kimi/Timmy-time-dashboard
Archived
1
0
Fork 0
forked from Rockachopa/Timmy-time-dashboard
Code Pull Requests Activity

[claude] Qwen3 two-model routing via task complexity classifier (#1065) v2 (#1233)

Browse Source 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
This commit is contained in:
Claude (Opus 4.6)
2026-03-23 22:58:21 +00:00
committed by Timmy Time
parent acc0df00cf
commit 1e1689f931
7 changed files with 635 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
src/config.py
View File

@@ -51,6 +51,13 @@ class Settings(BaseSettings):
# Set to 0 to use model defaults.
ollama_num_ctx: int = 32768
# Maximum models loaded simultaneously in Ollama — override with OLLAMA_MAX_LOADED_MODELS
# Set to 2 so Qwen3-8B and Qwen3-14B can stay hot concurrently (~17 GB combined).
# Requires Ollama ≥ 0.1.33. Export this to the Ollama process environment:
# OLLAMA_MAX_LOADED_MODELS=2 ollama serve
# or add it to your systemd/launchd unit before starting the harness.
ollama_max_loaded_models: int = 2
# Fallback model chains — override with FALLBACK_MODELS / VISION_FALLBACK_MODELS
# as comma-separated strings, e.g. FALLBACK_MODELS="qwen3:8b,qwen2.5:14b"
# Or edit config/providers.yaml → fallback_chains for the canonical source.