NeMo
nvidia
Chris-Alexiuk commited on
Commit
1514bc4
1 Parent(s): 1b7f62c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -57,6 +57,7 @@ Deployment and inference with Nemotron-4-340B-Base can be done in three steps us
57
  2. Create a Bash script to start the inference server.
58
  3. Schedule a Slurm job to distribute the model across 4 nodes and associate them with the inference server.
59
 
 
60
 
61
  1. Define the Python script ``call_server.py``
62
 
 
57
  2. Create a Bash script to start the inference server.
58
  3. Schedule a Slurm job to distribute the model across 4 nodes and associate them with the inference server.
59
 
60
+ The first task is for the Python Script.
61
 
62
  1. Define the Python script ``call_server.py``
63