NicoLab28 commited on
Commit
78778ce
·
verified ·
1 Parent(s): 12a7266

The plain matrices are not blind to what is stated once

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -118,7 +118,9 @@ That costs 0.0027 of pure-text cosine on the residual and 0.0013 on the matrix.
118
  | `mmh3-8b-ClipProj-v3` | 0.9289 |
119
  | `mmh3-4b-ClipProj-v3` | 0.9193 |
120
 
121
- **Prefer the `-mlp` files.** The plain matrices are honest linear baselines and useful as such, but a linear map does not carry an attribute the prompt states once. Ask for crossed ankles and it will seat the subject cross-legged — you can see it in the demo above, in the first two segments.
 
 
122
 
123
  ## What this is
124
 
 
118
  | `mmh3-8b-ClipProj-v3` | 0.9289 |
119
  | `mmh3-4b-ClipProj-v3` | 0.9193 |
120
 
121
+ **Prefer the `-mlp` files.** They measure closer to the 32B — 0.9449 against 0.9289 on the 8B — and on the demo scene both plain matrices get the seated pose wrong: the prompt asks for one bare leg crossed over the other, they sit her cross-legged. It is visible in the first two segments of the video.
122
+
123
+ The gap is narrower than that makes it sound, though, and it is worth being precise about it. The cat, the straw hat, the laundry, the bouncing knee — all of it comes through on the plain matrices too. A linear map is not blind to what is stated once; on this scene it missed one attribute out of many, and it happened to be the pose.
124
 
125
  ## What this is
126