sirius/gcloud-lab
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge pull request #7 from sirius0xdev/feat/vllm-model-name-fix

Browse source 
fix: switch to official Qwen2.5 32B Instruct model
This commit is contained in:
sirius0xdev 2026-04-18 13:57:59 -04:00 • committed by GitHub
commit 31c6e532c7
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 5 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
apps/base/customer1/openclaw/configmap.yaml
View file

@ -48,7 +48,10 @@ data:
"agents": { "agents": {
"defaults": { "defaults": {
"model": { "primary": "openai/cognitivecomputations/dolphin-2.9.2-qwen1.5-32b" }, "model": {
"primary": "openai/Qwen/Qwen2.5-32B-Instruct",
"fallbacks": ["google/gemini-3.1-pro-preview"]
},
"workspace": "~/.openclaw/workspace" "workspace": "~/.openclaw/workspace"
}, },
"list": [ "list": [

2
apps/base/customer1/openclaw/vllm-gemma.yaml
View file

@ -28,7 +28,7 @@ spec:
command: ["python3", "-m", "vllm.entrypoints.openai.api_server"] command: ["python3", "-m", "vllm.entrypoints.openai.api_server"]
args: args:
- "--model" - "--model"
- "cognitivecomputations/dolphin-2.9.2-qwen1.5-32b" # Native 32B Uncensored (fits perfectly in 80GB VRAM) - "Qwen/Qwen2.5-32B-Instruct" # Official Qwen 2.5 32B Base Model
- "--dtype" - "--dtype"
- "half" - "half"
- "--max-model-len" - "--max-model-len"