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

refactor: switch vLLM deployment to uncensored Dolphin-Gemma model

Browse source
This commit is contained in:
SiriusClaw 2026-04-18 15:09:21 +00:00
parent 3792be4262
commit e68774da48
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

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"
- "google/gemma-2b-it" # distilled gemma model - "cognitivecomputations/dolphin-2.8-gemma-2b-v0" # Uncensored/Distilled Dolphin-Gemma model
- "--dtype" - "--dtype"
- "bfloat16" - "bfloat16"
- "--max-model-len" - "--max-model-len"