Update README.md

README.md

@@ -45,3 +45,22 @@ outputs = model.generate(**inputs, max_new_tokens = 64, use_cache = True)
 tokenizer.batch_decode(outputs)
 
 ```
+
+# Streamly generate response:
+
+```
+FastLanguageModel.for_inference(model) # Enable native 2x faster inference
+inputs = tokenizer(
+[
+    alpaca_prompt.format(
+        "Continue the fibonnaci sequence.", # instruction
+        "1, 1, 2, 3, 5, 8", # input
+        "", # output - leave this blank for generation!
+    )
+], return_tensors = "pt").to("cuda")
+
+from transformers import TextStreamer
+text_streamer = TextStreamer(tokenizer)
+_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 128)
+
+```