adrianjoheni
commited on
Commit
•
b029ff9
1
Parent(s):
739e8c8
Upload folder using huggingface_hub
Browse files- .gitattributes +6 -32
- README.md +104 -0
- config.json +62 -0
- flax_model.msgpack +3 -0
- generation_config.json +16 -0
- metadata.json +1 -0
- pytorch_model.bin +3 -0
- source.spm +0 -0
- target.spm +0 -0
- tf_model.h5 +3 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -1,35 +1,9 @@
|
|
1 |
-
*.
|
2 |
-
*.
|
3 |
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
-
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
-
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
-
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
-
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
-
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
-
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
-
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
-
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
-
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
-
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
-
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
-
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
-
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
-
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
-
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
-
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
-
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
-
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
-
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
-
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
-
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
-
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
-
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
-
*.tar filter=lfs diff=lfs merge=lfs -text
|
29 |
*.tflite filter=lfs diff=lfs merge=lfs -text
|
30 |
-
*.
|
31 |
-
*.
|
32 |
-
*.
|
33 |
-
*.
|
34 |
-
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
-
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
1 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
3 |
*.bin filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
4 |
*.h5 filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
*.tflite filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
|
|
|
README.md
ADDED
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
- es
|
5 |
+
|
6 |
+
tags:
|
7 |
+
- translation
|
8 |
+
|
9 |
+
license: apache-2.0
|
10 |
+
---
|
11 |
+
|
12 |
+
### eng-spa
|
13 |
+
|
14 |
+
* source group: English
|
15 |
+
* target group: Spanish
|
16 |
+
* OPUS readme: [eng-spa](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-spa/README.md)
|
17 |
+
|
18 |
+
* model: transformer
|
19 |
+
* source language(s): eng
|
20 |
+
* target language(s): spa
|
21 |
+
* model: transformer
|
22 |
+
* pre-processing: normalization + SentencePiece (spm32k,spm32k)
|
23 |
+
* download original weights: [opus-2020-08-18.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-spa/opus-2020-08-18.zip)
|
24 |
+
* test set translations: [opus-2020-08-18.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-spa/opus-2020-08-18.test.txt)
|
25 |
+
* test set scores: [opus-2020-08-18.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-spa/opus-2020-08-18.eval.txt)
|
26 |
+
|
27 |
+
## Benchmarks
|
28 |
+
|
29 |
+
| testset | BLEU | chr-F |
|
30 |
+
|-----------------------|-------|-------|
|
31 |
+
| newssyscomb2009-engspa.eng.spa | 31.0 | 0.583 |
|
32 |
+
| news-test2008-engspa.eng.spa | 29.7 | 0.564 |
|
33 |
+
| newstest2009-engspa.eng.spa | 30.2 | 0.578 |
|
34 |
+
| newstest2010-engspa.eng.spa | 36.9 | 0.620 |
|
35 |
+
| newstest2011-engspa.eng.spa | 38.2 | 0.619 |
|
36 |
+
| newstest2012-engspa.eng.spa | 39.0 | 0.625 |
|
37 |
+
| newstest2013-engspa.eng.spa | 35.0 | 0.598 |
|
38 |
+
| Tatoeba-test.eng.spa | 54.9 | 0.721 |
|
39 |
+
|
40 |
+
|
41 |
+
### System Info:
|
42 |
+
- hf_name: eng-spa
|
43 |
+
|
44 |
+
- source_languages: eng
|
45 |
+
|
46 |
+
- target_languages: spa
|
47 |
+
|
48 |
+
- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-spa/README.md
|
49 |
+
|
50 |
+
- original_repo: Tatoeba-Challenge
|
51 |
+
|
52 |
+
- tags: ['translation']
|
53 |
+
|
54 |
+
- languages: ['en', 'es']
|
55 |
+
|
56 |
+
- src_constituents: {'eng'}
|
57 |
+
|
58 |
+
- tgt_constituents: {'spa'}
|
59 |
+
|
60 |
+
- src_multilingual: False
|
61 |
+
|
62 |
+
- tgt_multilingual: False
|
63 |
+
|
64 |
+
- prepro: normalization + SentencePiece (spm32k,spm32k)
|
65 |
+
|
66 |
+
- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-spa/opus-2020-08-18.zip
|
67 |
+
|
68 |
+
- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/eng-spa/opus-2020-08-18.test.txt
|
69 |
+
|
70 |
+
- src_alpha3: eng
|
71 |
+
|
72 |
+
- tgt_alpha3: spa
|
73 |
+
|
74 |
+
- short_pair: en-es
|
75 |
+
|
76 |
+
- chrF2_score: 0.721
|
77 |
+
|
78 |
+
- bleu: 54.9
|
79 |
+
|
80 |
+
- brevity_penalty: 0.978
|
81 |
+
|
82 |
+
- ref_len: 77311.0
|
83 |
+
|
84 |
+
- src_name: English
|
85 |
+
|
86 |
+
- tgt_name: Spanish
|
87 |
+
|
88 |
+
- train_date: 2020-08-18 00:00:00
|
89 |
+
|
90 |
+
- src_alpha2: en
|
91 |
+
|
92 |
+
- tgt_alpha2: es
|
93 |
+
|
94 |
+
- prefer_old: False
|
95 |
+
|
96 |
+
- long_pair: eng-spa
|
97 |
+
|
98 |
+
- helsinki_git_sha: d2f0910c89026c34a44e331e785dec1e0faa7b82
|
99 |
+
|
100 |
+
- transformers_git_sha: f7af09b4524b784d67ae8526f0e2fcc6f5ed0de9
|
101 |
+
|
102 |
+
- port_machine: brutasse
|
103 |
+
|
104 |
+
- port_time: 2020-08-24-18:20
|
config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/tmp/Helsinki-NLP/opus-mt-en-es",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "swish",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"MarianMTModel"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.0,
|
11 |
+
"bad_words_ids": [
|
12 |
+
[
|
13 |
+
65000
|
14 |
+
]
|
15 |
+
],
|
16 |
+
"bos_token_id": 0,
|
17 |
+
"classif_dropout": 0.0,
|
18 |
+
"classifier_dropout": 0.0,
|
19 |
+
"d_model": 512,
|
20 |
+
"decoder_attention_heads": 8,
|
21 |
+
"decoder_ffn_dim": 2048,
|
22 |
+
"decoder_layerdrop": 0.0,
|
23 |
+
"decoder_layers": 6,
|
24 |
+
"decoder_start_token_id": 65000,
|
25 |
+
"decoder_vocab_size": 65001,
|
26 |
+
"dropout": 0.1,
|
27 |
+
"encoder_attention_heads": 8,
|
28 |
+
"encoder_ffn_dim": 2048,
|
29 |
+
"encoder_layerdrop": 0.0,
|
30 |
+
"encoder_layers": 6,
|
31 |
+
"eos_token_id": 0,
|
32 |
+
"extra_pos_embeddings": 65001,
|
33 |
+
"force_bos_token_to_be_generated": false,
|
34 |
+
"forced_eos_token_id": 0,
|
35 |
+
"gradient_checkpointing": false,
|
36 |
+
"id2label": {
|
37 |
+
"0": "LABEL_0",
|
38 |
+
"1": "LABEL_1",
|
39 |
+
"2": "LABEL_2"
|
40 |
+
},
|
41 |
+
"init_std": 0.02,
|
42 |
+
"is_encoder_decoder": true,
|
43 |
+
"label2id": {
|
44 |
+
"LABEL_0": 0,
|
45 |
+
"LABEL_1": 1,
|
46 |
+
"LABEL_2": 2
|
47 |
+
},
|
48 |
+
"max_length": 512,
|
49 |
+
"max_position_embeddings": 512,
|
50 |
+
"model_type": "marian",
|
51 |
+
"normalize_before": false,
|
52 |
+
"normalize_embedding": false,
|
53 |
+
"num_beams": 4,
|
54 |
+
"num_hidden_layers": 6,
|
55 |
+
"pad_token_id": 65000,
|
56 |
+
"scale_embedding": true,
|
57 |
+
"share_encoder_decoder_embeddings": true,
|
58 |
+
"static_position_embeddings": true,
|
59 |
+
"transformers_version": "4.22.0.dev0",
|
60 |
+
"use_cache": true,
|
61 |
+
"vocab_size": 65001
|
62 |
+
}
|
flax_model.msgpack
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14b5e0865da9b6764e18b637e7c7e34b04be927dc41a1ba97bff23962c2f5857
|
3 |
+
size 309944974
|
generation_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bad_words_ids": [
|
3 |
+
[
|
4 |
+
65000
|
5 |
+
]
|
6 |
+
],
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"decoder_start_token_id": 65000,
|
9 |
+
"eos_token_id": 0,
|
10 |
+
"forced_eos_token_id": 0,
|
11 |
+
"max_length": 512,
|
12 |
+
"num_beams": 4,
|
13 |
+
"pad_token_id": 65000,
|
14 |
+
"renormalize_logits": true,
|
15 |
+
"transformers_version": "4.32.0.dev0"
|
16 |
+
}
|
metadata.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"hf_name":"eng-spa","source_languages":"eng","target_languages":"spa","opus_readme_url":"https:\/\/github.com\/Helsinki-NLP\/Tatoeba-Challenge\/tree\/master\/models\/eng-spa\/README.md","original_repo":"Tatoeba-Challenge","tags":["translation"],"languages":["en","es"],"src_constituents":["eng"],"tgt_constituents":["spa"],"src_multilingual":false,"tgt_multilingual":false,"prepro":" normalization + SentencePiece (spm32k,spm32k)","url_model":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/eng-spa\/opus-2020-08-18.zip","url_test_set":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/eng-spa\/opus-2020-08-18.test.txt","src_alpha3":"eng","tgt_alpha3":"spa","short_pair":"en-es","chrF2_score":0.721,"bleu":54.9,"brevity_penalty":0.978,"ref_len":77311.0,"src_name":"English","tgt_name":"Spanish","train_date":1597708800000,"src_alpha2":"en","tgt_alpha2":"es","prefer_old":false,"long_pair":"eng-spa","helsinki_git_sha":"d2f0910c89026c34a44e331e785dec1e0faa7b82","transformers_git_sha":"f7af09b4524b784d67ae8526f0e2fcc6f5ed0de9","port_machine":"brutasse","port_time":"2020-08-24-18:20"}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:befce0f620e8e63f83bbb7f0818eb51d541cba28057a7cc14b00466d85c4994c
|
3 |
+
size 312087523
|
source.spm
ADDED
Binary file (802 kB). View file
|
|
target.spm
ADDED
Binary file (826 kB). View file
|
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c0f86262f3ac03867ced8dd0b8ed83f7f2a39972f7249f60bf34ff8ea9e8765
|
3 |
+
size 312580600
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"target_lang": "spa", "source_lang": "eng"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|