Image-Text-to-Text
Safetensors
qwen3_5
conversational
Lambent commited on
Commit
a5a2f9f
·
verified ·
1 Parent(s): e6c0ed0

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -0
README.md ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ datasets:
4
+ - Luminous-Designs/schwartz-constitutional-sft
5
+ base_model:
6
+ - Luminous-Designs/Qwen3.5-9B-Base-Transcendent-Interiority
7
+ pipeline_tag: image-text-to-text
8
+ ---
9
+
10
+ Methodology:
11
+ * Synthesized 100 rows of SFT data utilizing a constitutional approach with the ancestor model (feedback with constitution)
12
+ * Stripped reasoning traces
13
+ * Trained at rank 256, lr 2e-7 for 8 epochs on those 100 rows