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

Merge pull request #18 from sirius0xdev/fix/vllm-trust-remote-code-tokenizer

Browse source 
fix: revert tokenizer mode to auto
This commit is contained in:
sirius0xdev 2026-04-18 16:35:51 -04:00 • committed by GitHub
commit 73a4ee6408
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
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
value: ""
- name: VLLM_TOKENIZER_MODE
value: "mistral"
value: "auto"
args:
- "--model"
- "dphn/Dolphin-Mistral-24B-Venice-Edition" # Uncensored 24B (Native)