-
Deepseek fixes
-
Update deepseek-r1-500gbofvram.kcppt
-
Fix incorrect variable
-
Upload Gemma-3-27B-it-abliterated.kcppt
-
Upload Gemma-3-27B-it.kcppt
-
Upload Gemma-3-27B-it.kcppt
-
Fix two gemma 3 27b settings
-
Upload QwQ-32B-Abliterated.kcppt
-
Increased gen amount for chat adapters
-
Upload QwQ-32B.kcppt
-
Enable think insertion
This is now possible and recommended by Deepseek
-
Upload deepseek-r1-500gbofvram.kcppt
-
Upload deepseek-r1-500gbofvram.kcppt
-
Upload deepseek-r1-500gbofvram.kcppt
-
Upload deepseek-r1-500gbofvram.kcppt
-
Cleanup
-
Increase Qwen2 VL 7B context size
Model doesn't work at 4K -
Upload Qwen2VL.kcppt
-
Upload Flux1-Dev.kcppt
-
Einstein's F16 collection
-
Upload 5 files
-
Rename MiniCPM.kcppt to MiniCPM-2.6.kcppt
-
Upload MiniCPM.kcppt
-
Upload Llama-3.1-8B.kcppt
-
Upload Llama-3.1-8B.kcppt
-
initial commit
