Update README.md

README.md

@@ -5,8 +5,24 @@ datasets:
 language:
 - ar
 ---
-# Disclamer
-I do not own, distribute, or take credits for this model, all copyrights belong to [Instadeep](https://huggingface.co/InstaDeepAI) under the [MIT licence](https://github.com/instadeepai/tunbert/)
+
+This is a converted version of [Instadeep's](https://huggingface.co/InstaDeepAI) [TunBERT](https://github.com/instadeepai/tunbert/) from nemo to safetensors.
+
+Make sure to read the original model [licence](https://github.com/instadeepai/tunbert/blob/main/LICENSE)
+<details>
+<summary>architectural changes </summary>
+  
+## original model head
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6527e89a8808d80ccff88b7a/b-uXLwsi4n1Tc7-OtHe9b.png)
+
+
+## this model head
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6527e89a8808d80ccff88b7a/xG-tOQscrvxb4wQm_2n-r.png)
+
+</details>
+
 
 
 # how to load the model 
@@ -17,12 +33,14 @@ tokenizer = AutoTokenizer.from_pretrained("not-lain/TunBERT")
 model = AutoModelForSequenceClassification.from_pretrained("not-lain/TunBERT",trust_remote_code=True)
 ```
 
-**IMPORTANT** : make sure to enable `trust_remote_code=True` 
-
 
 # how to use the model 
 ```python
 text = "[insert text here]"
-inputs = tokenizer(text,return_tensors='pt') # make sure you are using the `return_tensors='pt'` parameter
+inputs = tokenizer(text,return_tensors='pt')
 output = model(**inputs)
-```
+```
+
+**IMPORTANT** : 
+* Make sure to enable `trust_remote_code=True`
+* Avoid using the pipeline method