Instructions to use fewshot-goes-multilingual/mTk-AdversarialQA_en-SberQuAD_ru-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fewshot-goes-multilingual/mTk-AdversarialQA_en-SberQuAD_ru-1B with Transformers:

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

pipe = pipeline("text-generation", model="fewshot-goes-multilingual/mTk-AdversarialQA_en-SberQuAD_ru-1B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("fewshot-goes-multilingual/mTk-AdversarialQA_en-SberQuAD_ru-1B")
model = AutoModelForMultimodalLM.from_pretrained("fewshot-goes-multilingual/mTk-AdversarialQA_en-SberQuAD_ru-1B")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fewshot-goes-multilingual/mTk-AdversarialQA_en-SberQuAD_ru-1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fewshot-goes-multilingual/mTk-AdversarialQA_en-SberQuAD_ru-1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fewshot-goes-multilingual/mTk-AdversarialQA_en-SberQuAD_ru-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/fewshot-goes-multilingual/mTk-AdversarialQA_en-SberQuAD_ru-1B

SGLang

How to use fewshot-goes-multilingual/mTk-AdversarialQA_en-SberQuAD_ru-1B 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 "fewshot-goes-multilingual/mTk-AdversarialQA_en-SberQuAD_ru-1B" \
    --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": "fewshot-goes-multilingual/mTk-AdversarialQA_en-SberQuAD_ru-1B",
		"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 "fewshot-goes-multilingual/mTk-AdversarialQA_en-SberQuAD_ru-1B" \
        --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": "fewshot-goes-multilingual/mTk-AdversarialQA_en-SberQuAD_ru-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use fewshot-goes-multilingual/mTk-AdversarialQA_en-SberQuAD_ru-1B with Docker Model Runner:
```
docker model run hf.co/fewshot-goes-multilingual/mTk-AdversarialQA_en-SberQuAD_ru-1B
```

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 for mTk-AdversarialQA_en-SberQuAD_ru-1B

This model is a generative in-context few-shot learner specialized in Russian. It was trained on a combination of English AdversarialQA and Russian SberQuAD datasets.

You can find detailed information on Project Github & the referenced paper.

Model Details

Model Description

Developed by: Michal Stefanik & Marek Kadlcik, Masaryk University
Model type: mt5
Language(s) (NLP): en,ru
License: MIT
Finetuned from model: google/mt5-large

Model Sources

Repository: https://github.com/fewshot-goes-multilingual/slavic-incontext-learning
Paper: https://arxiv.org/abs/2304.01922

Uses

This model is intended to be used in a few-shot in-context learning format in the target language (Russian), or in the source language (English, see below). It was evaluated for unseen task learning (with k=3 demonstrations) in Russian: see the referenced paper for details.

How to Get Started with the Model

Use the code below to get started with the model.

from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
model = AutoModelForSeq2SeqLM.from_pretrained("{this model path}")
tokenizer = AutoTokenizer.from_pretrained("{this model path}")
# Instead, use keywords "Вопрос", "Контекст" and "Отвечать" for Russian few-shot prompts
input_text = """
    Question: What is the customer's name? 
    Context: Origin: Barrack Obama, Customer id: Bill Moe. 
    Answer: Bill Moe, 
    Question: What is the customer's name? 
    Context: Customer id: Barrack Obama, if not deliverable, return to Bill Clinton. 
    Answer:
"""
inputs = tokenizer(input_text, return_tensors="pt")

outputs = model.generate(**inputs)
print("Answer:")
print(tokenizer.decode(outputs))

Training Details

Training this model can be reproduced by running pip install -r requirements.txt && python train_mt5_qa_en_AQA+ru_info.py . See the referenced script for hyperparameters and other training configurations.

Citation

If you use our models or other resources in your research, please cite our work as follows.

BibTeX:

@inproceedings{stefanik2023resources,
               author = {\v{S}tef\'{a}nik, Michal and Kadlčík, Marek and Gramacki, Piotr and Sojka, Petr},
               title = {Resources and Few-shot Learners for In-context Learning in Slavic Languages},
               booktitle = {Proceedings of the 9th Workshop on Slavic Natural Language Processing},
               publisher = {ACL},
               numpages = {9},
               url = {https://arxiv.org/abs/2304.01922},
}

Downloads last month: 6

Safetensors

Model size

1B params

Tensor type

F32

Datasets used to train fewshot-goes-multilingual/mTk-AdversarialQA_en-SberQuAD_ru-1B

Paper for fewshot-goes-multilingual/mTk-AdversarialQA_en-SberQuAD_ru-1B

Resources and Few-shot Learners for In-context Learning in Slavic Languages

Paper • 2304.01922 • Published Apr 4, 2023