ww
commited on
Commit
·
ae1315a
1
Parent(s):
d5fa626
- config.json +60 -0
- metadata.json +1 -0
- source.spm +0 -0
- target.spm +0 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/tmp/Helsinki-NLP/opus-mt-zh-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 |
+
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 |
+
"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": 6,
|
52 |
+
"num_hidden_layers": 6,
|
53 |
+
"pad_token_id": 65000,
|
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": 65001
|
60 |
+
}
|
metadata.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"hf_name":"zho-eng","source_languages":"zho","target_languages":"eng","opus_readme_url":"https:\/\/github.com\/Helsinki-NLP\/Tatoeba-Challenge\/tree\/master\/models\/zho-eng\/README.md","original_repo":"Tatoeba-Challenge","tags":["translation"],"languages":["zh","en"],"src_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"],"tgt_constituents":["eng"],"src_multilingual":false,"tgt_multilingual":false,"prepro":" normalization + SentencePiece (spm32k,spm32k)","url_model":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/zho-eng\/opus-2020-07-17.zip","url_test_set":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/zho-eng\/opus-2020-07-17.test.txt","src_alpha3":"zho","tgt_alpha3":"eng","short_pair":"zh-en","chrF2_score":0.548,"bleu":36.1,"brevity_penalty":0.948,"ref_len":82826.0,"src_name":"Chinese","tgt_name":"English","train_date":"2020-07-17","src_alpha2":"zh","tgt_alpha2":"en","prefer_old":false,"long_pair":"zho-eng","helsinki_git_sha":"480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535","transformers_git_sha":"2207e5d8cb224e954a7cba69fa4ac2309e9ff30b","port_machine":"brutasse","port_time":"2020-08-21-14:41"}
|
source.spm
ADDED
Binary file (805 kB). View file
|
|
target.spm
ADDED
Binary file (807 kB). View file
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"target_lang": "eng", "source_lang": "zho"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|