valhalla commited on
Commit
2c055e1
1 Parent(s): df825c3
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/suraj/wmt21-checkpoints/wmt21-dense-24-wide-en-x",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "architectures": [
6
+ "M2M100ForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 0,
10
+ "d_model": 2048,
11
+ "decoder_attention_heads": 32,
12
+ "decoder_ffn_dim": 16384,
13
+ "decoder_layerdrop": 0,
14
+ "decoder_layers": 24,
15
+ "decoder_start_token_id": 2,
16
+ "dropout": 0.1,
17
+ "encoder_attention_heads": 32,
18
+ "encoder_ffn_dim": 16384,
19
+ "encoder_layerdrop": 0,
20
+ "encoder_layers": 24,
21
+ "eos_token_id": 2,
22
+ "init_std": 0.02,
23
+ "is_encoder_decoder": true,
24
+ "max_length": 200,
25
+ "max_position_embeddings": 1024,
26
+ "model_type": "m2m_100",
27
+ "num_beams": 5,
28
+ "num_hidden_layers": 24,
29
+ "pad_token_id": 1,
30
+ "scale_embedding": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.13.0.dev0",
33
+ "use_cache": true,
34
+ "vocab_size": 128009
35
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cfe907d6495809a367440273e123b51f2fce265285fa0e113b2521a63a8d33b
3
+ size 18773661472
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfa7dae3b7caabbdfd569cc48edc55283b31a6a56a3befb699bc7b9526961f77
3
+ size 2585112
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "additional_special_tokens": ["__en__", "__ha__", "__is__", "__ja__", "__cs__", "__ru__", "__zh__", "__de__"]}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"src_lang": "en", "tgt_lang": null, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "sp_model_kwargs": {}, "language_codes": "wmt21", "num_madeup_words": 0, "additional_special_tokens": ["__en__", "__ha__", "__is__", "__ja__", "__cs__", "__ru__", "__zh__", "__de__"], "tokenizer_class": "M2M100Tokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff