Upload folder using huggingface_hub
Browse files- README.md +1 -1
- config.json +1 -1
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -8,4 +8,4 @@ tags:
|
|
| 8 |
|
| 9 |
# selection-coder
|
| 10 |
|
| 11 |
-
~236M decoder, **only SelectionMixing (order-statistic routing), no attention**. Muon, bf16, trained on bigcode/starcoderdata. step=
|
|
|
|
| 8 |
|
| 9 |
# selection-coder
|
| 10 |
|
| 11 |
+
~236M decoder, **only SelectionMixing (order-statistic routing), no attention**. Muon, bf16, trained on bigcode/starcoderdata. step=4000.
|
config.json
CHANGED
|
@@ -7,5 +7,5 @@
|
|
| 7 |
"ff": 4,
|
| 8 |
"arch": "SelectionCoder",
|
| 9 |
"mixer": "SelectionMixing(no-attention)",
|
| 10 |
-
"step":
|
| 11 |
}
|
|
|
|
| 7 |
"ff": 4,
|
| 8 |
"arch": "SelectionCoder",
|
| 9 |
"mixer": "SelectionMixing(no-attention)",
|
| 10 |
+
"step": 4000
|
| 11 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 538700288
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f88c693efd579b4f7b92fc33310f2833878ce2d62502175d60f7c16df4774b27
|
| 3 |
size 538700288
|