Upload bartpho-word
Browse files- bpe.codes +0 -0
- config.json +35 -0
- pytorch_model.bin +3 -0
- tf_model.h5 +3 -0
- vocab.txt +0 -0
bpe.codes
ADDED
The diff for this file is too large to render.
See raw diff
|
|
config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_dropout": 0.0,
|
3 |
+
"activation_function": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"MBartModel"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": 0.0,
|
10 |
+
"d_model": 1024,
|
11 |
+
"decoder_attention_heads": 16,
|
12 |
+
"decoder_ffn_dim": 4096,
|
13 |
+
"decoder_layerdrop": 0.0,
|
14 |
+
"decoder_layers": 12,
|
15 |
+
"dropout": 0.1,
|
16 |
+
"encoder_attention_heads": 16,
|
17 |
+
"encoder_ffn_dim": 4096,
|
18 |
+
"encoder_layerdrop": 0.0,
|
19 |
+
"encoder_layers": 12,
|
20 |
+
"eos_token_id": 2,
|
21 |
+
"forced_eos_token_id": 2,
|
22 |
+
"gradient_checkpointing": false,
|
23 |
+
"init_std": 0.02,
|
24 |
+
"is_encoder_decoder": true,
|
25 |
+
"max_position_embeddings": 1024,
|
26 |
+
"model_type": "mbart",
|
27 |
+
"num_hidden_layers": 12,
|
28 |
+
"pad_token_id": 1,
|
29 |
+
"scale_embedding": false,
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"tokenizer_class": "PhobertTokenizer",
|
32 |
+
"transformers_version": "4.10.2",
|
33 |
+
"use_cache": true,
|
34 |
+
"vocab_size": 64001
|
35 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da9fbaf7d7dece30ed0c664f8e7cfa91efde34b210198ab8a0350ace38a86186
|
3 |
+
size 1681637133
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0f431c4fd186cacbb77b2d23d092daaec9220741c858c6fd53c22314daba520
|
3 |
+
size 1682005976
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|