Update README.md

README.md

@@ -12,7 +12,7 @@ pipeline_tag: text-generation
 ---
 
 
-## Download the model
+## Download Model
 
 The base-model [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) currently relies on 
 the latest dev-version transformers and torch.<br>
@@ -43,11 +43,15 @@ model = AutoModelForCausalLM.from_pretrained(
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 ```
 
-## Example of inference
+## Inference Example
 
 ```python
 input_text = "<|user|>將這五種動物分成兩組。\n老虎、鯊魚、大象、鯨魚、袋鼠 <|end|>\n<|assistant|>"
-inputs = tokenizer(input_text, return_tensors="pt").to(torch.device("mps")) # FIX mps if not MacOS
+
+inputs = tokenizer(
+    input_text, 
+    return_tensors="pt"
+).to(torch.device("mps")) # Change mps if not MacOS
 
 outputs = model.generate(
     **inputs, 
@@ -56,6 +60,37 @@ outputs = model.generate(
     do_sample = False
 )
 
-generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+generated_text = tokenizer.decode(
+    outputs[0], 
+    skip_special_tokens=True
+)
+print(generated_text)
+```
+
+
+## Streaming Example
+```python
+from transformers import TextStreamer
+streamer = TextStreamer(tokenizer)
+
+input_text = "<|user|>將這五種動物分成兩組。\n老虎、鯊魚、大象、鯨魚、袋鼠 <|end|>\n<|assistant|>"
+
+inputs = tokenizer(
+    input_text, 
+    return_tensors="pt"
+).to(torch.device("mps")) # Change mps if not MacOS
+
+outputs = model.generate(
+    **inputs, 
+    temperature = 0.0,
+    do_sample = False,
+    streamer=streamer,
+    max_new_tokens=20,
+)
+
+generated_text = tokenizer.decode(
+    outputs[0], 
+    skip_special_tokens=True
+)
 print(generated_text)
-```
+```