michael/AI-Profile-Router
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix Thinking Off handling

Browse Source
This commit is contained in:
Mikei386
2026-08-31 08:15:27 +02:00
parent 0fa9a34886
commit 7e36f1dbb7
5 changed files with 22 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files
config/install.env.example
+1 -1
View File
@@ -72,7 +72,7 @@ EXPERIMENTAL_MODEL_SHA256=40fac4050e940397dbf13087afd50f4734a11805bf9d65ef8ddd74
VISION_PROJECTOR_FILE=qwen/mmproj-BF16.gguf
VISION_PROJECTOR_URL=https://huggingface.co/unsloth/Qwen3.8-27B-GGUF/resolve/main/mmproj-BF16.gguf
VISION_PROJECTOR_SHA256=83ee4f4f205fa514161778c41df1ea14144faa0f713510893b63c2395f5c2d53
DEFAULT_REASONING_EFFORT=medium
DEFAULT_REASONING_EFFORT=off
# All standard profiles use the MTP tensor embedded in their GGUF. A separate
# draft-model artifact is neither downloaded nor passed to llama-server.