Instructions to use vabatista/t5-small-answer-extraction-en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vabatista/t5-small-answer-extraction-en with Transformers:

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

pipe = pipeline("text-generation", model="vabatista/t5-small-answer-extraction-en")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("vabatista/t5-small-answer-extraction-en")
model = AutoModelForSeq2SeqLM.from_pretrained("vabatista/t5-small-answer-extraction-en")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use vabatista/t5-small-answer-extraction-en with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vabatista/t5-small-answer-extraction-en"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vabatista/t5-small-answer-extraction-en",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/vabatista/t5-small-answer-extraction-en

SGLang

How to use vabatista/t5-small-answer-extraction-en 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 "vabatista/t5-small-answer-extraction-en" \
    --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": "vabatista/t5-small-answer-extraction-en",
		"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 "vabatista/t5-small-answer-extraction-en" \
        --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": "vabatista/t5-small-answer-extraction-en",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use vabatista/t5-small-answer-extraction-en with Docker Model Runner:
```
docker model run hf.co/vabatista/t5-small-answer-extraction-en
```

YAML Metadata Warning:The pipeline tag "text2text-generation" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other

This model is t5-small based and was trained using squad-v2 dataset to generate plausible answers (i.e. extract entities) from a context. You must use special token <ha>to delimiter the sentence you want to extract answers and also, start the input text as "generate answers"

Below is an example of usage:

extract answers: 
Several days before Colorado Congresswoman Lauren Boebert and a male companion were kicked out of a Denver showing of “Beetlejuice,” the representative of Colorado's 3rd congressional district spent campaign funds at his bar, filings with the Federal Election Commission show.
According to Boebert’s official filings with the Federal Election Commission dated Oct. 14, Boebert spent $317.48 at Hooch Craft Cocktail Bar in Aspen on July 31 for “Event Catering”, more than 10 days prior to the “Beetlejuice” incident.  
<ha> The Aspen, Colo. based bar is owned by Quinn Gallagher, 46, who was later revealed to be Boebert’s escort on the night that both were booted from the theater. <ha>

The expected output will be answers with <sep> tokens. For instance, in the above example, Quinn Gallagher `

Downloads last month: 5

vabatista
/

t5-small-answer-extraction-en

Dataset used to train vabatista/t5-small-answer-extraction-en