Upload 7 files
Browse files- .gitattributes +2 -0
- config.json +44 -0
- source.spm +3 -0
- special_tokens_map.json +23 -0
- target.spm +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +39 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,5 @@ saved_model/**/* 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
|
|
|
|
|
|
|
|
|
| 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
|
| 36 |
+
source.spm filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
target.spm filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0,
|
| 3 |
+
"activation_function": "swish",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"MarianMTModel"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0,
|
| 8 |
+
"bad_words_ids": [
|
| 9 |
+
[
|
| 10 |
+
32000
|
| 11 |
+
]
|
| 12 |
+
],
|
| 13 |
+
"bos_token_id": 0,
|
| 14 |
+
"d_model": 512,
|
| 15 |
+
"decoder_attention_heads": 8,
|
| 16 |
+
"decoder_ffn_dim": 2048,
|
| 17 |
+
"decoder_layerdrop": 0,
|
| 18 |
+
"decoder_layers": 6,
|
| 19 |
+
"decoder_start_token_id": 32000,
|
| 20 |
+
"decoder_vocab_size": 32001,
|
| 21 |
+
"dropout": 0.1,
|
| 22 |
+
"encoder_attention_heads": 8,
|
| 23 |
+
"encoder_ffn_dim": 2048,
|
| 24 |
+
"encoder_layerdrop": 0,
|
| 25 |
+
"encoder_layers": 6,
|
| 26 |
+
"eos_token_id": 0,
|
| 27 |
+
"forced_eos_token_id": 0,
|
| 28 |
+
"init_std": 0.02,
|
| 29 |
+
"is_encoder_decoder": true,
|
| 30 |
+
"max_length": 512,
|
| 31 |
+
"max_position_embeddings": 512,
|
| 32 |
+
"model_type": "marian",
|
| 33 |
+
"normalize_embedding": false,
|
| 34 |
+
"num_beams": 4,
|
| 35 |
+
"num_hidden_layers": 6,
|
| 36 |
+
"pad_token_id": 32000,
|
| 37 |
+
"scale_embedding": true,
|
| 38 |
+
"share_encoder_decoder_embeddings": true,
|
| 39 |
+
"static_position_embeddings": true,
|
| 40 |
+
"torch_dtype": "float16",
|
| 41 |
+
"transformers_version": "4.40.2",
|
| 42 |
+
"use_cache": true,
|
| 43 |
+
"vocab_size": 32001
|
| 44 |
+
}
|
source.spm
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6824c2996a4877cae8a0240f11a112ab0e4ea1f22e54cd42179376fe558f4ff
|
| 3 |
+
size 792751
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": {
|
| 3 |
+
"content": "</s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"pad_token": {
|
| 10 |
+
"content": "<pad>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
target.spm
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6824c2996a4877cae8a0240f11a112ab0e4ea1f22e54cd42179376fe558f4ff
|
| 3 |
+
size 792751
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "</s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<unk>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"32000": {
|
| 20 |
+
"content": "<pad>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"clean_up_tokenization_spaces": true,
|
| 29 |
+
"eos_token": "</s>",
|
| 30 |
+
"extra_special_tokens": {},
|
| 31 |
+
"model_max_length": 512,
|
| 32 |
+
"pad_token": "<pad>",
|
| 33 |
+
"separate_vocabs": false,
|
| 34 |
+
"source_lang": "ja",
|
| 35 |
+
"sp_model_kwargs": {},
|
| 36 |
+
"target_lang": "en",
|
| 37 |
+
"tokenizer_class": "MarianTokenizer",
|
| 38 |
+
"unk_token": "<unk>"
|
| 39 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|