Normal1919 commited on
Commit
1207d8f
1 Parent(s): af9898c

Upload 8 files

Browse files
config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "E:\\PycharmProjects\\dl_models\\opus-mt-en-zh",
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
+ "do_blenderbot_90_layernorm": false,
27
+ "dropout": 0.1,
28
+ "encoder_attention_heads": 8,
29
+ "encoder_ffn_dim": 2048,
30
+ "encoder_layerdrop": 0.0,
31
+ "encoder_layers": 6,
32
+ "eos_token_id": 0,
33
+ "extra_pos_embeddings": 0,
34
+ "force_bos_token_to_be_generated": false,
35
+ "forced_eos_token_id": 0,
36
+ "gradient_checkpointing": false,
37
+ "id2label": {
38
+ "0": "LABEL_0",
39
+ "1": "LABEL_1",
40
+ "2": "LABEL_2"
41
+ },
42
+ "init_std": 0.02,
43
+ "is_encoder_decoder": true,
44
+ "label2id": {
45
+ "LABEL_0": 0,
46
+ "LABEL_1": 1,
47
+ "LABEL_2": 2
48
+ },
49
+ "max_length": 512,
50
+ "max_position_embeddings": 512,
51
+ "model_type": "marian",
52
+ "normalize_before": false,
53
+ "normalize_embedding": false,
54
+ "num_beams": 4,
55
+ "num_hidden_layers": 6,
56
+ "pad_token_id": 65000,
57
+ "scale_embedding": true,
58
+ "share_encoder_decoder_embeddings": true,
59
+ "static_position_embeddings": true,
60
+ "torch_dtype": "float32",
61
+ "transformers_version": "4.31.0",
62
+ "use_cache": true,
63
+ "vocab_size": 65001
64
+ }
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": "4.31.0"
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"}
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c637c9315499fbc65f1c8be79feb87379a3529fda33c50521aadbff9bad8230f
3
+ size 310018949
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