add gemma-3-270m-it-qat model

This commit is contained in:
2026-02-28 22:25:47 +01:00
parent 8c29fc8018
commit 2bb23c4ed0

View File

@@ -538,3 +538,18 @@ models:
--presence-penalty 1.5 --presence-penalty 1.5
--no-warmup --no-warmup
--port ${PORT} --port ${PORT}
"gemma-3-270m-it-qat-GGUF:Q4_K_M":
ttl: 600
cmd: |
/app/llama-server
-hf unsloth/gemma-3-270m-it-qat-GGUF:Q4_K_M
--ctx-size 16384
--predict 4096
--temp 1.0
--min-p 0.01
--top-p 0.95
--top-k 64
--repeat-penalty 1.0
--no-warmup
--port ${PORT}