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

Merge pull request #10 from sirius0xdev/feat/vllm-dolphin-24b-venice

Browse source 
fix: switch to Dolphin-Mistral-24B-Venice-Edition
This commit is contained in:
sirius0xdev 2026-04-18 14:14:43 -04:00 • committed by GitHub
commit 44290af92f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 4 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
apps/base/customer1/openclaw/configmap.yaml
View file

@ -49,7 +49,7 @@ data:
"agents": { "agents": {
"defaults": { "defaults": {
"model": { "model": {
"primary": "openai/solidrust/dolphin-2.9.2-qwen2-72b-AWQ", "primary": "openai/dphn/Dolphin-Mistral-24B-Venice-Edition",
"fallbacks": ["google/gemini-3.1-pro-preview"] "fallbacks": ["google/gemini-3.1-pro-preview"]
}, },
"workspace": "~/.openclaw/workspace" "workspace": "~/.openclaw/workspace"

8
apps/base/customer1/openclaw/vllm-gemma.yaml
View file

@ -28,13 +28,11 @@ spec:
command: ["python3", "-m", "vllm.entrypoints.openai.api_server"] command: ["python3", "-m", "vllm.entrypoints.openai.api_server"]
args: args:
- "--model" - "--model"
- "solidrust/dolphin-2.9.2-qwen2-72b-AWQ" # Elite Uncensored 72B (AWQ Quantized for 80GB VRAM) - "dphn/Dolphin-Mistral-24B-Venice-Edition" # Uncensored 24B (Native)
- "--quantization"
- "awq"
- "--dtype" - "--dtype"
- "half" - "bfloat16"
- "--max-model-len" - "--max-model-len"
- "16384" - "32768"
ports: ports:
- containerPort: 8000 - containerPort: 8000
resources: resources: