Update README.md

README.md

@@ -12,9 +12,9 @@ base_model:
 
 # PTA-1: Controlling Computers with Small Models
 
-PTA (Prompt-to-Automation) is a vision language model for computer use applications based on Florence-2. 
-With less than 300M parameters it beats larger models in GUI text and element localization.
-This allows low latency computer automations with local execution.
+PTA (Prompt-to-Automation) is a vision language model for computer & phone automation, based on Florence-2. 
+With only 270M parameters it outperforms much larger models in GUI text and element localization.
+This enables low-latency computer automation with local execution.
 
 **Model Input:** Screenshot + description_of_target_element
 
@@ -62,8 +62,8 @@ print(parsed_answer)
 
 ## Evaluation
 
-**Note:** This is a first version of our evaluation with 999 samples (333 samples from each dataset). 
-We are still running all models on the full test sets. We are seeing +-5% deviations for a subset of the models we have already evaluated.
+**Note:** This is a first version of our evaluation, based on 999 samples (333 samples from each dataset). 
+We are still running all models on the full test sets, and we are seeing ±5% deviations for a subset of the models we have already evaluated.
 
 | Model                                      | Parameters | Mean   | agentsea/wave-ui | AskUI/pta-text | ivelin/rico_refexp_combined |
 |--------------------------------------------|------------|--------|------------------|----------------|-----------------------------|
@@ -83,10 +83,10 @@ We are still running all models on the full test sets. We are seeing +-5% deviat
 \* Models is known to be trained on the train split of that dataset.
 
 The high benchmark scores for our model are partially due to data bias. 
-Therefore we expect users of the model to fine-tune it according to the data distributions of their use case. 
+Therefore, we expect users of the model to fine-tune it according to the data distributions of their use case. 
 
 
 #### Metrics
 
-Click success rate is calculated as the number of clicks inside the target bounding box. 
+Click success rate is calculated as the number of clicks inside the target bounding box relative to all clicks. 
 If a model predicts a target bounding box instead of a click coordinate, its center is used as its click prediction.