straylight: cap Ornith 1.5 sampling and thinking budget
Default temp 0.6 / top-p 0.95 / top-k 20 and reasoning-budget 8192 so unrestricted <think> does not stall long agent turns.
This commit is contained in:
@@ -73,8 +73,14 @@ let
|
|||||||
|
|
||||||
; Ornith 1.5 35B-A3B MoE (official GGUF). ~3B active, multimodal; mmproj
|
; Ornith 1.5 35B-A3B MoE (official GGUF). ~3B active, multimodal; mmproj
|
||||||
; comes with --hf-repo. Q4_K_M is ~22 GB.
|
; comes with --hf-repo. Q4_K_M is ~22 GB.
|
||||||
|
; Sampling + a thinking cap: unrestricted <think> on this checkpoint stalls
|
||||||
|
; long agent turns (Talos). Clients that send their own temperature still win.
|
||||||
[ornith-1.5-35b-a3b]
|
[ornith-1.5-35b-a3b]
|
||||||
hf-repo = ornith-ai/Ornith-1.5-35B-A3B-GGUF:Q4_K_M
|
hf-repo = ornith-ai/Ornith-1.5-35B-A3B-GGUF:Q4_K_M
|
||||||
|
temp = 0.6
|
||||||
|
top-p = 0.95
|
||||||
|
top-k = 20
|
||||||
|
reasoning-budget = 8192
|
||||||
dedup-cache-models = true
|
dedup-cache-models = true
|
||||||
|
|
||||||
; Qwen 3.8 27B dense, refusal-ablated. Preferred uncensored coding agent.
|
; Qwen 3.8 27B dense, refusal-ablated. Preferred uncensored coding agent.
|
||||||
|
|||||||
Reference in New Issue
Block a user