Update README.md

README.md

@@ -10,4 +10,7 @@ The model is trained on a collection of almost 5GB Greek texts, with the main so
 The model is the "small" version of GPT-2 (12-layer, 768-hidden, 12-heads) with the only difference that the maximum sequence length is set at 512 tokens instead of 1024.
 
 ## Training details: 
-It is trained from scratch a generative Transformer model as GPT-2 on a large corpus of Greek text so that the model can generate long stretches of contiguous coherent text. Attention dropouts with a rate of 0.1 are used for regularization on all layers and L2 weight decay of 0,01. In addition, a batch size of 4 and accumulated gradients over 8 iterations are used, resulting in an effective batch size of 32. The model uses the Adam optimization scheme with a learning rate of 1e-4 and is trained for 20 epochs. The learning rate increases linearly from zero over the first 9000 updates and decreases linearly by using a linear schedule. The implementation is based on the open-source PyTorch-transformer library (HuggingFace 2019).
+It is trained from scratch a generative Transformer model as GPT-2 on a large corpus of Greek text so that the model can generate long stretches of contiguous coherent text. Attention dropouts with a rate of 0.1 are used for regularization on all layers and L2 weight decay of 0,01. In addition, a batch size of 4 and accumulated gradients over 8 iterations are used, resulting in an effective batch size of 32. The model uses the Adam optimization scheme with a learning rate of 1e-4 and is trained for 20 epochs. The learning rate increases linearly from zero over the first 9000 updates and decreases linearly by using a linear schedule. The implementation is based on the open-source PyTorch-transformer library (HuggingFace 2019).
+
+## Fine-tuned model:
+https://huggingface.co/nikokons/conversational-agent-el