sneakyfree commited on
Commit
ed8520c
·
verified ·
1 Parent(s): 21d88b3

upstream-archive byte-perfect snapshot of Helsinki-NLP/opus-mt-cus-en (ADR-039 Phase D)

Browse files
.gitattributes CHANGED
@@ -1,35 +1,11 @@
1
- *.7z filter=lfs diff=lfs merge=lfs -text
2
- *.arrow filter=lfs diff=lfs merge=lfs -text
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
- *.tgz filter=lfs diff=lfs merge=lfs -text
31
- *.wasm filter=lfs diff=lfs merge=lfs -text
32
- *.xz filter=lfs diff=lfs merge=lfs -text
33
- *.zip filter=lfs diff=lfs merge=lfs -text
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
+ model.safetensors filter=lfs diff=lfs merge=lfs -text
10
+ source.spm filter=lfs diff=lfs merge=lfs -text
11
+ target.spm filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - so
4
+ - cus
5
+ - en
6
+
7
+ tags:
8
+ - translation
9
+
10
+ license: apache-2.0
11
+ ---
12
+
13
+ ### cus-eng
14
+
15
+ * source group: Cushitic languages
16
+ * target group: English
17
+ * OPUS readme: [cus-eng](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/cus-eng/README.md)
18
+
19
+ * model: transformer
20
+ * source language(s): som
21
+ * target language(s): eng
22
+ * model: transformer
23
+ * pre-processing: normalization + SentencePiece (spm12k,spm12k)
24
+ * download original weights: [opus-2020-07-26.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/cus-eng/opus-2020-07-26.zip)
25
+ * test set translations: [opus-2020-07-26.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/cus-eng/opus-2020-07-26.test.txt)
26
+ * test set scores: [opus-2020-07-26.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/cus-eng/opus-2020-07-26.eval.txt)
27
+
28
+ ## Benchmarks
29
+
30
+ | testset | BLEU | chr-F |
31
+ |-----------------------|-------|-------|
32
+ | Tatoeba-test.multi.eng | 16.2 | 0.303 |
33
+ | Tatoeba-test.som-eng.som.eng | 16.2 | 0.303 |
34
+
35
+
36
+ ### System Info:
37
+ - hf_name: cus-eng
38
+
39
+ - source_languages: cus
40
+
41
+ - target_languages: eng
42
+
43
+ - opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/cus-eng/README.md
44
+
45
+ - original_repo: Tatoeba-Challenge
46
+
47
+ - tags: ['translation']
48
+
49
+ - languages: ['so', 'cus', 'en']
50
+
51
+ - src_constituents: {'som'}
52
+
53
+ - tgt_constituents: {'eng'}
54
+
55
+ - src_multilingual: True
56
+
57
+ - tgt_multilingual: False
58
+
59
+ - prepro: normalization + SentencePiece (spm12k,spm12k)
60
+
61
+ - url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/cus-eng/opus-2020-07-26.zip
62
+
63
+ - url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/cus-eng/opus-2020-07-26.test.txt
64
+
65
+ - src_alpha3: cus
66
+
67
+ - tgt_alpha3: eng
68
+
69
+ - short_pair: cus-en
70
+
71
+ - chrF2_score: 0.303
72
+
73
+ - bleu: 16.2
74
+
75
+ - brevity_penalty: 1.0
76
+
77
+ - ref_len: 3.0
78
+
79
+ - src_name: Cushitic languages
80
+
81
+ - tgt_name: English
82
+
83
+ - train_date: 2020-07-26
84
+
85
+ - src_alpha2: cus
86
+
87
+ - tgt_alpha2: en
88
+
89
+ - prefer_old: False
90
+
91
+ - long_pair: cus-eng
92
+
93
+ - helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
94
+
95
+ - transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
96
+
97
+ - port_machine: brutasse
98
+
99
+ - port_time: 2020-08-21-14:41
config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/tmp/Helsinki-NLP/opus-mt-cus-en",
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
+ 23374
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": 23374,
25
+ "decoder_vocab_size": 23375,
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": 23375,
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": 23374,
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": 23375
60
+ }
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 23374
5
+ ]
6
+ ],
7
+ "bos_token_id": 0,
8
+ "decoder_start_token_id": 23374,
9
+ "eos_token_id": 0,
10
+ "forced_eos_token_id": 0,
11
+ "max_length": 512,
12
+ "num_beams": 4,
13
+ "pad_token_id": 23374,
14
+ "renormalize_logits": true,
15
+ "transformers_version": "4.32.0.dev0"
16
+ }
metadata.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"hf_name":"cus-eng","source_languages":"cus","target_languages":"eng","opus_readme_url":"https:\/\/github.com\/Helsinki-NLP\/Tatoeba-Challenge\/tree\/master\/models\/cus-eng\/README.md","original_repo":"Tatoeba-Challenge","tags":["translation"],"languages":["so","cus","en"],"src_constituents":["som"],"tgt_constituents":["eng"],"src_multilingual":true,"tgt_multilingual":false,"prepro":" normalization + SentencePiece (spm12k,spm12k)","url_model":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/cus-eng\/opus-2020-07-26.zip","url_test_set":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/cus-eng\/opus-2020-07-26.test.txt","src_alpha3":"cus","tgt_alpha3":"eng","short_pair":"cus-en","chrF2_score":0.303,"bleu":16.2,"brevity_penalty":1.0,"ref_len":3.0,"src_name":"Cushitic languages","tgt_name":"English","train_date":"2020-07-26","src_alpha2":"cus","tgt_alpha2":"en","prefer_old":false,"long_pair":"cus-eng","helsinki_git_sha":"480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535","transformers_git_sha":"2207e5d8cb224e954a7cba69fa4ac2309e9ff30b","port_machine":"brutasse","port_time":"2020-08-21-14:41"}
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dead6180c93b24191ec73f46dfd6c79bcf2c19f68934a3efb4ecf19ec62d056
3
+ size 226646028
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11a2e3fe4c98bcbe892823c436baaa9e3c0af00ac5d86146ca3bdd79b7a28292
3
+ size 226670457
source.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38df7718566f354da8d0b0a91aaf7adb45db623c3de934f324d35c178ed8e22a
3
+ size 453945
target.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cac993f533fd57d4f0eee80f05406ccae3d463ff1f2968077420d76d295f8b23
3
+ size 450961
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b7914aa39513a1c52b2ad8ee202eef11078f259c3d0d49384872d1533b3ef33
3
+ size 226997544
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"target_lang": "eng", "source_lang": "cus"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff