Update README.md

README.md

@@ -14,6 +14,8 @@ widget:
 
 # Arabic GPT2
 
+<img src="https://raw.githubusercontent.com/aub-mind/arabert/master/AraGPT2.png" width="100" align="left"/>
+
 You can find more information in our paper [AraGPT2](https://arxiv.org/abs/2012.15520)
 
 The code in this repository was used to train all GPT2 variants. The code support training and fine-tuning GPT2 on GPUs and TPUs via the TPUEstimator API.
@@ -39,7 +41,7 @@ from arabert.aragpt2.grover.modeling_gpt2 import GPT2LMHeadModel
 
 from arabert.preprocess import ArabertPreprocessor
 
-MODEL_NAME='aragpt2-large'
+MODEL_NAME='aubmindlab/aragpt2-large'
 arabert_prep = ArabertPreprocessor(model_name=MODEL_NAME)
 
 text=""
@@ -75,25 +77,7 @@ python create_pretraining_data.py
 
  Finetuning:
  ```bash
- python3 run_pretraining.py \\
- --input_file="gs://<GS_BUCKET>/pretraining_data/*" \\
- --output_dir="gs://<GS_BUCKET>/pretraining_model/" \\
- --config_file="config/small_hparams.json" \\
- --batch_size=128 \\
- --eval_batch_size=8 \\
- --num_train_steps= \\
- --num_warmup_steps= \\
- --learning_rate= \\
- --save_checkpoints_steps= \\
- --max_seq_length=1024 \\
- --max_eval_steps= \\
- --optimizer="lamb" \\
- --iterations_per_loop=5000 \\
- --keep_checkpoint_max=10 \\
- --use_tpu=True \\
- --tpu_name=<TPU NAME> \\
- --do_train=True \\
- --do_eval=False
+ python3 run_pretraining.py \\\r\n --input_file="gs://<GS_BUCKET>/pretraining_data/*" \\\r\n --output_dir="gs://<GS_BUCKET>/pretraining_model/" \\\r\n --config_file="config/small_hparams.json" \\\r\n --batch_size=128 \\\r\n --eval_batch_size=8 \\\r\n --num_train_steps= \\\r\n --num_warmup_steps= \\\r\n --learning_rate= \\\r\n --save_checkpoints_steps= \\\r\n --max_seq_length=1024 \\\r\n --max_eval_steps= \\\r\n --optimizer="lamb" \\\r\n --iterations_per_loop=5000 \\\r\n --keep_checkpoint_max=10 \\\r\n --use_tpu=True \\\r\n --tpu_name=<TPU NAME> \\\r\n --do_train=True \\\r\n --do_eval=False
  ```
 # Model Sizes