upstream-archive byte-perfect snapshot of Helsinki-NLP/opus-mt-eo-af (ADR-039 Phase D)
Browse files- .gitattributes +7 -32
- README.md +97 -0
- config.json +60 -0
- generation_config.json +16 -0
- metadata.json +1 -0
- pytorch_model.bin +3 -0
- source.spm +3 -0
- target.spm +3 -0
- tf_model.h5 +3 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -1,35 +1,10 @@
|
|
| 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 |
-
|
| 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 |
+
source.spm filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
target.spm filter=lfs diff=lfs merge=lfs -text
|
|
|
README.md
ADDED
|
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- eo
|
| 4 |
+
- af
|
| 5 |
+
|
| 6 |
+
tags:
|
| 7 |
+
- translation
|
| 8 |
+
|
| 9 |
+
license: apache-2.0
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
### epo-afr
|
| 13 |
+
|
| 14 |
+
* source group: Esperanto
|
| 15 |
+
* target group: Afrikaans
|
| 16 |
+
* OPUS readme: [epo-afr](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/epo-afr/README.md)
|
| 17 |
+
|
| 18 |
+
* model: transformer-align
|
| 19 |
+
* source language(s): epo
|
| 20 |
+
* target language(s): afr
|
| 21 |
+
* model: transformer-align
|
| 22 |
+
* pre-processing: normalization + SentencePiece (spm4k,spm4k)
|
| 23 |
+
* download original weights: [opus-2020-06-16.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/epo-afr/opus-2020-06-16.zip)
|
| 24 |
+
* test set translations: [opus-2020-06-16.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/epo-afr/opus-2020-06-16.test.txt)
|
| 25 |
+
* test set scores: [opus-2020-06-16.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/epo-afr/opus-2020-06-16.eval.txt)
|
| 26 |
+
|
| 27 |
+
## Benchmarks
|
| 28 |
+
|
| 29 |
+
| testset | BLEU | chr-F |
|
| 30 |
+
|-----------------------|-------|-------|
|
| 31 |
+
| Tatoeba-test.epo.afr | 19.5 | 0.369 |
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
### System Info:
|
| 35 |
+
- hf_name: epo-afr
|
| 36 |
+
|
| 37 |
+
- source_languages: epo
|
| 38 |
+
|
| 39 |
+
- target_languages: afr
|
| 40 |
+
|
| 41 |
+
- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/epo-afr/README.md
|
| 42 |
+
|
| 43 |
+
- original_repo: Tatoeba-Challenge
|
| 44 |
+
|
| 45 |
+
- tags: ['translation']
|
| 46 |
+
|
| 47 |
+
- languages: ['eo', 'af']
|
| 48 |
+
|
| 49 |
+
- src_constituents: {'epo'}
|
| 50 |
+
|
| 51 |
+
- tgt_constituents: {'afr'}
|
| 52 |
+
|
| 53 |
+
- src_multilingual: False
|
| 54 |
+
|
| 55 |
+
- tgt_multilingual: False
|
| 56 |
+
|
| 57 |
+
- prepro: normalization + SentencePiece (spm4k,spm4k)
|
| 58 |
+
|
| 59 |
+
- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/epo-afr/opus-2020-06-16.zip
|
| 60 |
+
|
| 61 |
+
- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/epo-afr/opus-2020-06-16.test.txt
|
| 62 |
+
|
| 63 |
+
- src_alpha3: epo
|
| 64 |
+
|
| 65 |
+
- tgt_alpha3: afr
|
| 66 |
+
|
| 67 |
+
- short_pair: eo-af
|
| 68 |
+
|
| 69 |
+
- chrF2_score: 0.369
|
| 70 |
+
|
| 71 |
+
- bleu: 19.5
|
| 72 |
+
|
| 73 |
+
- brevity_penalty: 0.9570000000000001
|
| 74 |
+
|
| 75 |
+
- ref_len: 8432.0
|
| 76 |
+
|
| 77 |
+
- src_name: Esperanto
|
| 78 |
+
|
| 79 |
+
- tgt_name: Afrikaans
|
| 80 |
+
|
| 81 |
+
- train_date: 2020-06-16
|
| 82 |
+
|
| 83 |
+
- src_alpha2: eo
|
| 84 |
+
|
| 85 |
+
- tgt_alpha2: af
|
| 86 |
+
|
| 87 |
+
- prefer_old: False
|
| 88 |
+
|
| 89 |
+
- long_pair: epo-afr
|
| 90 |
+
|
| 91 |
+
- helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
|
| 92 |
+
|
| 93 |
+
- transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
|
| 94 |
+
|
| 95 |
+
- port_machine: brutasse
|
| 96 |
+
|
| 97 |
+
- port_time: 2020-08-21-14:41
|
config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/tmp/Helsinki-NLP/opus-mt-eo-af",
|
| 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 |
+
7474
|
| 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": 7474,
|
| 25 |
+
"decoder_vocab_size": 7475,
|
| 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": 7475,
|
| 33 |
+
"forced_eos_token_id": 0,
|
| 34 |
+
"id2label": {
|
| 35 |
+
"0": "LABEL_0",
|
| 36 |
+
"1": "LABEL_1",
|
| 37 |
+
"2": "LABEL_2"
|
| 38 |
+
},
|
| 39 |
+
"init_std": 0.02,
|
| 40 |
+
"is_encoder_decoder": true,
|
| 41 |
+
"label2id": {
|
| 42 |
+
"LABEL_0": 0,
|
| 43 |
+
"LABEL_1": 1,
|
| 44 |
+
"LABEL_2": 2
|
| 45 |
+
},
|
| 46 |
+
"max_length": 512,
|
| 47 |
+
"max_position_embeddings": 512,
|
| 48 |
+
"model_type": "marian",
|
| 49 |
+
"normalize_before": false,
|
| 50 |
+
"normalize_embedding": false,
|
| 51 |
+
"num_beams": 4,
|
| 52 |
+
"num_hidden_layers": 6,
|
| 53 |
+
"pad_token_id": 7474,
|
| 54 |
+
"scale_embedding": true,
|
| 55 |
+
"share_encoder_decoder_embeddings": true,
|
| 56 |
+
"static_position_embeddings": true,
|
| 57 |
+
"transformers_version": "4.22.0.dev0",
|
| 58 |
+
"use_cache": true,
|
| 59 |
+
"vocab_size": 7475
|
| 60 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bad_words_ids": [
|
| 3 |
+
[
|
| 4 |
+
7474
|
| 5 |
+
]
|
| 6 |
+
],
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"decoder_start_token_id": 7474,
|
| 9 |
+
"eos_token_id": 0,
|
| 10 |
+
"forced_eos_token_id": 0,
|
| 11 |
+
"max_length": 512,
|
| 12 |
+
"num_beams": 4,
|
| 13 |
+
"pad_token_id": 7474,
|
| 14 |
+
"renormalize_logits": true,
|
| 15 |
+
"transformers_version": "4.32.0.dev0"
|
| 16 |
+
}
|
metadata.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"hf_name":"epo-afr","source_languages":"epo","target_languages":"afr","opus_readme_url":"https:\/\/github.com\/Helsinki-NLP\/Tatoeba-Challenge\/tree\/master\/models\/epo-afr\/README.md","original_repo":"Tatoeba-Challenge","tags":["translation"],"languages":["eo","af"],"src_constituents":["epo"],"tgt_constituents":["afr"],"src_multilingual":false,"tgt_multilingual":false,"prepro":" normalization + SentencePiece (spm4k,spm4k)","url_model":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/epo-afr\/opus-2020-06-16.zip","url_test_set":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/epo-afr\/opus-2020-06-16.test.txt","src_alpha3":"epo","tgt_alpha3":"afr","short_pair":"eo-af","chrF2_score":0.369,"bleu":19.5,"brevity_penalty":0.957,"ref_len":8432.0,"src_name":"Esperanto","tgt_name":"Afrikaans","train_date":"2020-06-16","src_alpha2":"eo","tgt_alpha2":"af","prefer_old":false,"long_pair":"epo-afr","helsinki_git_sha":"480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535","transformers_git_sha":"2207e5d8cb224e954a7cba69fa4ac2309e9ff30b","port_machine":"brutasse","port_time":"2020-08-21-14:41"}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f58114cac41b12750ea16063ac48f286315726cd0958f3e92ccbdd256263e18c
|
| 3 |
+
size 194043657
|
source.spm
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d82af69a5b53e5dd92d744e7ad98bd4658e62eee2e245bb438d8484aa97fe74a
|
| 3 |
+
size 304479
|
target.spm
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f958c6340c87c2f683c3671ab8e81f4b635e51e0a15ddb5ccf0028cea56b0a29
|
| 3 |
+
size 304596
|
tf_model.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca0d62f800d4411aed4ccd80a621ae3613f0be0a6f5ab5fa1543002dd887c41b
|
| 3 |
+
size 194307144
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"target_lang": "afr", "source_lang": "epo"}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|