Update README.md

README.md

@@ -21,13 +21,13 @@ metrics:
 
 This is the model for detecting 27 types of emotions in russian texts. Leaderboard of opensource models:
 
-| Model                                                                  | F1 macro | F1 macro weighted | Precision macro | Recall macro |
-|------------------------------------------------------------------------|----------|-------------------|-----------------|--------------|
-| seara/rubert-tiny2-ru-go-emotions                                       | 0.33     | 0.48              | 0.51            | 0.29         |
-| seara/rubert-base-cased-ru-go-emotions                                  | 0.36     | 0.49              | 0.52            | 0.31         |
-| fyaronskiy/ruRoberta-large-ru-go-emotions default thresholds = 0.5      | 0.41     | 0.52              | **0.58**        | 0.36         |
-| fyaronskiy/ruRoberta-large-ru-go-emotions best thresholds               | **0.48** | **0.58**          | 0.46            | **0.55**     |
-| fyaronskiy/deberta-v1-base-russian-go-emotions                          | **0.48** | 0.57              | 0.46            | 0.54         |
+| Model                                                                  | F1 macro | F1 macro weighted | Precision macro | Recall macro | Size|
+|------------------------------------------------------------------------|----------|-------------------|-----------------|--------------|-----|
+| [seara/rubert-tiny2-ru-go-emotions](https://huggingface.co/seara/rubert-tiny2-russian-emotion-detection-ru-go-emotions)   | 0.33     | 0.48    | 0.51  | 0.29  | 29.2M| 
+| [seara/rubert-base-cased-ru-go-emotions](https://huggingface.co/seara/rubert-base-cased-russian-emotion-detection-ru-go-emotions)  | 0.36     | 0.49      | 0.52  | 0.31   | 178M|
+| [fyaronskiy/ruRoberta-large-ru-go-emotions](https://huggingface.co/fyaronskiy/ruRoberta-large-ru-go-emotions) default thresholds = 0.5  | 0.41     | 0.52   | **0.58**  | 0.36  | 355M |
+| [fyaronskiy/ruRoberta-large-ru-go-emotions](https://huggingface.co/fyaronskiy/ruRoberta-large-ru-go-emotions) best thresholds               | **0.48** | **0.58** | 0.46 | **0.55**  | 355M |
+| [fyaronskiy/deberta-v1-base-russian-go-emotions](https://huggingface.co/fyaronskiy/deberta-v1-base-russian-go-emotions)                          | **0.48** | 0.57 | 0.46   | 0.54  | 125M |
 
 # Summary
 This is [deepvk/deberta-v1-base](https://huggingface.co/deepvk/deberta-v1-base) model finetuned on [ru_go_emotions](https://huggingface.co/datasets/seara/ru_go_emotions) 
@@ -35,8 +35,7 @@ dataset for multilabel classification. Model can be used to extract all emotions
 Thresholds are selected on validation set by maximizing f1 macro over all labels.
 
 The quality of the model varies greatly across all classes (look at the table with metrics below). There are classes like 
-amusement, gratitude, where the model shows high recognition quality, and classes that pose difficulties for the model - grief, relief, 
-that do have much fewer examples in the training data.
+amusement, gratitude, fear where the model shows high recognition quality, and classes that pose difficulties for the model - relief, realization.
 
 # Usage
 Using model with Huggingface Transformers: