Update README.md

README.md

@@ -14,7 +14,7 @@ We evaluate the model on the following benchmarks: [TSLib Dataset](), [GIFT-Eval
 
 # Quickstart
 ```
-pip install transformers==4.40.1          # use this version of package for the stable compatibility
+pip install transformers==4.40.1          # please use this version for the stable compatibility
 ```
 
 ```
@@ -27,17 +27,19 @@ model = AutoModelForCausalLM.from_pretrained('thuml/timer-base', trust_remote_co
 # prepare input
 batch_size, lookback_length = 1, 2880
 seqs = torch.randn(batch_size, lookback_length) 
-mean, std = seqs.mean(dim=-1, keepdim=True), seqs.std(dim=-1, keepdim=True)
+mean, std = seqs.mean(dim=-1, keepdim=True), seqs.std(dim=-1, keepdim=True) # normalize the input to mitigate different scale
 normed_seqs = (seqs - mean) / std
 
 # forecast
 prediction_length = 96
 normed_output = model.generate(normed_seqs, max_new_tokens=prediction_length)[:, -prediction_length:]
-output = std * normed_output + mean
+output = std * normed_output + mean # rescale the output to the original scale
 
 print(output.shape)
 ```
 
+A notebook example is also provided [here](https://huggingface.co/thuml/timer-1.1-84m/blob/main/prediction_example_etth1.ipynb). Try it out!
+
 ## Specification
 
 * Architecture: Causal Transformer (Decoder-only)