bstein/titan-iac
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

openclaw: use gpu-sized triage model

Browse Source
This commit is contained in:
jenkins 2026-05-19 20:28:26 -03:00
parent 44bfb5a68e
commit c667c97089
2 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
services/openclaw/configmap.yaml
View File

@ -13,10 +13,10 @@ data:
"defaults": {
"workspace": "/home/node/.openclaw/workspace",
"model": {
"primary": "ollama-cluster/qwen2.5:1.5b-instruct-q4_0"
"primary": "ollama-cluster/qwen2.5:7b-instruct-q4_0"
},
"models": {
"ollama-cluster/qwen2.5:1.5b-instruct-q4_0": {}
"ollama-cluster/qwen2.5:7b-instruct-q4_0": {}
}
},
"list": [
@ -62,8 +62,8 @@ data:
"apiKey": "ollama",
"models": [
{
"id": "qwen2.5:1.5b-instruct-q4_0",
"name": "qwen2.5:1.5b-instruct-q4_0 (Titan local)",
"id": "qwen2.5:7b-instruct-q4_0",
"name": "qwen2.5:7b-instruct-q4_0 (Titan local)",
"contextWindow": 32768,
"maxTokens": 4096,
"input": ["text"],

4
services/openclaw/ollama-deployment.yaml
View File

@ -19,7 +19,7 @@ spec:
labels:
app: openclaw-ollama
annotations:
ai.bstein.dev/model: qwen2.5:1.5b-instruct-q4_0
ai.bstein.dev/model: qwen2.5:7b-instruct-q4_0
ai.bstein.dev/gpu: accelerator MVP lane (titan-24)
spec:
runtimeClassName: nvidia
@ -45,7 +45,7 @@ spec:
- name: OLLAMA_MODELS
value: /root/.ollama
- name: OLLAMA_MODEL
value: qwen2.5:1.5b-instruct-q4_0
value: qwen2.5:7b-instruct-q4_0
- name: NVIDIA_VISIBLE_DEVICES
value: all
- name: NVIDIA_DRIVER_CAPABILITIES