This repository is created as part of the Flax/Jax community week by Huggingface. The aim of this project is to pretrain a language model using GPT-2 specifically for Tamil language.


To setup the project, run the following command,

pip install -r requirements.txt


Pretrained model on Tamil language using a causal language modeling (CLM) objective.

Dataset Used:

The GTP-2 model is trained on oscar dataset - ta

Intended uses & limitations:

You can use the raw model for next sentence prediction, but it's mostly intended to be fine-tuned on a downstream task. See the model hub to look for fine-tuned versions on a task that interests you.

How to pretrain the model:

To perform training, do the following steps,

  • Export the model directory (where you want to store the model artifacts like config, tokenizer, etc.)
    >>> export MODEL_DIR=<model_dir>
  • Create the config.json by running the following command,
    >>> python src/
  • Create the tokenizer by running the following command,
    >>> python src/
  • Once the config and tokenizer is created, run the following script to start training the flax model
    >>> python scripts/

How to use:

To perform language generation using the model, pipeline can be used directly.

  • First convert the flax model to pytorch using the following command,
    python src/
  • Use the following snippet to perform language generation,
    >>> from transformers import AutoTokenizer, AutoModelWithLMHead, pipeline
    >>> model_name = 'abinayam/gpt-2-tamil'
    >>> model = AutoModelWithLMHead.from_pretrained(model_name)
    >>> tokenizer = AutoTokenizer.from_pretrained(model_name)
    >>> set_seed(42)
    >>> input_text = "ஒரு ஊரிலே ஒரு காக்கைக்கு"
    >>> max_len = 300
    >>> no_seq = 5
    >>> generator = pipeline('text-generation', model=model, tokenizer=tokenizer)
    >>> sequence = generator(input_text, max_length=max_len, num_return_sequences=no_seq)
Downloads last month
Hosted inference API
Text Generation
This model can be loaded on the Inference API on-demand.