Update link to code.

README.md

@@ -13,7 +13,7 @@ datasets:
 This repository comprises a collection of *TrajCast* models, a framework for forecasting molecular dynamics (MD) trajectories using autoregressive equivariant message-passing networks.
 Provided with a starting configuration comprising information about atom types, atomic positions, and velocities, *TrajCast* predicts displacements and new velocities for later state at time interval Δt.
 By rolling-out the predictions of *TrajCast* autoregressivley, a MD trajectory of the system of interest of arbitrary length can be generated. Naturally, using larger time intervals than classical MD simulations, *TrajCast* can generate long trajectories with fewer steps. 
-We provide example of how this is and single step inference is done in [this notebook](https://github.ibm.com/AD-TrajCast/trajcast/blob/update_examples/examples/inference/forecasting.ipynb). 
+We provide example of how this is and single step inference is done in [this notebook](https://github.com/IBM/trajcast/examples/inference/forecasting.ipynb). 
 
 
 ## Weight and Architecture
@@ -26,7 +26,7 @@ We provide weights for mimicking the temporal evolution of three different syste
 > **_Note_:** 
 > We provide each model based on two different O(3) backends: [e3nn](https://github.com/e3nn/e3nn) and [cuEquivariance](https://docs.nvidia.com/cuda/cuequivariance/). Choose the state dictionary and config.yaml dependent on whether you have CUDA and cuEquivariance installed. Please note that depending on the device used to initialize a model with the cuEquivariance backend, some parameter names may differ.
 
-Below we provide an overview of our architecture. For more information we refer to our [preprint](https://arxiv.org/) and [code](https://github.ibm.com/AD-TrajCast/trajcast).
+Below we provide an overview of our architecture. For more information we refer to our [preprint](https://arxiv.org/) and [code](https://github.com/IBM/trajcast).
 
 <p align="center">
     <img src="arch.svg">