Instructions to use vocabtrimmer/mt5-small-trimmed-it-itquad-qg with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vocabtrimmer/mt5-small-trimmed-it-itquad-qg with Transformers:

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

pipe = pipeline("text-generation", model="vocabtrimmer/mt5-small-trimmed-it-itquad-qg")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("vocabtrimmer/mt5-small-trimmed-it-itquad-qg")
model = AutoModelForMultimodalLM.from_pretrained("vocabtrimmer/mt5-small-trimmed-it-itquad-qg")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use vocabtrimmer/mt5-small-trimmed-it-itquad-qg with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/vocabtrimmer/mt5-small-trimmed-it-itquad-qg

SGLang

How to use vocabtrimmer/mt5-small-trimmed-it-itquad-qg 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 "vocabtrimmer/mt5-small-trimmed-it-itquad-qg" \
    --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": "vocabtrimmer/mt5-small-trimmed-it-itquad-qg",
		"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 "vocabtrimmer/mt5-small-trimmed-it-itquad-qg" \
        --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": "vocabtrimmer/mt5-small-trimmed-it-itquad-qg",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use vocabtrimmer/mt5-small-trimmed-it-itquad-qg with Docker Model Runner:
```
docker model run hf.co/vocabtrimmer/mt5-small-trimmed-it-itquad-qg
```

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 `vocabtrimmer/mt5-small-trimmed-it-itquad-qg`

This model is fine-tuned version of vocabtrimmer/mt5-small-trimmed-it for question generation task on the lmqg/qg_itquad (dataset_name: default) via lmqg.

Overview

Language model: vocabtrimmer/mt5-small-trimmed-it
Language: it
Training data: lmqg/qg_itquad (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="it", model="vocabtrimmer/mt5-small-trimmed-it-itquad-qg")

# model prediction
questions = model.generate_q(list_context="Dopo il 1971 , l' OPEC ha tardato ad adeguare i prezzi per riflettere tale deprezzamento.", list_answer="Dopo il 1971")

With transformers

from transformers import pipeline

pipe = pipeline("text2text-generation", "vocabtrimmer/mt5-small-trimmed-it-itquad-qg")
output = pipe("<hl> Dopo il 1971 <hl> , l' OPEC ha tardato ad adeguare i prezzi per riflettere tale deprezzamento.")

Evaluation

Metric (Question Generation): raw metric file

	Score	Type	Dataset
BERTScore	80.56	default	lmqg/qg_itquad
Bleu_1	22.44	default	lmqg/qg_itquad
Bleu_2	14.65	default	lmqg/qg_itquad
Bleu_3	10.11	default	lmqg/qg_itquad
Bleu_4	7.17	default	lmqg/qg_itquad
METEOR	17.45	default	lmqg/qg_itquad
MoverScore	56.59	default	lmqg/qg_itquad
ROUGE_L	21.78	default	lmqg/qg_itquad

Training hyperparameters

The following hyperparameters were used during fine-tuning:

dataset_path: lmqg/qg_itquad
dataset_name: default
input_types: paragraph_answer
output_types: question
prefix_types: None
model: vocabtrimmer/mt5-small-trimmed-it
max_length: 512
max_length_output: 32
epoch: 14
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: 2

Dataset used to train vocabtrimmer/mt5-small-trimmed-it-itquad-qg

Paper for vocabtrimmer/mt5-small-trimmed-it-itquad-qg

Generative Language Models for Paragraph-Level Question Generation

Paper • 2210.03992 • Published Oct 8, 2022

Evaluation results

BLEU4 (Question Generation) on lmqg/qg_itquad
self-reported

7.170
ROUGE-L (Question Generation) on lmqg/qg_itquad
self-reported

21.780
METEOR (Question Generation) on lmqg/qg_itquad
self-reported

17.450
BERTScore (Question Generation) on lmqg/qg_itquad
self-reported

80.560
MoverScore (Question Generation) on lmqg/qg_itquad
self-reported

56.590

Model Card of vocabtrimmer/mt5-small-trimmed-it-itquad-qg