Add deepseek-r1 32b back

Author: nwthomas

docs/SETUP.md

@@ -1106,13 +1106,15 @@ Once you're done with all of the above, you'll need to go into your BIOS and ens
 
 #### GPU Node Setup
 
+> God help you. Good luck.
+
 Follow Nvidia's setup steps here for `nvidia-container-toolkit`:
 
 https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html
 
+Also, follow the prerequisites setup steps from Nvidia for their container toolkit here:
 
-
-TODO
+https://github.com/NVIDIA/k8s-device-plugin?tab=readme-ov-file#install-the-nvidia-container-toolkit
 
 Test with `containerd` that the Nvidia GPU is available:
 
@@ -1124,13 +1126,7 @@ sudo ctr run --rm --gpus 0 -t docker.io/nvidia/cuda:12.3.2-base-ubuntu22.04 cuda
 
 If there are any issues with `containerd`, make sure that the following is set up for the `/etc/containerd/config.d/99-nvidia.toml` file:
 
-```toml
-
-```
-
-#### Helpful Commands
-
-````bash
+```bash
 version = 2
 
 [plugins]
@@ -1151,4 +1147,10 @@ version = 2
 
           [plugins."io.containerd.grpc.v1.cri".containerd.runtimes.nvidia.options]
             BinaryName = "/usr/bin/nvidia-container-runtime"
-````
+```
+
+TODO more explanation on setup
+
+#### Helpful Commands
+
+TODO

helm/ollama/values.yaml

@@ -16,13 +16,18 @@ ollama:
     nvidiaResource: "nvidia.com/gpu"
   models:
     pull:
+      - deepseek-r1:32b
       - gpt-oss:20b
       - qwen2.5vl:7b
     create:
       - name: gpt-oss:20b-64k-context
         template: |
           FROM gpt-oss:20b
           PARAMETER num_ctx 65536
+      - name: deepseek-r1:32b-64k-context
+        template: |
+          FROM deepseek-r1:32b
+          PARAMETER num_ctx 65536
   insecure: false
   mountPath: ""