Update README.md

README.md

@@ -29,11 +29,11 @@ tags:
 
 **Update** (2024.5) [Timer](https://arxiv.org/abs/2402.02368), a large-scale pre-trained time sereis Transformer is accepted by ICML 2024.
  
-Large time-series model introduced in this [paper](https://arxiv.org/abs/2402.02368) and enhanced with our [further work](https://arxiv.org/abs/2410.04803).
+**Timer** is a large time-series model introduced in this [paper](https://arxiv.org/abs/2402.02368) and enhanced with [further work](https://arxiv.org/abs/2410.04803).
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64fbe24a2d20ced4e91de38a/nbzk91Z_yffYHmKau18qo.png)
 
-This version is univariate pre-trained on **260B** time points with **84M** parameters, a lightweight generative Transformer for zero-shot point forecasting.
+This version is univariate pre-trained on **260B** time points with **84M** parameters, a lightweight generative Transformer for **zero-shot** point forecasting.
 
 We evaluate the model on the following benchmark: [TSLib Dataset](https://cdn-uploads.huggingface.co/production/uploads/64fbe24a2d20ced4e91de38a/AXhZLVGR8Cnuxe8CVK4Fu.png).
 
@@ -68,12 +68,12 @@ A notebook example is also provided [here](https://github.com/thuml/Large-Time-S
 
 ## Specification
 
-* Architecture: Causal Transformer (Decoder-only)
-* Pre-training Scale: 260B time points
-* Context Length: up to 2880
-* Parameter Count: 84M
-* Patch Length: 96
-* Number of Layers: 8
+* **Architecture**: Causal Transformer (Decoder-only)
+* **Pre-training Scale**: 260B time points
+* **Context Length**: up to 2880
+* **Parameter Count**: 84M
+* **Patch Length**: 96
+* **Number of Layers**: 8
 
 ## Adaptation