add Qwen3-Coder-Next model
This commit is contained in:
@@ -466,3 +466,18 @@ models:
|
||||
--presence-penalty 0.4
|
||||
--no-warmup
|
||||
--port ${PORT}
|
||||
|
||||
"Qwen3-Coder-Next-GGUF:Q4_K_M":
|
||||
ttl: 600
|
||||
cmd: |
|
||||
/app/llama-server
|
||||
-hf unsloth/Qwen3-Coder-Next-GGUF:Q4_K_M
|
||||
--ctx-size 32768
|
||||
--predict 8192
|
||||
--temp 1.0
|
||||
--min-p 0.01
|
||||
--top-p 0.95
|
||||
--top-k 40
|
||||
--repeat-penalty 1.0
|
||||
--no-warmup
|
||||
--port ${PORT}
|
||||
|
||||
Reference in New Issue
Block a user