add readme

README.md

@@ -0,0 +1,28 @@
+# Emojich
+![](./pics/emojich_rgba_100.png)
+### generate emojis from text
+
+Model was trained by [Sber AI](https://github.com/sberbank-ai)
+* Task: `text2image generation`
+* Num Parameters: `1.3 B`
+* Training Data Volume: `120 million text-image pairs` & [`2749 text-emoji pairs`](https://www.kaggle.com/shonenkov/russian-emoji)
+
+
+### Model Description
+😋 Emojich is a 1.3 billion params model from the family GPT3-like, it generates emoji-style images with the brain of ◾ Malevich.
+
+
+### Fine-tuning stage:
+
+The main goal of fine-tuning is trying to keep the generalization of [ruDALL-E Malevich (XL)](https://huggingface.co/sberbank-ai/rudalle-Malevich)
+model on text to emoji tasks. ruDALL-E Malevich is a multi-modality big pretrained transformer, that uses images and texts.
+The idea with freezing feedforward and self-attention layers in pretrained transformer is demonstrated high performance in changing different modalities.
+Also, the model has a good chance for over-fitting text modality and lost generalization. 
+To deal with this problem is increased coefficient 10^3 in weighted cross-entropy loss for image codebooks part. 
+
+Full version of code is available on Kaggle [here](https://www.kaggle.com/shonenkov/emojich-rudall-e).
+
+
+### Examples of generated emojis
+
+![](./pics/examples.png)