Training in progress, epoch 0
Browse files- config.json +5 -5
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -23,15 +23,15 @@
|
|
| 23 |
"is_decoder": true,
|
| 24 |
"is_encoder_decoder": false,
|
| 25 |
"max_length": 768,
|
| 26 |
-
"max_position_embeddings":
|
| 27 |
"model_type": "mbart",
|
| 28 |
"num_hidden_layers": 12,
|
| 29 |
"scale_embedding": true,
|
| 30 |
"torch_dtype": "float32",
|
| 31 |
"use_cache": true,
|
| 32 |
-
"vocab_size":
|
| 33 |
},
|
| 34 |
-
"decoder_start_token_id":
|
| 35 |
"encoder": {
|
| 36 |
"attention_probs_dropout_prob": 0.0,
|
| 37 |
"depths": [
|
|
@@ -46,8 +46,8 @@
|
|
| 46 |
"hidden_dropout_prob": 0.0,
|
| 47 |
"hidden_size": 1024,
|
| 48 |
"image_size": [
|
| 49 |
-
|
| 50 |
-
|
| 51 |
],
|
| 52 |
"initializer_range": 0.02,
|
| 53 |
"layer_norm_eps": 1e-05,
|
|
|
|
| 23 |
"is_decoder": true,
|
| 24 |
"is_encoder_decoder": false,
|
| 25 |
"max_length": 768,
|
| 26 |
+
"max_position_embeddings": 768,
|
| 27 |
"model_type": "mbart",
|
| 28 |
"num_hidden_layers": 12,
|
| 29 |
"scale_embedding": true,
|
| 30 |
"torch_dtype": "float32",
|
| 31 |
"use_cache": true,
|
| 32 |
+
"vocab_size": 57604
|
| 33 |
},
|
| 34 |
+
"decoder_start_token_id": 57579,
|
| 35 |
"encoder": {
|
| 36 |
"attention_probs_dropout_prob": 0.0,
|
| 37 |
"depths": [
|
|
|
|
| 46 |
"hidden_dropout_prob": 0.0,
|
| 47 |
"hidden_size": 1024,
|
| 48 |
"image_size": [
|
| 49 |
+
800,
|
| 50 |
+
384
|
| 51 |
],
|
| 52 |
"initializer_range": 0.02,
|
| 53 |
"layer_norm_eps": 1e-05,
|
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 sha256:953fb7774e853f0e315927440a4bb350798501e8dfa96912d16f88738e7809aa
|
| 3 |
+
size 806248600
|