Harden and demote experimental Hermes compressor

This commit is contained in:
Mikei386
2026-08-26 01:40:38 +02:00
parent 99285fe81a
commit aaadc57c07
7 changed files with 52 additions and 40 deletions
+2 -2
View File
@@ -12,8 +12,8 @@ XTTS_CACHE_DIR=/data/models/xtts-v2-cache
XTTS_GPU_DEVICE=GPU-4834d9d7-5b61-3004-1fb3-4ae49d482d4b
AI_DNS=192.168.1.1
# Dedicated Hermes context compressor on the RTX 3060.
COMPRESSION_MODEL_FILE=qwen3.5-2b-compression/Qwen_Qwen3.5-2B-Q4_K_M.gguf
# Experimental context-compression benchmark service on the RTX 3060.
COMPRESSION_MODEL_FILE=qwen3.5-4b-compression/Qwen_Qwen3.5-4B-Q4_K_M.gguf
COMPRESSION_CONTEXT=65536
COMPRESSION_GPU_DEVICE=GPU-4834d9d7-5b61-3004-1fb3-4ae49d482d4b