AbstractPhil commited on
Commit
779f739
·
verified ·
1 Parent(s): f08e3ed

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -0
README.md CHANGED
@@ -43,6 +43,16 @@ of anchored attenuation rules.
43
  Theoretically this not only solved rope, but it pushed the context window so far out that it's going to become a python problem for
44
  moving data into the machine, rather than a vram or a gpu computational problem for processing it.
45
 
 
 
 
 
 
 
 
 
 
 
46
  Combined with the potency hybrid attention, or no attention which is what I'll use, hybrid attention will enable Ulysses, which means...
47
  well... multi-machine optimization.
48
 
 
43
  Theoretically this not only solved rope, but it pushed the context window so far out that it's going to become a python problem for
44
  moving data into the machine, rather than a vram or a gpu computational problem for processing it.
45
 
46
+ Below is a rope component synthesizer that produces many forms of rope that I specifically created for bulk ensemble experimentation.
47
+
48
+ https://github.com/AbstractEyes/geofractal/blob/main/src/geofractal/router/components/rope_component.py
49
+
50
+ Below is a transformer component built specifically for high-yield reuse.
51
+
52
+ https://github.com/AbstractEyes/geofractal/blob/main/src/geofractal/router/components/transformer_component.py
53
+
54
+ Those are viable ropes within their spectrums but they don't conform to all utility, not like the potential from the geolip concept.
55
+
56
  Combined with the potency hybrid attention, or no attention which is what I'll use, hybrid attention will enable Ulysses, which means...
57
  well... multi-machine optimization.
58