Instructions to use microsoft/BioGPT-Large-PubMedQA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use microsoft/BioGPT-Large-PubMedQA with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="microsoft/BioGPT-Large-PubMedQA")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("microsoft/BioGPT-Large-PubMedQA")
model = AutoModelForCausalLM.from_pretrained("microsoft/BioGPT-Large-PubMedQA")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use microsoft/BioGPT-Large-PubMedQA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "microsoft/BioGPT-Large-PubMedQA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/BioGPT-Large-PubMedQA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/microsoft/BioGPT-Large-PubMedQA

SGLang

How to use microsoft/BioGPT-Large-PubMedQA with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "microsoft/BioGPT-Large-PubMedQA" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/BioGPT-Large-PubMedQA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "microsoft/BioGPT-Large-PubMedQA" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/BioGPT-Large-PubMedQA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use microsoft/BioGPT-Large-PubMedQA with Docker Model Runner:
```
docker model run hf.co/microsoft/BioGPT-Large-PubMedQA
```

Deployment error on Sagemaker: could not load model

by droxi-raveh - opened Jul 25, 2023

Discussion

droxi-raveh

Jul 25, 2023

Hi,
I'm trying to deploy an endpoint for of this model using sagemaker, specifically the code offered under 'Deploy':

import sagemaker
import boto3
from sagemaker.huggingface import HuggingFaceModel

try:
role = sagemaker.get_execution_role()
except ValueError:
iam = boto3.client('iam')
role = iam.get_role(RoleName='sagemaker_execution_role')['Role']['Arn']

models

hub = {
'HF_MODEL_ID':'microsoft/BioGPT-Large-PubMedQA',
'HF_TASK':'text-generation'
}

create Hugging Face Model Class

huggingface_model = HuggingFaceModel(
transformers_version='4.26.0',
pytorch_version='1.13.1',
py_version='py39',
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 ",
})

The deployment succeeded, but when calling predict, the workers die because they cannot load the model. When looking at the Cloudwatch logs, I see the following error:

2023-07-25T14:48:59,331 [INFO ] W-9000-microsoft__BioGPT-Large-P-stdout com.amazonaws.ml.mms.wlm.WorkerLifeCycle - ValueError: Could not load model /.sagemaker/mms/models/microsoft__BioGPT-Large-PubMedQA with any of the following classes: (<class 'transformers.models.auto.modeling_auto.AutoModelForCausalLM'>, <class 'transformers.models.biogpt.modeling_biogpt.BioGptForCausalLM'>).

Any idea on how to solve? Perhaps I need to use a newer version of transformers?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment