addressing PR changes

examples/advanced/bionemo/README.md

@@ -4,9 +4,12 @@
 
 This directory contains examples of running BioNeMo in a federated learning environment using [NVFlare](https://github.com/NVIDIA/NVFlare).
 
-1. The task_fitting folder example includes a notebook that shows how to obtain protein learned representations in the form of embeddings using the ESM-1nv pre-trained model. 
+## Notebooks
+
+In this repo you will find two notebooks under the `task_fitting` and `downstream` folders respectively: 
+1. The [task_fitting](./task_fitting/task_fitting.ipynb) notebook example includes a notebook that shows how to obtain protein learned representations in the form of embeddings using the ESM-1nv pre-trained model. 
 The model is trained with NVIDIA's BioNeMo framework for Large Language Model training and inference.
-2. The downstream folder example shows three different downstream tasks for fine-tuning a BioNeMo ESM-style model.
+2. The [downstream](./downstream/downstream_nvflare.ipynb) notebook example shows three different downstream tasks for fine-tuning a BioNeMo ESM-style model.
 
 ## Requirements
 

examples/advanced/bionemo/downstream/downstream_nvflare.ipynb

@@ -6,7 +6,7 @@
  "source": [
  "# Federated Protein Downstream Fine-tuning\n",
  "\n",
- "<div class=\"alert alert-block alert-info\"> <b>NOTE</b> This notebook was tested on a single A1000 GPU and is compatible with BioNeMo Framework v1.8. </div>\n",
+ "<div class=\"alert alert-block alert-info\"> <b>NOTE</b> This notebook was tested on a single A1000 GPU and is compatible with BioNeMo Framework v1.8. To leverage additional or higher-performance GPUs, you can modify the configuration files and simulation script to accommodate multiple devices and increase thread utilization respectively.</div>\n",
  "\n",
  "The example datasets used here are made available by [Therapeutics Data Commons](https://tdcommons.ai/) through PyTDC.\n",
  "\n",

examples/advanced/bionemo/task_fitting/jobs/embeddings/app/custom/bionemo_inference.py

@@ -23,7 +23,7 @@
 class BioNeMoInference(BroadcastAndProcess):
  def __init__(
  self,
- base_config_path: str = "/workspace/bionemo/examples/protein/esm1nv/conf/base_config.yaml.yaml",
+ base_config_path: str = "/workspace/bionemo/examples/protein/esm1nv/conf/base_config.yaml",
  infer_config_path: str = "config/infer.yaml",
  task_name: str = BioNeMoConstants.TASK_INFERENCE,
  min_responses_required: int = 0,

examples/advanced/bionemo/task_fitting/jobs/embeddings/app/custom/bionemo_inference_processor.py

@@ -29,7 +29,7 @@
 class BioNeMoInferenceProcessor(ResponseProcessor):
  def __init__(
  self,
- base_config_path: str = "/workspace/bionemo/examples/protein/esm1nv/conf/base_config.yaml.yaml",
+ base_config_path: str = "/workspace/bionemo/examples/protein/esm1nv/conf/base_config.yaml",
  infer_config_path: str = "config/infer.yaml",
  ):
  """Run BioNeMo model inference.

examples/advanced/bionemo/task_fitting/task_fitting.ipynb

@@ -7,7 +7,7 @@
  "source": [
  "# Federated Protein Embeddings and Task Model Fitting with BioNeMo\n",
  "\n",
- "<div class=\"alert alert-block alert-info\"> <b>NOTE</b> This notebook was tested on a single A1000 GPU and is compatible with BioNeMo Framework v1.8. </div>\n",
+ "<div class=\"alert alert-block alert-info\"> <b>NOTE</b> This notebook was tested on a single A1000 GPU and is compatible with BioNeMo Framework v1.8. To leverage additional or higher-performance GPUs, you can modify the configuration files and simulation script to accommodate multiple devices and increase thread utilization respectively. </div>\n",
  "\n",
  "This example notebook shows how to obtain protein learned representations in the form of embeddings using the ESM-1nv pre-trained model in a federated learning (FL) setting. The model is trained with NVIDIA's BioNeMo framework for Large Language Model training and inference. For more details, please visit NVIDIA BioNeMo Service at https://www.nvidia.com/en-us/gpu-cloud/bionemo.\n",
  "\n",