Trained on Kurier seed 42 [no dropout, consistency bt]
Browse files- config.json +2 -2
- pytorch_model.bin +1 -1
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"_num_labels": 3,
|
4 |
"activation_dropout": 0.0,
|
5 |
"activation_function": "gelu",
|
@@ -18,7 +18,7 @@
|
|
18 |
"decoder_layerdrop": 0.0,
|
19 |
"decoder_layers": 12,
|
20 |
"decoder_start_token_id": 250003,
|
21 |
-
"dropout": 0.
|
22 |
"encoder_attention_heads": 16,
|
23 |
"encoder_ffn_dim": 4096,
|
24 |
"encoder_layerdrop": 0.0,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "facebook/mbart-large-cc25",
|
3 |
"_num_labels": 3,
|
4 |
"activation_dropout": 0.0,
|
5 |
"activation_function": "gelu",
|
|
|
18 |
"decoder_layerdrop": 0.0,
|
19 |
"decoder_layers": 12,
|
20 |
"decoder_start_token_id": 250003,
|
21 |
+
"dropout": 0.0,
|
22 |
"encoder_attention_heads": 16,
|
23 |
"encoder_ffn_dim": 4096,
|
24 |
"encoder_layerdrop": 0.0,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2444583325
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98aed71469b37795d60de2ef062e9f633ddd629a7229f83a94f0ba2301352348
|
3 |
size 2444583325
|