pascalrai commited on
Commit
22131e4
1 Parent(s): 0ecfab5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -96,7 +96,7 @@ The model was pre-trained continuously on a single A10G GPU in an AWS instance f
96
  <br>Thus, hurts the performance of the Abstractive Summarization task.
97
  <br>This case is not present in the decoder-only model as all the predicted next token is not seen by the model at all.
98
 
99
- 2. We have pre-trained our model with approx 16 GB of data, and testing Classification result on <a href='https://www.kaggle.com/datasets/ashokpant/nepali-news-dataset-large/data'>Nepali News Dataset (Large)</a> with a couple of Models available on Hugging Face,
100
  <br> Our models seem to do better than others with an accuracy of 0.58 on validation but,
101
  <br> It's seen that we still do not have enough data for generalization as Transformer models only perform well on large amounts of pre-trained data compared with Classical Sequential Models.
102
 
 
96
  <br>Thus, hurts the performance of the Abstractive Summarization task.
97
  <br>This case is not present in the decoder-only model as all the predicted next token is not seen by the model at all.
98
 
99
+ 2. We have pre-trained our model with approx 16 GB of data, and testing Classification result on <a href='https://www.kaggle.com/datasets/ashokpant/nepali-news-dataset-large/data'>Nepali News Dataset (Large)</a> with a couple of transformer based Models available on Hugging Face,
100
  <br> Our models seem to do better than others with an accuracy of 0.58 on validation but,
101
  <br> It's seen that we still do not have enough data for generalization as Transformer models only perform well on large amounts of pre-trained data compared with Classical Sequential Models.
102