In progress training - batch: 0
Browse files- config.json +1 -1
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -30,7 +30,7 @@
|
|
| 30 |
"dense",
|
| 31 |
"moe"
|
| 32 |
],
|
| 33 |
-
"stm_size":
|
| 34 |
"use_attention_output_bias": false,
|
| 35 |
"use_flash_attention": true,
|
| 36 |
"use_gated": true,
|
|
|
|
| 30 |
"dense",
|
| 31 |
"moe"
|
| 32 |
],
|
| 33 |
+
"stm_size": 1024,
|
| 34 |
"use_attention_output_bias": false,
|
| 35 |
"use_flash_attention": true,
|
| 36 |
"use_gated": true,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e4cab829fae3b074222d1d633a11e21c5ec5dcfd907f03671f72dcdef3e866b
|
| 3 |
+
size 1118958072
|