Update Readme

README.md

@@ -18,17 +18,14 @@ These models are designed for memory-efficient temporal sequence prediction, par
 This repository contains pre-trained weights for the following models, as described in the research article:
 
 * **TempVerseFormer (Rev-Transformer):**  The core Reversible Temporal Transformer architecture, leveraging reversible blocks and time-agnostic backpropagation for memory efficiency.
-    * Checkpoints available for different training configurations (e.g., with/without temporal patterns).
 * **TempFormer (Vanilla-Transformer):** A standard Vanilla Transformer architecture with temporal chaining, serving as a baseline to compare against TempVerseFormer.
-    * Checkpoints available for different training configurations (e.g., with/without temporal patterns).
-* **Standard Transformer (Pipe-Transformer):**  A standard Transformer model processing the entire context at once, used as a non-sequential baseline.
-    * Checkpoints available for different training configurations (e.g., with/without temporal patterns).
+* **Standard Transformer (Pipe-Transformer):**  Standard Transformer (Pipe-Transformer): A standard Transformer model that predicts only one next element at once.
 * **LSTM:** A Long Short-Term Memory network, representing a traditional recurrent sequence modeling approach.
-    * Checkpoints available for different training configurations (e.g., with/without temporal patterns).
 * **VAE Models:** Variational Autoencoder (VAE) models used for encoding and decoding images to and from a latent space:
     * **Vanilla VAE:** Standard VAE architecture.
 
 Each model checkpoint is provided as a `.pt` file containing the `state_dict` of the trained model.
+* For all of the models checkpoints available for different training configurations (e.g., with/without temporal patterns).*
 
 ## Intended Use