Add Qwen3.5-35-A3B model
This commit is contained in:
@@ -456,3 +456,30 @@ models:
|
||||
--repeat-penalty 1.0
|
||||
--no-warmup
|
||||
--port ${PORT}
|
||||
|
||||
"Qwen3.5-35B-A3B-GGUF:Q4_K_M":
|
||||
ttl: 600
|
||||
cmd: |
|
||||
/app/llama-server
|
||||
-hf unsloth/Qwen3.5-35B-A3B-GGUF:Q4_K_M
|
||||
--ctx-size 16384
|
||||
--temp 1.0
|
||||
--min-p 0.00
|
||||
--top-p 0.95
|
||||
--top-k 20
|
||||
--no-warmup
|
||||
--port ${PORT}
|
||||
|
||||
"Qwen3.5-35B-A3B-GGUF-nothink:Q4_K_M":
|
||||
ttl: 600
|
||||
cmd: |
|
||||
/app/llama-server
|
||||
-hf unsloth/Qwen3.5-35B-A3B-GGUF:Q4_K_M
|
||||
--ctx-size 16384
|
||||
--temp 1.0
|
||||
--min-p 0.00
|
||||
--top-p 0.95
|
||||
--top-k 20
|
||||
--no-warmup
|
||||
--port ${PORT}
|
||||
--chat-template-kwargs "{\"enable_thinking\": false}"
|
||||
|
||||
Reference in New Issue
Block a user