Instructions to use pamessina/T5FactExtractor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pamessina/T5FactExtractor with Transformers:

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

pipe = pipeline("text-generation", model="pamessina/T5FactExtractor")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("pamessina/T5FactExtractor")
model = AutoModelForSeq2SeqLM.from_pretrained("pamessina/T5FactExtractor", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pamessina/T5FactExtractor with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pamessina/T5FactExtractor"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pamessina/T5FactExtractor",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/pamessina/T5FactExtractor

SGLang

How to use pamessina/T5FactExtractor 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 "pamessina/T5FactExtractor" \
    --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": "pamessina/T5FactExtractor",
		"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 "pamessina/T5FactExtractor" \
        --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": "pamessina/T5FactExtractor",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pamessina/T5FactExtractor with Docker Model Runner:
```
docker model run hf.co/pamessina/T5FactExtractor
```

Update README.md

by denisparra - opened Jan 9

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+10

-3

Files changed (1) hide show

README.md +10 -3

README.md CHANGED Viewed

@@ -1,3 +1,10 @@
----
-license: apache-2.0
----

+---
+license: apache-2.0
+---
+T5FactExtractor is an encoder-decoder model trained to extract radiological facts from the findings and impression sections of X-ray radiological reports, as described in the article:
+Pablo Messina, Rene Vidal, Denis Parra, Alvaro Soto, and Vladimir Araujo. 2024.
+**Extracting and Encoding: Leveraging Large Language Models and Medical Knowledge to Enhance Radiological Text Representation**.
+In Findings of the Association for Computational Linguistics: ACL 2024, pages 3955–3986, Bangkok, Thailand. Association for Computational Linguistics.
+https://aclanthology.org/2024.findings-acl.236/