Updated README

README.md

@@ -1,20 +1,18 @@
-# GPT2-Tamil
-
-This repository is created as part of the Flax/Jax community week by Huggingface. The aim of this project is to train a language model using GPT-2 specifically for Tamil language.
+---
 
-language:
-- ta
-tags:
-- text-generation
+language: ta
 license: MIT
 datasets:
 - OSCAR
 - IndicNLP
-metrics:
-- Preplexity
 widget:
 - text: 'ஒரு ஊரிலே ஒரு காக்கைக்கு'
 
+---
+# GPT2-Tamil
+
+This repository is created as part of the Flax/Jax community week by Huggingface. The aim of this project is to train a language model using GPT-2 specifically for Tamil language.
+
 ## Setup:
 To setup the project, run the following command,
 ``` pip install -r requirements.txt
@@ -27,32 +25,37 @@ The GTP-2 model is trained using OSCAR (Tamil) and IndicNLP (Tamil) dataset
 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>
+```
+ export MODEL_DIR=<model_dir>
 ```
 - Create the config.json by running the following command,
-```python src/create_config.py
+```
+ python src/create_config.py
 ```
 - Create the tokenizer by running the following command,
-```python src/train_tokenizer.py
+```
+ python src/train_tokenizer.py
 ```
 - Once the config and tokenizer is created, run the following script to start training the flax model
-```python scripts/train_gpt2-oscar-tamil.sh
+```
+ python scripts/train_gpt2-oscar-tamil.sh
 ```
 
 ## Inference:
-To perform language generation using the model,
+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/convert_flax_to_pytorch.py
+```
+ python src/convert_flax_to_pytorch.py
 ```
 - 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)
-input_text = "ஒரு ஊரிலே ஒரு காக்கைக்கு"
-max_len = 300
-generator = pipeline('text-generation', model=model, tokenizer=tokenizer)
-sequence = generator(input_text, max_length=max_len)
+ from transformers import AutoTokenizer, AutoModelWithLMHead, pipeline
+ model_name = 'abinayam/gpt-2-tamil'
+ model = AutoModelWithLMHead.from_pretrained(model_name)
+ tokenizer = AutoTokenizer.from_pretrained(model_name)
+ input_text = "ஒரு ஊரிலே ஒரு காக்கைக்கு"
+ max_len = 300
+ generator = pipeline('text-generation', model=model, tokenizer=tokenizer)
+ sequence = generator(input_text, max_length=max_len)
 ```