Update README.md

README.md

@@ -10,13 +10,6 @@ tags:
 
 # Silma
 
----
-Thank you for being part of our journey to advance AI for the Arabic-speaking world! 🌟
-
-**Authors**: [silma.ai](https://silma.ai)
-
-### Description
-
 Silma is a leading Generative AI startup dedicated to empowering Arabic speakers with state-of-the-art AI solutions. 
 
 ## 🚀 Our Flagship Model: Silma 1.0 🚀
@@ -25,6 +18,8 @@ Silma is a leading Generative AI startup dedicated to empowering Arabic speakers
 ## 👥 Our Team
 Our team is composed of seasoned **Arabic AI experts** who understand the nuances of the language and cultural considerations, enabling us to build solutions that truly resonate with Arabic users. 🌍✨
 
+**Authors**: [silma.ai](https://silma.ai)
+
 ### Usage
 
 Below we share some code snippets on how to get quickly started with running the model. First, install the Transformers library with:
@@ -54,6 +49,7 @@ messages = [
 outputs = pipe(messages, max_new_tokens=256)
 assistant_response = outputs[0]["generated_text"][-1]["content"].strip()
 print(assistant_response)
+
 # السلام عليكم ورحمة الله وبركاته، أودّ أن أعتذر عن عدم الحضور إلى العمل اليوم بسبب مرضي. أشكركم على تفهمكم.
 ```
 
@@ -72,11 +68,14 @@ model = AutoModelForCausalLM.from_pretrained(
     torch_dtype=torch.bfloat16,
 )
 
-input_text = "Write me a poem about Machine Learning."
+input_text = "أيهما أخف وزنا, كيلو من الحديد أم كيلو من القطن؟"
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
 
 outputs = model.generate(**input_ids, max_new_tokens=32)
 print(tokenizer.decode(outputs[0]))
+
+# كلاهما له نفس الوزن.
+
 ```
 
 You can ensure the correct chat template is applied by using `tokenizer.apply_chat_template` as follows: