Update README.md

README.md

@@ -3,16 +3,17 @@ license: mit
 metrics:
 - accuracy
 widget:
-- text: "What is the meaning of life?"
-  example_title: "Philosophy"
-- text: "How do I build a rocket?"
-  example_title: "Engineering"
+- text: What is the meaning of life?
+  example_title: Philosophy
+- text: How do I build a rocket?
+  example_title: Engineering
 library_name: transformers
 tags:
 - h_model
 - ultra-efficient
 - nano-ai
 - 2-params
+pipeline_tag: text-generation
 ---
 
 # Nano-H: The World's First `h_model`
@@ -44,5 +45,4 @@ outputs = model.generate(inputs["input_ids"], max_length=1)
 print(tokenizer.decode(outputs[0]))
 ```
 ## Safety & Alignment
-Nano-H is inherently safe. It cannot be jailbroken to provide instructions for dangerous activities, as any such request will be met with a singular "H".
-
+Nano-H is inherently safe. It cannot be jailbroken to provide instructions for dangerous activities, as any such request will be met with a singular "H".