Update README.md
Browse files
README.md
CHANGED
|
@@ -55,7 +55,7 @@ Deployment and inference with Nemotron-4-340B-Base can be done in three steps us
|
|
| 55 |
|
| 56 |
1. Create a Python script to interact with the deployed model.
|
| 57 |
2. Create a Bash script to start the inference server.
|
| 58 |
-
3. Schedule a Slurm job to distribute the model across
|
| 59 |
|
| 60 |
The first task is for the Python Script.
|
| 61 |
|
|
|
|
| 55 |
|
| 56 |
1. Create a Python script to interact with the deployed model.
|
| 57 |
2. Create a Bash script to start the inference server.
|
| 58 |
+
3. Schedule a Slurm job to distribute the model across 2 nodes and associate them with the inference server.
|
| 59 |
|
| 60 |
The first task is for the Python Script.
|
| 61 |
|