kami
d0afd9d4f6
Stock Qwen3-1.7B, not the CPT'd one — that training is still running. It won on both fixtures we have, measured tonight on an otherwise idle box: routing, 77 RU cases, intent-only: 67.5% vs 59.7% for Qwen3.5-0.8B talk fixture, 27 cases: 20/27 vs 11-17/27 It also beat Qwen3.5-2B, which is 20% larger, on every routing column. Two other things came with it: n_ctx goes 2048 -> 4096. This is a Thinking variant, so reasoning tokens need the room, and 4096 is the context every score above was measured at. Shipping 2048 would ship something nobody measured. The doc now says not to bother with sub-500M models, because I checked and they are not close. LFM2.5-350M routes at 5.2% — worse than guessing among 7 intents — and answers "столица Франции?" with "Сторзит", which is not a word. The 230M replies to Russian in Spanish. Their published IFEval and BFCL numbers are good and they are all English. Note the routing gain needs the LLM router actually wired on to show up. It is still nil, so this commit buys the phrasing improvement today and the routing improvement when that lands. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ
65 lines
2.7 KiB
JSON
65 lines
2.7 KiB
JSON
{
|
|
"db_path": "/var/lib/maven/maven.db.enc",
|
|
"db_tmpfs": "/dev/shm/maven-plain.db",
|
|
"db_key_env": "MAVEN_DB_KEY",
|
|
"socket_path": "/run/maven/mavend.sock",
|
|
"state_dir": "/var/lib/maven",
|
|
|
|
"phraser": {
|
|
"model_path": "/opt/maven/models/llm/qwen3/Qwen3-1.7B-UD-Q4_K_XL.gguf",
|
|
"bin_path": "llama-server",
|
|
"n_gpu_layers": 99,
|
|
"n_ctx": 4096,
|
|
"timeout": "60s",
|
|
"llm_nudges": false
|
|
},
|
|
|
|
"telegram": {
|
|
"bot_token": "${TELEGRAM_BOT_TOKEN}",
|
|
"chat_id": "${TELEGRAM_CHAT_ID}"
|
|
},
|
|
|
|
"digest": {
|
|
"enabled": true,
|
|
"window": "30m",
|
|
"max_items": 5,
|
|
"severity_ceiling": 2
|
|
},
|
|
|
|
"nexus": { "url": "http://nexus:9740" },
|
|
"praxis": { "url": "http://praxis:8989" },
|
|
"hexis": { "url": "http://hexis:9741" },
|
|
|
|
"voice": {
|
|
"enabled": true,
|
|
"bind": "0.0.0.0:9100",
|
|
"lang": "ru",
|
|
"stt": { "socket": "/run/maven/stt.sock", "lang": "ru" },
|
|
"tts": { "socket": "/run/maven/tts.sock", "lang": "ru" },
|
|
"embedder": {
|
|
"model_path": "/opt/maven/models/embedder/multilingual-e5-small/model_quantized.onnx",
|
|
"tokenizer_path": "/opt/maven/models/embedder/multilingual-e5-small/tokenizer.json",
|
|
"lib_path": "/opt/maven/lib/libonnxruntime.so"
|
|
},
|
|
"llm_router": true,
|
|
"query_min_score": 0.55,
|
|
"query_min_margin": 0.008,
|
|
"clarify_max_attempts": 3,
|
|
"tool_timeout": "30s",
|
|
"tools": [
|
|
{ "name": "status", "cmd": ["systemctl", "status"], "scope": "homelab", "destructive": false },
|
|
{ "name": "ps", "cmd": ["docker", "ps"], "scope": "homelab", "destructive": false },
|
|
{ "name": "uptime", "cmd": ["uptime"], "scope": "homelab", "destructive": false },
|
|
{ "name": "disk", "cmd": ["df", "-h"], "scope": "homelab", "destructive": false },
|
|
{ "name": "memory", "cmd": ["free", "-h"], "scope": "homelab", "destructive": false },
|
|
{ "name": "logs", "cmd": ["journalctl", "-n", "50", "-u"], "scope": "homelab", "destructive": false },
|
|
{ "name": "restart", "cmd": ["systemctl", "restart"], "scope": "homelab", "destructive": true },
|
|
{ "name": "stop", "cmd": ["systemctl", "stop"], "scope": "homelab", "destructive": true },
|
|
{ "name": "start", "cmd": ["systemctl", "start"], "scope": "homelab", "destructive": true },
|
|
{ "name": "docker-restart", "cmd": ["docker", "restart"], "scope": "homelab", "destructive": true },
|
|
{ "name": "docker-stop", "cmd": ["docker", "stop"], "scope": "homelab", "destructive": true },
|
|
{ "name": "reboot", "cmd": ["systemctl", "reboot"], "scope": "homelab", "destructive": true }
|
|
]
|
|
}
|
|
}
|