Instructions to use lmqg/mt5-small-dequad-ae with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lmqg/mt5-small-dequad-ae with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="lmqg/mt5-small-dequad-ae")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("lmqg/mt5-small-dequad-ae") model = AutoModelForSeq2SeqLM.from_pretrained("lmqg/mt5-small-dequad-ae") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use lmqg/mt5-small-dequad-ae with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lmqg/mt5-small-dequad-ae" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lmqg/mt5-small-dequad-ae", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/lmqg/mt5-small-dequad-ae
- SGLang
How to use lmqg/mt5-small-dequad-ae 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 "lmqg/mt5-small-dequad-ae" \ --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": "lmqg/mt5-small-dequad-ae", "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 "lmqg/mt5-small-dequad-ae" \ --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": "lmqg/mt5-small-dequad-ae", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use lmqg/mt5-small-dequad-ae with Docker Model Runner:
docker model run hf.co/lmqg/mt5-small-dequad-ae
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
Model Card of lmqg/mt5-small-dequad-ae
This model is fine-tuned version of google/mt5-small for answer extraction on the lmqg/qg_dequad (dataset_name: default) via lmqg.
Overview
- Language model: google/mt5-small
- Language: de
- Training data: lmqg/qg_dequad (default)
- Online Demo: https://autoqg.net/
- Repository: https://github.com/asahi417/lm-question-generation
- Paper: https://arxiv.org/abs/2210.03992
Usage
- With
lmqg
from lmqg import TransformersQG
# initialize model
model = TransformersQG(language="de", model="lmqg/mt5-small-dequad-ae")
# model prediction
answers = model.generate_a("das erste weltweit errichtete Hermann Brehmer 1855 im niederschlesischen ''Görbersdorf'' (heute Sokołowsko, Polen).")
- With
transformers
from transformers import pipeline
pipe = pipeline("text2text-generation", "lmqg/mt5-small-dequad-ae")
output = pipe("Sommerzeit <hl> Frühling <hl>: Umstellung von Normalzeit auf Sommerzeit – die Uhr wird um eine Stunde ''vor''gestellt. Herbst: Umstellung von Sommerzeit auf Normalzeit – die Uhr wird um eine Stunde ''zurück''gestellt. Als Sommerzeit wird die gegenüber der Zonenzeit meist um eine Stunde vorgestellte Uhrzeit bezeichnet, die während eines bestimmten Zeitraums im Sommerhalbjahr (und oft auch etwas darüber hinaus) als gesetzliche Zeit dient. Eine solche Regelung wird fast nur in Ländern der gemäßigten Zonen angewandt. Die mitteleuropäische Sommerzeit beginnt am letzten Sonntag im März um 2:00 Uhr MEZ, indem die Stundenzählung um eine Stunde von 2:00 Uhr auf 3:00 Uhr vorgestellt wird. Sie endet jeweils am letzten Sonntag im Oktober um 3:00 Uhr MESZ, indem die Stundenzählung um eine Stunde von 3:00 Uhr auf 2:00 Uhr zurückgestellt wird.")
Evaluation
- Metric (Answer Extraction): raw metric file
| Score | Type | Dataset | |
|---|---|---|---|
| AnswerExactMatch | 8.8 | default | lmqg/qg_dequad |
| AnswerF1Score | 36.07 | default | lmqg/qg_dequad |
| BERTScore | 74.03 | default | lmqg/qg_dequad |
| Bleu_1 | 17.77 | default | lmqg/qg_dequad |
| Bleu_2 | 11.73 | default | lmqg/qg_dequad |
| Bleu_3 | 7.74 | default | lmqg/qg_dequad |
| Bleu_4 | 5.11 | default | lmqg/qg_dequad |
| METEOR | 21.09 | default | lmqg/qg_dequad |
| MoverScore | 56.82 | default | lmqg/qg_dequad |
| ROUGE_L | 17.54 | default | lmqg/qg_dequad |
Training hyperparameters
The following hyperparameters were used during fine-tuning:
- dataset_path: lmqg/qg_dequad
- dataset_name: default
- input_types: ['paragraph_sentence']
- output_types: ['answer']
- prefix_types: None
- model: google/mt5-small
- max_length: 512
- max_length_output: 32
- epoch: 22
- batch: 32
- lr: 0.001
- fp16: False
- random_seed: 1
- gradient_accumulation_steps: 2
- label_smoothing: 0.15
The full configuration can be found at fine-tuning config file.
Citation
@inproceedings{ushio-etal-2022-generative,
title = "{G}enerative {L}anguage {M}odels for {P}aragraph-{L}evel {Q}uestion {G}eneration",
author = "Ushio, Asahi and
Alva-Manchego, Fernando and
Camacho-Collados, Jose",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, U.A.E.",
publisher = "Association for Computational Linguistics",
}
- Downloads last month
- 7
Dataset used to train lmqg/mt5-small-dequad-ae
Paper for lmqg/mt5-small-dequad-ae
Evaluation results
- BLEU4 (Answer Extraction) on lmqg/qg_dequadself-reported5.110
- ROUGE-L (Answer Extraction) on lmqg/qg_dequadself-reported17.540
- METEOR (Answer Extraction) on lmqg/qg_dequadself-reported21.090
- BERTScore (Answer Extraction) on lmqg/qg_dequadself-reported74.030
- MoverScore (Answer Extraction) on lmqg/qg_dequadself-reported56.820
- AnswerF1Score (Answer Extraction) on lmqg/qg_dequadself-reported36.070
- AnswerExactMatch (Answer Extraction) on lmqg/qg_dequadself-reported8.800