polpetta/desktop-dotfiles
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

style(llama-swap): consistent flag ordering across all profiles

Browse Source
This commit is contained in:
Davide Polonio 2026-04-10 15:44:24 +02:00
parent 55ac2e5568
commit 6ea3e870bd
1 changed files with 10 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
ollama/llama-swap.yaml
View File

@ -26,7 +26,8 @@ models:
--ctx-size 32768 --ctx-size 32768
--flash-attn --flash-attn
--jinja --jinja
--cache-type-k q8_0 --cache-type-v q8_0 --cache-type-k q8_0
--cache-type-v q8_0
--temp 0.7 --top-p 0.9 --temp 0.7 --top-p 0.9
"qwen3.5:9b-uncensored": "qwen3.5:9b-uncensored":
@ -40,7 +41,8 @@ models:
--ctx-size 32768 --ctx-size 32768
--flash-attn --flash-attn
--jinja --jinja
--cache-type-k q8_0 --cache-type-v q8_0 --cache-type-k q8_0
--cache-type-v q8_0
--temp 0.7 --top-p 0.9 --temp 0.7 --top-p 0.9
"qwen3.5:9b-claude-4.6-opus-reasoning": "qwen3.5:9b-claude-4.6-opus-reasoning":
@ -54,29 +56,30 @@ models:
--ctx-size 32768 --ctx-size 32768
--flash-attn --flash-attn
--jinja --jinja
--cache-type-k q8_0 --cache-type-v q8_0 --cache-type-k q8_0
--cache-type-v q8_0
--temp 0.6 --top-p 0.95 --temp 0.6 --top-p 0.95
"gemma4:e4b-uncensored": "gemma4:e4b-uncensored":
cmd: | cmd: |
/app/llama-server /app/llama-server
--host 0.0.0.0 --port ${PORT} --host 0.0.0.0 --port ${PORT}
--jinja
--flash-attn
--model /models/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q8_K_P.gguf --model /models/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q8_K_P.gguf
--mmproj /models/mmproj-Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-f16.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" --alias "hf.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive:q8_k_p"
--n-gpu-layers 999 --n-gpu-layers 999
--ctx-size 8192 --ctx-size 8192
--flash-attn
--jinja
"gemma4:26b-a4b": "gemma4:26b-a4b":
cmd: | cmd: |
/app/llama-server /app/llama-server
--host 0.0.0.0 --port ${PORT} --host 0.0.0.0 --port ${PORT}
--jinja
--flash-attn
--model /models/gemma-4-26B-A4B-it-UD-IQ4_NL.gguf --model /models/gemma-4-26B-A4B-it-UD-IQ4_NL.gguf
--mmproj /models/gemma-4-26B-A4B-it-UD-IQ4_NL-mmproj-BF16.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" --alias "hf.co/unsloth/gemma-4-26B-A4B-it:ud-iq4_nl"
--n-gpu-layers 999 --n-gpu-layers 999
--ctx-size 8192 --ctx-size 8192
--flash-attn
--jinja