ronghua commited on
Commit
a414f2d
1 Parent(s): 2fe2075

Upload 9 files

Browse files
Files changed (8) hide show
  1. .gitattributes +6 -32
  2. config.json +61 -0
  3. generation_config.json +16 -0
  4. metadata.json +1 -0
  5. source.spm +0 -0
  6. target.spm +0 -0
  7. tokenizer_config.json +1 -0
  8. vocab.json +0 -0
.gitattributes CHANGED
@@ -1,35 +1,9 @@
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
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
 
 
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./",
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
+ "do_blenderbot_90_layernorm": false,
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": 0,
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
+ "static_position_embeddings": true,
58
+ "transformers_version": "4.9.0.dev0",
59
+ "use_cache": true,
60
+ "vocab_size": 65001
61
+ }
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-zho","source_languages":"eng","target_languages":"zho","opus_readme_url":"https:\/\/github.com\/Helsinki-NLP\/Tatoeba-Challenge\/tree\/master\/models\/eng-zho\/README.md","original_repo":"Tatoeba-Challenge","tags":["translation"],"languages":["en","zh"],"src_constituents":["eng"],"tgt_constituents":["cmn_Hans","nan","nan_Hani","gan","yue","cmn_Kana","yue_Hani","wuu_Bopo","cmn_Latn","yue_Hira","cmn_Hani","cjy_Hans","cmn","lzh_Hang","lzh_Hira","cmn_Hant","lzh_Bopo","zho","zho_Hans","zho_Hant","lzh_Hani","yue_Hang","wuu","yue_Kana","wuu_Latn","yue_Bopo","cjy_Hant","yue_Hans","lzh","cmn_Hira","lzh_Yiii","lzh_Hans","cmn_Bopo","cmn_Hang","hak_Hani","cmn_Yiii","yue_Hant","lzh_Kana","wuu_Hani"],"src_multilingual":false,"tgt_multilingual":false,"prepro":" normalization + SentencePiece (spm32k,spm32k)","url_model":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/eng-zho\/opus-2020-07-17.zip","url_test_set":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/eng-zho\/opus-2020-07-17.test.txt","src_alpha3":"eng","tgt_alpha3":"zho","short_pair":"en-zh","chrF2_score":0.268,"bleu":31.4,"brevity_penalty":0.896,"ref_len":110468.0,"src_name":"English","tgt_name":"Chinese","train_date":"2020-07-17","src_alpha2":"en","tgt_alpha2":"zh","prefer_old":false,"long_pair":"eng-zho","helsinki_git_sha":"480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535","transformers_git_sha":"2207e5d8cb224e954a7cba69fa4ac2309e9ff30b","port_machine":"brutasse","port_time":"2020-08-21-14:41"}
source.spm ADDED
Binary file (806 kB). View file
 
target.spm ADDED
Binary file (805 kB). View file
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"target_lang": "zho", "source_lang": "eng"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff