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

fix: revert tokenizer mode to auto

Browse source
This commit is contained in:
SiriusClaw 2026-04-18 20:34:15 +00:00
parent 0f5d0b17e5
commit 6df1e12ab0
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

@ -32,7 +32,7 @@ spec:
- name: HF_TOKEN - name: HF_TOKEN
value: "" value: ""
- name: VLLM_TOKENIZER_MODE - name: VLLM_TOKENIZER_MODE
value: "mistral" value: "auto"
args: args:
- "--model" - "--model"
- "dphn/Dolphin-Mistral-24B-Venice-Edition" # Uncensored 24B (Native) - "dphn/Dolphin-Mistral-24B-Venice-Edition" # Uncensored 24B (Native)