Instructions to use GeorgiaTech/scibert-generative-pubmedqa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GeorgiaTech/scibert-generative-pubmedqa with Transformers:

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

pipe = pipeline("text-generation", model="GeorgiaTech/scibert-generative-pubmedqa")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("GeorgiaTech/scibert-generative-pubmedqa")
model = AutoModelForSeq2SeqLM.from_pretrained("GeorgiaTech/scibert-generative-pubmedqa")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use GeorgiaTech/scibert-generative-pubmedqa with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/GeorgiaTech/scibert-generative-pubmedqa

SGLang

How to use GeorgiaTech/scibert-generative-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 "GeorgiaTech/scibert-generative-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": "GeorgiaTech/scibert-generative-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 "GeorgiaTech/scibert-generative-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": "GeorgiaTech/scibert-generative-pubmedqa",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use GeorgiaTech/scibert-generative-pubmedqa with Docker Model Runner:
```
docker model run hf.co/GeorgiaTech/scibert-generative-pubmedqa
```

hbeadles commited on Apr 26, 2024

Commit

cf9a941

verified ·

1 Parent(s): 93faf03

Update README.md

Browse files

Files changed (1) hide show

README.md +19 -0

README.md CHANGED Viewed

@@ -1,3 +1,22 @@
 ---
 license: mit
 ---

 ---
 license: mit
+datasets:
+- qiaojin/PubMedQA
+language:
+- en
+pipeline_tag: text2text-generation
+tags:
+- medical
 ---
+*Author - Hayden Beadles*
+This model is meant to evaluate the results of creating an Encoder / Decoder generative model using SciBERT. The model is then finetuned on 30000 samples of the PubMedQA dataset. Instead of being finetuned
+on the columns **question** and **final_answer**, where **final_answer** is a set of yes / no answers, we instead fine tune on the more challenging **long_answer** column, which gives a short answer
+to the question.
+The model was fine-tuned over 3 epochs, using the Adam learning rate scheduler, with a max length of 128 tokens.
+The results are to help gauge SciBERT's abilities to answer (generate an answer) directly to a question, with no context provided. It is meant to evaluate the overall models training and attention towards
+a more focused topic, to see if SciBERTs base training gives it any advantages.