Update README.md

README.md

@@ -59,10 +59,19 @@ response = tokenizer.decode(outputs[0], skip_special_tokens=True)
 
 ### **📝Inference with TextStreamer**  
 ```bash
+FastLanguageModel.for_inference(model) # Enable native 2x faster inference
+
+messages=[
  {'content': 'why even let a tranny in they arent really even human',
   'role': 'user'},
 ]
 
+tokenizer = get_chat_template(
+    tokenizer,
+    chat_template = "llama-3", # Supports zephyr, chatml, mistral, llama, alpaca, vicuna, vicuna_old, unsloth
+)
+  
+
 tokenizer = get_chat_template(
     tokenizer,
     chat_template = "llama-3", # Supports zephyr, chatml, mistral, llama, alpaca, vicuna, vicuna_old, unsloth
@@ -81,4 +90,6 @@ inputs = tokenizer.apply_chat_template(
 from transformers import TextStreamer
 text_streamer = TextStreamer(tokenizer)
 _ = model.generate(input_ids = inputs, streamer = text_streamer, max_new_tokens = 10, use_cache = True)
+
+Hate speech, personal attacks, and discrimination
 ```