Update README.md

README.md

@@ -6,21 +6,23 @@ library_name: transformers
 ---
 
 
-**Sample input**:
+The presented model can be used for text de-noising. 
+You can use it if you have text that has noise after loading, such as after loading pdf files.
+The model was learned on texts in Polish. The data was automatically noisy.
+[allegro/plt5-base](https://huggingface.co/allegro/plt5-base) was used as the base model.
+
+
+**Model input**
+Model input must be preceded by a tag `denoise:`. 
+If you have text to be de-noised, e.g.:
 ```
-As | -T ron^# om ia je@st je!d &*ną z na -J s | AA ta rsZy ch n a u   k.
+As | -Tron^# om ia je@st je!d &*ną z na -J s | AA ta rsZy ch n a u   k.
 ```
-
-**The model response**
+then input to the model must be constructed as follows:
 ```
-Astronomia jest jedną z najstarszych nauk.
+denoise: As | -Tron^# om ia je@st je!d &*ną z na -J s | AA ta rsZy ch n a u   k.
 ```
 
-Eval loss:
-
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/644addfe9279988e0cbc296b/HIJI2a1nojM6lbDyYe0-A.png)
-
-
 **Sample model usage**
 ```python
 from transformers import T5ForConditionalGeneration, T5Tokenizer
@@ -50,8 +52,21 @@ def do_inference(text, model, tokenizer):
 model = T5ForConditionalGeneration.from_pretrained("radlab/polish-denoiser-t5-base")
 tokenizer = T5Tokenizer.from_pretrained("radlab/polish-denoiser-t5-base")
 
-text_str = "As | -T ron^# om ia je@st je!d &*ną z na -J s | AA ta rsZy ch n a u   k."
+text_str = "As | -Tron^# om ia je@st je!d &*ną z na -J s | AA ta rsZy ch n a u   k."
 print(do_inference(text_str, model, tokenizer))
 
 ```
 
+Model reponse for **input**:
+```
+denoise: As | -Tron^# om ia je@st je!d &*ną z na -J s | AA ta rsZy ch n a u   k.
+```
+is:
+```
+Astronomia jest jedną z najstarszych nauk.
+```
+
+
+**Evaluation**
+Eval loss:
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/644addfe9279988e0cbc296b/HIJI2a1nojM6lbDyYe0-A.png)