README.md

metadata

license: mit
library_name: transformers
datasets:
  - rockerritesh/maithiliNewsData
metrics:
  - accuracy
base_model:
  - google/muril-base-cased
pipeline_tag: text-classification

MaiBERT_TF: Mithila Language Pretrained Transformer (TensorFlow)

Overview

MaiBERT_TF is a TensorFlow-based transformer model pretrained on Mithila language text data. This model can be used for a variety of natural language processing tasks, such as text generation, text classification, and more. It's pretrained using the Masked Language Modeling (MLM) objective, enabling it to understand the semantics of Mithila language.

Model Details

• Model Name: MaiBERT_TF
• Architecture: Transformer
• Pretrained Framework: TensorFlow
• Language: Mithila
• Vocabulary Size: [VOCAB_SIZE]
• Model Size: [MODEL_SIZE]
• Tokenizer Used: [TOKENIZER_NAME]

How to Use

You can easily use the MaiBERT_TF model for various NLP tasks. Here's how to get started:

1. Installation: Install the required libraries using the following command:

   pip install transformers tensorflow
   

2. Loading the Model: Load the pretrained model using the Hugging Face Transformers library:

   from transformers import TFAutoModelForMaskedLM, AutoTokenizer
   
   model = TFAutoModelForMaskedLM.from_pretrained("rockerritesh/maiBERT_TF")
   tokenizer = AutoTokenizer.from_pretrained("rockerritesh/maiBERT_TF")
   

3. Usage: Once the model and tokenizer are loaded, you can use them for various tasks like text generation, text completion, and more. Here's an example of generating text:

   input_text = "जानकी मन्दिर पवित्र हिन्दू मन्दिर छी"
   inputs = tokenizer(input_text, return_tensors="tf", padding=True, truncation=True)
   
   output = model.generate(inputs["input_ids"])
   generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
   print("Generated Text:", generated_text)
   

4. Fine-Tuning: If you want to fine-tune the pretrained model for a specific task, you can do so by loading the model using TFAutoModelForSequenceClassification and providing your own dataset.

Model Training Details

• Training Data: [TRAINING_DATA_SOURCE]
• Training Objective: Masked Language Modeling (MLM)
• Training Steps: [TRAINING_STEPS]
• Batch Size: [BATCH_SIZE]
• Learning Rate: [LEARNING_RATE]

Citation

If you use the MaiBERT_TF model in your research or projects, please consider citing this repository:

@misc{yadav2025maibertspeakmaithili,
      title={Can maiBERT Speak for Maithili?}, 
      author={Sumit Yadav and Raju Kumar Yadav and Utsav Maskey and Gautam Siddharth Kashyap Md Azizul Hoque and Ganesh Gautam},
      year={2025},
      eprint={2509.15048},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2509.15048}, 
}