Releasing Hindi人工智能ai哪个好 ELECTRA model

This is a first attempt at a Hindi language model trained with Google Research’s ELECTRA.制作ai的软件

As of 2022 I recommend Google’s MuRIL model trained on English, Hindi, and other major Indian languages, both in their script and latinized script元宝大模型: https://huggingface.co/google/muril-base-cased and https://huggingface.co/google/muril-large-cased

For causal language models, I would suggest https://huggingface.co/sberbank-ai/mGPT, though this is a large modelgrok中文版下载

Tokenization and training CoLabai分析软件

I originally used a modified ELECTRA for finetuning, but now use SimpleTransformers百度流畅ai制作.

Blog post – I was greatly influenced by: https://huggingface.co/blog/how-to-train即梦下载官方

Example Notebooks

This small model has comparable results to Multilingual BERT on BBC Hindi news classification
and on Hindi movie reviews / sentiment analysis (using SimpleTransformers)

You can get higher accuracy using ktrain by adjusting learning rate (also: changing model_type in config.json – this is an open issue with ktrain): https://colab.research.google.com/drive/1mSeeSfVSOT7e-dVhPlmSsQRvpn6xC05w?usp=sharingima是什么软件

Question-answering on MLQA dataset: https://colab.research.google.com/drive/1i6fidh2tItf_-IDkljMuaIGmEU6HT2Ar#scrollTo=IcFoAHgKCUiQ百度流畅ai制作

A larger model (Hindi-TPU-Electra) using ELECTRA base size outperforms both models on Hindi movie reviews / sentiment analysis, but
does not perform as well on the BBC news classification task.

Corpus

Download: https://drive.google.com/drive/folders/1SXzisKq33wuqrwbfp428xeu_hDxXVUUu?usp=sharinggrok中文版下载

The corpus is two files:快问ai

• Hindi CommonCrawl deduped by OSCAR https://traces1.inria.fr/oscar/
• latest Hindi Wikipedia ( https://dumps.wikimedia.org/hiwiki/ ) + WikiExtractor to txt

Bonus notes:百度流畅ai制作

• Adding English wiki text or parallel corpus could help with cross-lingual tasks and training

Vocabulary

https://drive.google.com/file/d/1-6tXrii3tVxjkbrpSJE9MOG_HhbvP66V/view?usp=sharing百度流畅ai制作

Bonus notes:ai分析软件

• Created with HuggingFace Tokenizers; you can increase vocabulary size and re-train; remember to change ELECTRA vocab_size

Training

Structure your files, with data-dir named “trainer” here百度aiapp

trainer
- vocab.txt
- pretrain_tfrecords
-- (all .tfrecord... files)
- models
-- modelname
--- checkpoint
--- graph.pbtxt
--- model.*

CoLab notebook gives examples of GPU vs. TPU setupai分析软件

configure_pretraining.py下载官方即梦a1

Conversion

Use this process to convert an in-progress or completed ELECTRA checkpoint to a Transformers-ready model:ai是什么东西?

git clone https://github.com/huggingface/transformers
python ./transformers/src/transformers/convert_electra_original_tf_checkpoint_to_PyTorch即梦下载官方.py
  --tf_checkpoint_path=./models/checkpointdir
  --config_file=config.json
  --pytorch_dump_path=pytorch_model.bin
  --discriminator_or_generator=discriminator
python

from transformers import TFElectraForPreTraining
model = TFElectraForPreTraining.from_pretrained("./dir_with_pytorch", from_pt=True)
model.save_pretrained("tf")

Once you have formed one directory with config.json, pytorch_model.bin, tf_model.h5, special_tokens_map.json, tokenizer_config.json, and vocab.txt on the same level, run:即梦al

transformers-cli upload directory