stop-20261117/pretraining-one: step 20610
Browse files
.gitattributes
CHANGED
|
@@ -37,3 +37,4 @@ full-20261117/pretraining-one/train.json filter=lfs diff=lfs merge=lfs -text
|
|
| 37 |
full-20261117/pretraining-one-best/train.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
full-20261117/pretraining-two/train.json filter=lfs diff=lfs merge=lfs -text
|
| 39 |
full-20261117/pretraining-two-best/train.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 37 |
full-20261117/pretraining-one-best/train.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
full-20261117/pretraining-two/train.json filter=lfs diff=lfs merge=lfs -text
|
| 39 |
full-20261117/pretraining-two-best/train.json filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
stop-20261117/pretraining-one/train.json filter=lfs diff=lfs merge=lfs -text
|
stop-20261117/pretraining-one/checkpoint.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
stop-20261117/pretraining-one/config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"layers": 12,
|
| 3 |
+
"width": 768,
|
| 4 |
+
"heads": 6,
|
| 5 |
+
"depth_layers": 2,
|
| 6 |
+
"depth_width": 256,
|
| 7 |
+
"depth_heads": 4,
|
| 8 |
+
"context": 4096,
|
| 9 |
+
"codebooks": 8,
|
| 10 |
+
"cardinality": 2048,
|
| 11 |
+
"fps": 12.5,
|
| 12 |
+
"text": "one",
|
| 13 |
+
"factorization": "two-tracks-delay-0-1-1-1-1-1-1-1-text-advance-shift-6+0"
|
| 14 |
+
}
|
stop-20261117/pretraining-one/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:798a4c7b21e11514311f9f09e608ebf3980faf0a0ad9f30b1bf267f2431578c0
|
| 3 |
+
size 803524736
|
stop-20261117/pretraining-one/train.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:406a13d31eced80d2d39ffb6e0ac72bba6094e0450548a585f529ab38b310e67
|
| 3 |
+
size 14148922
|