feat: add new models

This commit is contained in:
Davide Polonio 2026-04-10 15:10:38 +02:00
parent c6e4901dee
commit 2d852879b6

View File

@ -44,3 +44,25 @@ models:
--n-gpu-layers 999
--ctx-size 32768
--temp 0.6 --top-k 20 --top-p 0.95 --repeat-penalty 1
"gemma4:e4b-uncensored":
cmd: |
/app/llama-server
--host 0.0.0.0 --port ${PORT}
--jinja
--model /models/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q8_K_P.gguf
--mmproj /models/mmproj-Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-f16.gguf
--alias "hf.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive:q8_k_p"
--n-gpu-layers 999
--ctx-size 8192
"gemma4:26b-a4b":
cmd: |
/app/llama-server
--host 0.0.0.0 --port ${PORT}
--jinja
--model /models/gemma-4-26B-A4B-it-UD-IQ4_NL.gguf
--mmproj /models/gemma-4-26B-A4B-it-UD-IQ4_NL-mmproj-BF16.gguf
--alias "hf.co/unsloth/gemma-4-26B-A4B-it:ud-iq4_nl"
--n-gpu-layers 999
--ctx-size 8192