odegiber commited on
Commit
cb6961c
1 Parent(s): dc86b49

Added model files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<s>": 32001
3
+ }
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "relu",
4
+ "architectures": [
5
+ "MarianMTModel"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "d_model": 256,
10
+ "decoder_attention_heads": 8,
11
+ "decoder_ffn_dim": 1536,
12
+ "decoder_layerdrop": 0.0,
13
+ "decoder_layers": 2,
14
+ "decoder_start_token_id": 32000,
15
+ "decoder_vocab_size": 32001,
16
+ "dropout": 0.1,
17
+ "encoder_attention_heads": 8,
18
+ "encoder_ffn_dim": 1536,
19
+ "encoder_layerdrop": 0.0,
20
+ "encoder_layers": 6,
21
+ "eos_token_id": 0,
22
+ "forced_eos_token_id": 0,
23
+ "init_std": 0.02,
24
+ "is_encoder_decoder": true,
25
+ "max_length": null,
26
+ "max_position_embeddings": 256,
27
+ "model_type": "marian",
28
+ "normalize_embedding": false,
29
+ "num_hidden_layers": 6,
30
+ "pad_token_id": 32000,
31
+ "scale_embedding": true,
32
+ "share_encoder_decoder_embeddings": true,
33
+ "static_position_embeddings": true,
34
+ "torch_dtype": "float16",
35
+ "transformers_version": "4.46.1",
36
+ "use_cache": true,
37
+ "vocab_size": 32001
38
+ }
flores_devtest.target ADDED
The diff for this file is too large to render. See raw diff
 
generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bad_words_ids": [
4
+ [
5
+ 32000
6
+ ]
7
+ ],
8
+ "bos_token_id": 0,
9
+ "decoder_start_token_id": 32000,
10
+ "eos_token_id": 0,
11
+ "forced_eos_token_id": 0,
12
+ "max_length": 512,
13
+ "pad_token_id": 32000,
14
+ "transformers_version": "4.46.1"
15
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:710825e77e18ffb2a40242359a293ca0b7db0c5277737510c638a417af1d051b
3
+ size 50743442
source.spm ADDED
Binary file (820 kB). View file
 
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
target.spm ADDED
Binary file (820 kB). View file
 
tokenizer_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "</s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<unk>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "32000": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "32001": {
28
+ "content": "<s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "</s>",
39
+ "model_max_length": 512,
40
+ "pad_token": "<pad>",
41
+ "separate_vocabs": false,
42
+ "source_lang": null,
43
+ "sp_model_kwargs": {},
44
+ "target_lang": null,
45
+ "tokenizer_class": "MarianTokenizer",
46
+ "unk_token": "<unk>"
47
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff