2026-09-22 04:56:26 +00:00
1 changed files with 7 additions and 0 deletions
@@ -71,6 +71,13 @@ let
    [ornith-1.5-9b-uncensored]
    hf-repo = mradermacher/Ornith-1.5-9B-uncensored-GGUF:Q4_K_M
    dedup-cache-models = true
    ; Runaway guard (2026-09-21): as Hermes' auxiliary model (approval, title, web
    ; extract) it got requests with no max_tokens, never converged, and one generation
    ; ran to 46k tokens (~70 min at 11 t/s) after the client's 60 s timeout, starving the
    ; 35B. Helper tasks need short answers: cap thinking and total output server-side.
    ; A client that sends its own smaller max_tokens still wins.
    reasoning-budget = 2048
    n-predict = 4096
    ; Qwen3-VL-8B Instruct, refusal-ablated (prithivMLmods v2 / mradermacher).
    ; Dedicated VLM in the same size class as Ornith 1.5 9B. Explicit mmproj-url