Harden and demote experimental Hermes compressor

compose.yaml

@@ -97,7 +97,7 @@ services:
     cap_drop: [ALL]
     command:
       - --model
-      - "/models/${COMPRESSION_MODEL_FILE:-qwen3.5-2b-compression/Qwen_Qwen3.5-2B-Q4_K_M.gguf}"
+      - "/models/${COMPRESSION_MODEL_FILE:-qwen3.5-4b-compression/Qwen_Qwen3.5-4B-Q4_K_M.gguf}"
       - --alias
       - qwen-compression
       - --ctx-size
@@ -117,6 +117,21 @@ services:
       - --port
       - "8099"
       - --metrics
+      # Official Qwen3.5 non-thinking sampler. The presence penalty is
+      # essential here: without it one technical YAML benchmark repeated the
+      # summary structure for more than 40K tokens.
+      - --temperature
+      - "1.0"
+      - --top-p
+      - "1.0"
+      - --top-k
+      - "20"
+      - --presence-penalty
+      - "2.0"
+      # Hermes' own summary ceiling is 10K. Keep a little completion margin,
+      # but never allow an accidental repetition loop to fill the 65K slot.
+      - --n-predict
+      - "12000"
       - --n-gpu-layers
       - all
       - --device