Instructions to use obss/mt5-small-3task-both-tquad2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use obss/mt5-small-3task-both-tquad2 with Transformers:

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

pipe = pipeline("text-generation", model="obss/mt5-small-3task-both-tquad2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("obss/mt5-small-3task-both-tquad2")
model = AutoModelForSeq2SeqLM.from_pretrained("obss/mt5-small-3task-both-tquad2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use obss/mt5-small-3task-both-tquad2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "obss/mt5-small-3task-both-tquad2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "obss/mt5-small-3task-both-tquad2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/obss/mt5-small-3task-both-tquad2

SGLang

How to use obss/mt5-small-3task-both-tquad2 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 "obss/mt5-small-3task-both-tquad2" \
    --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": "obss/mt5-small-3task-both-tquad2",
		"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 "obss/mt5-small-3task-both-tquad2" \
        --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": "obss/mt5-small-3task-both-tquad2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use obss/mt5-small-3task-both-tquad2 with Docker Model Runner:
```
docker model run hf.co/obss/mt5-small-3task-both-tquad2
```

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

mt5-small for Turkish Question Generation

Automated question generation and question answering using text-to-text transformers by OBSS AI.

from core.api import GenerationAPI
generation_api = GenerationAPI('mt5-small-3task-both-tquad2', qg_format='both')

Citation 📜

@article{akyon2022questgen,
    author = {Akyon, Fatih Cagatay and Cavusoglu, Ali Devrim Ekin and Cengiz, Cemil and Altinuc, Sinan Onur and Temizel, Alptekin},
    doi = {10.3906/elk-1300-0632.3914},
    journal = {Turkish Journal of Electrical Engineering and Computer Sciences},
    title = {{Automated question generation and question answering from Turkish texts}},
    url = {https://journals.tubitak.gov.tr/elektrik/vol30/iss5/17/},
    year = {2022}
}

Overview ✔️

Language model: mt5-small
Language: Turkish
Downstream-task: Extractive QA/QG, Answer Extraction
Training data: TQuADv2-train Code: https://github.com/obss/turkish-question-generation
Paper: https://journals.tubitak.gov.tr/elektrik/vol30/iss5/17/

Hyperparameters

batch_size = 256
n_epochs = 15
base_LM_model = "mt5-small"
max_source_length = 512
max_target_length = 64
learning_rate = 1.0e-3
task_lisst = ["qa", "qg", "ans_ext"]
qg_format = "both"

Performance

Refer to paper.

Usage 🔥

from core.api import GenerationAPI

generation_api = GenerationAPI('mt5-small-3task-both-tquad2', qg_format='both')

context = """
Bu modelin eğitiminde, Türkçe soru cevap verileri kullanılmıştır.
Çalışmada sunulan yöntemle, Türkçe metinlerden otomatik olarak soru ve cevap
üretilebilir. Bu proje ile paylaşılan kaynak kodu ile Türkçe Soru Üretme
/ Soru Cevaplama konularında yeni akademik çalışmalar yapılabilir.
Projenin detaylarına paylaşılan Github ve Arxiv linklerinden ulaşılabilir.
"""

# a) Fully Automated Question Generation
generation_api(task='question-generation', context=context)

# b) Question Answering
question = "Bu model ne işe yarar?"
generation_api(task='question-answering', context=context, question=question)

# b) Answer Extraction
generation_api(task='answer-extraction', context=context)

Downloads last month: 13

Dataset used to train obss/mt5-small-3task-both-tquad2

Paper for obss/mt5-small-3task-both-tquad2

Automated question generation and question answering from Turkish texts

Paper • 2111.06476 • Published Nov 11, 2021 • 1