ai4bharat / MultiIndicQuestionGenerationSS

huggingface.co
Total runs: 9
24-hour runs: 0
7-day runs: 1
30-day runs: 1
Model's Last Updated: Mai 23 2022
text2text-generation

Introduction of MultiIndicQuestionGenerationSS

Model Details of MultiIndicQuestionGenerationSS

MultiIndicQuestionGenerationSS

MultiIndicQuestionGenerationSS is a multilingual, sequence-to-sequence pre-trained model, a IndicBARTSS checkpoint fine-tuned on the 11 languages of IndicQuestionGeneration dataset. For fine-tuning details, see the paper . You can use MultiIndicQuestionGenerationSS to build question generation applications for Indian languages by fine-tuning the model with supervised training data for the question generation task. Some salient features of the MultiIndicQuestionGenerationSS are:

  • Supported languages: Assamese, Bengali, Gujarati, Hindi, Marathi, Oriya, Punjabi, Kannada, Malayalam, Tamil, and Telugu. Not all of these languages are supported by mBART50 and mT5.
  • The model is much smaller than the mBART and mT5(-base) models, so less computationally expensive for finetuning and decoding.
  • Fine-tuned on large Indic language corpora (770 K examples).
  • Unlike ai4bharat/MultiIndicQuestionGenerationUnified, each language is written in its own script, so you do not need to perform any script mapping to/from Devanagari.

You can read more about MultiIndicQuestionGenerationSS in this paper .

Using this model in transformers
from transformers import MBartForConditionalGeneration, AutoModelForSeq2SeqLM
from transformers import AlbertTokenizer, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("ai4bharat/MultiIndicQuestionGenerationSS", do_lower_case=False, use_fast=False, keep_accents=True)

# Or use tokenizer = AlbertTokenizer.from_pretrained("ai4bharat/MultiIndicQuestionGenerationSS", do_lower_case=False, use_fast=False, keep_accents=True)

model = AutoModelForSeq2SeqLM.from_pretrained("ai4bharat/MultiIndicQuestionGenerationSS")

# Or use model = MBartForConditionalGeneration.from_pretrained("ai4bharat/MultiIndicQuestionGenerationSS")

# Some initial mapping
bos_id = tokenizer._convert_token_to_id_with_added_voc("<s>")
eos_id = tokenizer._convert_token_to_id_with_added_voc("</s>")
pad_id = tokenizer._convert_token_to_id_with_added_voc("<pad>")
# To get lang_id use any of ['<2as>', '<2bn>', '<2gu>', '<2hi>', '<2kn>', '<2ml>', '<2mr>', '<2or>', '<2pa>', '<2ta>', '<2te>']

# First tokenize the input and outputs. The format below is how IndicBARTSS was trained so the input should be "Sentence </s> <2xx>" where xx is the language code. Similarly, the output should be "<2yy> Sentence </s>". 
inp = tokenizer("7 फरवरी, 2016 [SEP] खेल 7 फरवरी, 2016 को कैलिफोर्निया के सांता क्लारा में सैन फ्रांसिस्को खाड़ी क्षेत्र में लेवी स्टेडियम में खेला गया था। </s> <2hi>", add_special_tokens=False, return_tensors="pt", padding=True).input_ids 

out = tokenizer("<2hi> सुपर बाउल किस दिन खेला गया? </s>", add_special_tokens=False, return_tensors="pt", padding=True).input_ids 

model_outputs=model(input_ids=inp, decoder_input_ids=out[:,0:-1], labels=out[:,1:])

# For loss
model_outputs.loss ## This is not label smoothed.

# For logits
model_outputs.logits

# For generation. Pardon the messiness. Note the decoder_start_token_id.

model.eval() # Set dropouts to zero

model_output=model.generate(inp, use_cache=True,no_repeat_ngram_size=3,encoder_no_repeat_ngram_size=3, num_beams=4, max_length=20, min_length=1, early_stopping=True, pad_token_id=pad_id, bos_token_id=bos_id, eos_token_id=eos_id, decoder_start_token_id=tokenizer._convert_token_to_id_with_added_voc("<2hi>"))

# Decode to get output strings
decoded_output=tokenizer.decode(model_output[0], skip_special_tokens=True, clean_up_tokenization_spaces=False)

print(decoded_output) # कब होगा पहला एएफएल गेम?
Benchmarks

Scores on the IndicQuestionGeneration test sets are as follows:

Language RougeL
as 20.73
bn 30.38
gu 28.13
hi 34.42
kn 23.77
ml 22.24
mr 23.62
or 27.53
pa 32.53
ta 23.49
te 25.81
Citation

If you use this model, please cite the following paper:

@inproceedings{Kumar2022IndicNLGSM,
  title={IndicNLG Suite: Multilingual Datasets for Diverse NLG Tasks in Indic Languages},
  author={Aman Kumar and Himani Shrotriya and Prachi Sahu and Raj Dabre and Ratish Puduppully and Anoop Kunchukuttan and Amogh Mishra and Mitesh M. Khapra and Pratyush Kumar},
  year={2022},
  url = "https://arxiv.org/abs/2203.05437"
  }

License

The model is available under the MIT License.

Runs of ai4bharat MultiIndicQuestionGenerationSS on huggingface.co

9
Total runs
0
24-hour runs
1
3-day runs
1
7-day runs
1
30-day runs

More Information About MultiIndicQuestionGenerationSS huggingface.co Model

MultiIndicQuestionGenerationSS huggingface.co

MultiIndicQuestionGenerationSS huggingface.co is an AI model on huggingface.co that provides MultiIndicQuestionGenerationSS's model effect (), which can be used instantly with this ai4bharat MultiIndicQuestionGenerationSS model. huggingface.co supports a free trial of the MultiIndicQuestionGenerationSS model, and also provides paid use of the MultiIndicQuestionGenerationSS. Support call MultiIndicQuestionGenerationSS model through api, including Node.js, Python, http.

MultiIndicQuestionGenerationSS huggingface.co Url

https://huggingface.co/ai4bharat/MultiIndicQuestionGenerationSS

ai4bharat MultiIndicQuestionGenerationSS online free

MultiIndicQuestionGenerationSS huggingface.co is an online trial and call api platform, which integrates MultiIndicQuestionGenerationSS's modeling effects, including api services, and provides a free online trial of MultiIndicQuestionGenerationSS, you can try MultiIndicQuestionGenerationSS online for free by clicking the link below.

ai4bharat MultiIndicQuestionGenerationSS online free url in huggingface.co:

https://huggingface.co/ai4bharat/MultiIndicQuestionGenerationSS

MultiIndicQuestionGenerationSS install

MultiIndicQuestionGenerationSS is an open source model from GitHub that offers a free installation service, and any user can find MultiIndicQuestionGenerationSS on GitHub to install. At the same time, huggingface.co provides the effect of MultiIndicQuestionGenerationSS install, users can directly use MultiIndicQuestionGenerationSS installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

MultiIndicQuestionGenerationSS install url in huggingface.co:

https://huggingface.co/ai4bharat/MultiIndicQuestionGenerationSS

Url of MultiIndicQuestionGenerationSS

MultiIndicQuestionGenerationSS huggingface.co Url

Provider of MultiIndicQuestionGenerationSS huggingface.co

ai4bharat
ORGANIZATIONS

Other API from ai4bharat

huggingface.co

Total runs: 1.1M
Run Growth: 781.3K
Growth Rate: 67.72%
Updated: August 07 2022
huggingface.co

Total runs: 49.5K
Run Growth: 3.2K
Growth Rate: 6.71%
Updated: Dezember 21 2022
huggingface.co

Total runs: 1.7K
Run Growth: 350
Growth Rate: 19.84%
Updated: August 07 2022
huggingface.co

Total runs: 1.1K
Run Growth: -3.1K
Growth Rate: -276.92%
Updated: März 11 2024
huggingface.co

Total runs: 223
Run Growth: -81
Growth Rate: -23.62%
Updated: Oktober 18 2024
huggingface.co

Total runs: 24
Run Growth: 9
Growth Rate: 42.86%
Updated: Oktober 18 2024
huggingface.co

Total runs: 18
Run Growth: 7
Growth Rate: 30.43%
Updated: Oktober 18 2024
huggingface.co

Total runs: 8
Run Growth: -3
Growth Rate: -11.54%
Updated: Oktober 18 2024
huggingface.co

Total runs: 3
Run Growth: 17
Growth Rate: 56.67%
Updated: Oktober 18 2024
huggingface.co

Total runs: 3
Run Growth: 10
Growth Rate: 40.00%
Updated: Oktober 18 2024