gsarti commited on
Commit
2df3a1d
1 Parent(s): 6d20b61

Initial commit

Browse files
Files changed (7) hide show
  1. README.md +23 -0
  2. config.json +37 -0
  3. merges.txt +0 -0
  4. pytorch_model.bin +3 -0
  5. tokenizer_config.json +8 -0
  6. vocab-src.json +0 -0
  7. vocab-tgt.json +0 -0
README.md CHANGED
@@ -1,3 +1,26 @@
1
  ---
 
 
 
 
2
  license: cc-by-sa-4.0
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
1
  ---
2
+ language:
3
+ - en
4
+ - zh
5
+ - multilingual
6
  license: cc-by-sa-4.0
7
+ tags:
8
+ - translation
9
+ - wmt20
10
+ datasets:
11
+ - wmt/news-commentary
12
+ - wmt/wikititles
13
+ - wmt/uncorpus
14
+ widget:
15
+ - text: "飓风黛安源于1955年8月7日小安的列斯群岛和佛得角之间的一股东风波。8月12日,达到持续风速每小时195公里的最高强度。"
16
+ - text: "中华人民共和国哪家制药公司研发出中国首个具有全球知识产权的单克隆抗体?"
17
+ - text: "世界遺產委員會決定將乌克兰敖德萨历史中心、也门示巴古國地标建筑及黎巴嫩拉希德·卡拉米國際會展中心等3個項目新增至联合国教科文组织《世界遺產名錄》,同時列入《濒危世界遗产名录》。"
18
  ---
19
+
20
+ # Fairseq Zh-En NMT WMT20 MLQE
21
+
22
+ This repository contains the English-German model trained with the [fairseq toolkit](https://github.com/pytorch/fairseq) that was used to produce translations used in the WMT20 shared task on quality estimation (QE) on the [MLQE dataset](https://github.com/facebookresearch/mlqe).
23
+
24
+ The checkpoint was converted from the original fairseq checkpoint available [here](https://github.com/facebookresearch/mlqe/tree/master/nmt_models) using the `convert_fsmt_original_pytorch_checkpoint_to_pytorch.py` script from the 🤗 Transformers library (v4.26.0).
25
+
26
+ Please refer to the repositories linked above for additional information on usage, parameters and training data
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "FSMTForConditionalGeneration"
4
+ ],
5
+ "model_type": "fsmt",
6
+ "activation_dropout": 0.0,
7
+ "activation_function": "relu",
8
+ "attention_dropout": 0.0,
9
+ "d_model": 512,
10
+ "dropout": 0.3,
11
+ "init_std": 0.02,
12
+ "max_position_embeddings": 1024,
13
+ "num_hidden_layers": 6,
14
+ "src_vocab_size": 29640,
15
+ "tgt_vocab_size": 54648,
16
+ "langs": [
17
+ "en",
18
+ "zh"
19
+ ],
20
+ "encoder_attention_heads": 8,
21
+ "encoder_ffn_dim": 2048,
22
+ "encoder_layerdrop": 0,
23
+ "encoder_layers": 6,
24
+ "decoder_attention_heads": 8,
25
+ "decoder_ffn_dim": 2048,
26
+ "decoder_layerdrop": 0,
27
+ "decoder_layers": 6,
28
+ "bos_token_id": 0,
29
+ "pad_token_id": 1,
30
+ "eos_token_id": 2,
31
+ "is_encoder_decoder": true,
32
+ "scale_embedding": true,
33
+ "tie_word_embeddings": false,
34
+ "num_beams": 5,
35
+ "early_stopping": false,
36
+ "length_penalty": 1.0
37
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe4c5322a8d32a3699fd010cacb5ba0155f700d6b7bff602d7319f65b4acfaa6
3
+ size 424881925
tokenizer_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "langs": [
3
+ "en",
4
+ "zh"
5
+ ],
6
+ "model_max_length": 1024,
7
+ "do_lower_case": false
8
+ }
vocab-src.json ADDED
The diff for this file is too large to render. See raw diff
 
vocab-tgt.json ADDED
The diff for this file is too large to render. See raw diff