subham92 commited on
Commit
d8815c1
1 Parent(s): b5885c5

Added model

Browse files
Files changed (6) hide show
  1. config.json +53 -0
  2. metadata.json +1 -0
  3. source.spm +0 -0
  4. target.spm +0 -0
  5. tokenizer_config.json +1 -0
  6. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "swish",
4
+ "add_bias_logits": false,
5
+ "add_final_layer_norm": false,
6
+ "architectures": [
7
+ "MarianMTModel"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "bad_words_ids": [
11
+ [
12
+ 59658
13
+ ]
14
+ ],
15
+ "bos_token_id": 0,
16
+ "classif_dropout": 0.0,
17
+ "d_model": 512,
18
+ "decoder_attention_heads": 8,
19
+ "decoder_ffn_dim": 2048,
20
+ "decoder_layerdrop": 0.0,
21
+ "decoder_layers": 6,
22
+ "decoder_start_token_id": 59658,
23
+ "dropout": 0.1,
24
+ "encoder_attention_heads": 8,
25
+ "encoder_ffn_dim": 2048,
26
+ "encoder_layerdrop": 0.0,
27
+ "encoder_layers": 6,
28
+ "eos_token_id": 0,
29
+ "extra_pos_embeddings": 59659,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1",
33
+ "2": "LABEL_2"
34
+ },
35
+ "init_std": 0.02,
36
+ "is_encoder_decoder": true,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_2": 2
41
+ },
42
+ "max_length": 512,
43
+ "max_position_embeddings": 512,
44
+ "model_type": "marian",
45
+ "normalize_before": false,
46
+ "normalize_embedding": false,
47
+ "num_beams": 4,
48
+ "num_hidden_layers": 6,
49
+ "pad_token_id": 59658,
50
+ "scale_embedding": true,
51
+ "static_position_embeddings": true,
52
+ "vocab_size": 59659
53
+ }
metadata.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"hf_name":"fin-eng","source_languages":"fin","target_languages":"eng","opus_readme_url":"https:\/\/github.com\/Helsinki-NLP\/Tatoeba-Challenge\/tree\/master\/models\/fin-eng\/README.md","original_repo":"Tatoeba-Challenge","tags":["translation"],"languages":["fi","en"],"src_constituents":["fin"],"tgt_constituents":["eng"],"src_multilingual":false,"tgt_multilingual":false,"prepro":" normalization + SentencePiece (spm32k,spm32k)","url_model":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/fin-eng\/opus-2020-08-05.zip","url_test_set":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/fin-eng\/opus-2020-08-05.test.txt","src_alpha3":"fin","tgt_alpha3":"eng","short_pair":"fi-en","chrF2_score":0.697,"bleu":53.4,"brevity_penalty":0.99,"ref_len":74651.0,"src_name":"Finnish","tgt_name":"English","train_date":"2020-08-05","src_alpha2":"fi","tgt_alpha2":"en","prefer_old":false,"long_pair":"fin-eng","helsinki_git_sha":"480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535","transformers_git_sha":"2207e5d8cb224e954a7cba69fa4ac2309e9ff30b","port_machine":"brutasse","port_time":"2020-08-21-14:41"}
source.spm ADDED
Binary file (832 kB). View file
 
target.spm ADDED
Binary file (790 kB). View file
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"target_lang": "eng", "source_lang": "fin"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff