Hugging Face Model Class # create Hugging Face Model Class
huggingface_model = HuggingFaceModel( huggingface_model = HuggingFaceModel(
image_uri=get_huggingface_llm_image_uri("huggingface",version="1.4.0"), image_uri=get_huggingface_llm_image_uri("huggingface",version="1.4.0"),
env=hub, env=hub,
role=role, role=role,
) )
# deploy model to SageMaker Inference # deploy model to SageMaker Inference
predictor = huggingface_model.deploy( predictor = huggingface_model.deploy(
initial_instance_count=1, initial_instance_count=1,
instance_type="ml.g5.2xlarge", instance_type="ml.g5.2xlarge",
container_startup_health_check_timeout=300, container_startup_health_check_timeout=300,
) )
# send request # send request
predictor.predict({ predictor.predict({
"messages": [ "messages": [
{"role": "system", "content": "You are a helpful assistant." }, {"role": "system", "content": "You are a helpful assistant." },
{"role": "user", "content": "What is deep learning?"} {"role": "user", "content": "What is deep learning?"}
] ]