The plain matrices are not blind to what is stated once
Browse files- RELEASE_NOTES_v3.md +6 -4
RELEASE_NOTES_v3.md
CHANGED
|
@@ -54,10 +54,12 @@ That costs 0.0027 of pure-text cosine on the residual and 0.0013 on the matrix
|
|
| 54 |
which is why the 8B figures above are slightly below what a text-only corpus
|
| 55 |
would have given.
|
| 56 |
|
| 57 |
-
**Prefer the `-mlp` files.**
|
| 58 |
-
|
| 59 |
-
|
| 60 |
-
|
|
|
|
|
|
|
| 61 |
|
| 62 |
## What this does not fix, and will not
|
| 63 |
|
|
|
|
| 54 |
which is why the 8B figures above are slightly below what a text-only corpus
|
| 55 |
would have given.
|
| 56 |
|
| 57 |
+
**Prefer the `-mlp` files.** They measure closer to the 32B, 0.9449 against
|
| 58 |
+
0.9289 on the 8B, and on the demo scene both plain matrices get the seated pose
|
| 59 |
+
wrong: the prompt asks for one bare leg crossed over the other and they sit her
|
| 60 |
+
cross-legged. But the gap is narrower than that sounds — the cat, the straw hat,
|
| 61 |
+
the laundry and the bouncing knee all come through on the plain matrices too. On
|
| 62 |
+
this scene they missed one attribute among many, and it happened to be the pose.
|
| 63 |
|
| 64 |
## What this does not fix, and will not
|
| 65 |
|