staka commited on
Commit
8227fda
1 Parent(s): 75d3ae1

First model version

Browse files
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "swish",
4
+ "architectures": [
5
+ "MarianMTModel"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "bad_words_ids": [
9
+ [
10
+ 32000
11
+ ]
12
+ ],
13
+ "bos_token_id": 0,
14
+ "classifier_dropout": 0.0,
15
+ "d_model": 512,
16
+ "decoder_attention_heads": 8,
17
+ "decoder_ffn_dim": 2048,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 6,
20
+ "decoder_start_token_id": 32000,
21
+ "dropout": 0.1,
22
+ "encoder_attention_heads": 8,
23
+ "encoder_ffn_dim": 2048,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 6,
26
+ "eos_token_id": 0,
27
+ "forced_eos_token_id": 0,
28
+ "gradient_checkpointing": false,
29
+ "init_std": 0.02,
30
+ "is_encoder_decoder": true,
31
+ "max_length": 512,
32
+ "max_position_embeddings": 512,
33
+ "model_type": "marian",
34
+ "normalize_embedding": false,
35
+ "num_beams": 12,
36
+ "num_hidden_layers": 6,
37
+ "pad_token_id": 32000,
38
+ "scale_embedding": true,
39
+ "static_position_embeddings": true,
40
+ "torch_dtype": "float16",
41
+ "transformers_version": "4.9.2",
42
+ "use_cache": true,
43
+ "vocab_size": 32001
44
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:779a996cd2d7bdf2839bb53b4147d2dc3a9ac9461bed75cfbe191c3f725ca758
3
+ size 153960131
source.spm ADDED
Binary file (768 kB). View file
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
target.spm ADDED
Binary file (768 kB). View file
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"target_lang": "ja", "source_lang": "en"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff