Add initial files.
Browse files- .gitattributes +1 -0
- config.json +44 -0
- generation_config.json +16 -0
- pytorch_model.bin +3 -0
- source.spm +3 -0
- special_tokens_map.json +5 -0
- target.spm +3 -0
- tokenizer_config.json +11 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
*.spm filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_dropout":0.0,
|
3 |
+
"activation_function":"swish",
|
4 |
+
"architectures":[
|
5 |
+
"MarianMTModel"
|
6 |
+
],
|
7 |
+
"attention_dropout":0.0,
|
8 |
+
"bad_words_ids":[
|
9 |
+
[
|
10 |
+
50000
|
11 |
+
]
|
12 |
+
],
|
13 |
+
"bos_token_id":0,
|
14 |
+
"d_model":512,
|
15 |
+
"decoder_attention_heads":8,
|
16 |
+
"decoder_ffn_dim":2048,
|
17 |
+
"decoder_layerdrop":0.0,
|
18 |
+
"decoder_layers":6,
|
19 |
+
"decoder_start_token_id":50000,
|
20 |
+
"decoder_vocab_size":50001,
|
21 |
+
"dropout":0.1,
|
22 |
+
"encoder_attention_heads":8,
|
23 |
+
"encoder_ffn_dim":2048,
|
24 |
+
"encoder_layerdrop":0.0,
|
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":6,
|
35 |
+
"num_hidden_layers":6,
|
36 |
+
"pad_token_id":50000,
|
37 |
+
"scale_embedding":true,
|
38 |
+
"share_encoder_decoder_embeddings":true,
|
39 |
+
"static_position_embeddings":true,
|
40 |
+
"torch_dtype":"float32",
|
41 |
+
"transformers_version":"4.28.1",
|
42 |
+
"use_cache":true,
|
43 |
+
"vocab_size":50001
|
44 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config":true,
|
3 |
+
"bad_words_ids":[
|
4 |
+
[
|
5 |
+
50000
|
6 |
+
]
|
7 |
+
],
|
8 |
+
"bos_token_id":0,
|
9 |
+
"decoder_start_token_id":50000,
|
10 |
+
"eos_token_id":0,
|
11 |
+
"forced_eos_token_id":0,
|
12 |
+
"max_length":512,
|
13 |
+
"num_beams":6,
|
14 |
+
"pad_token_id":50000,
|
15 |
+
"transformers_version":"4.28.1"
|
16 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89ce59f89b975bc8276ac28a996b5491bb43cba7d683bef2135c15bf490331cb
|
3 |
+
size 279238981
|
source.spm
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42ae7eebaf272a647188da19cc42afa89e92f1abe12a07693d2824cdfe99d694
|
3 |
+
size 1161734
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token":"</s>",
|
3 |
+
"pad_token":"<pad>",
|
4 |
+
"unk_token":"<unk>"
|
5 |
+
}
|
target.spm
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42ae7eebaf272a647188da19cc42afa89e92f1abe12a07693d2824cdfe99d694
|
3 |
+
size 1161734
|
tokenizer_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces":true,
|
3 |
+
"eos_token":"</s>",
|
4 |
+
"model_max_length":512,
|
5 |
+
"pad_token":"<pad>",
|
6 |
+
"separate_vocabs":false,
|
7 |
+
"source_lang":"cy",
|
8 |
+
"target_lang":"en",
|
9 |
+
"tokenizer_class":"MarianTokenizer",
|
10 |
+
"unk_token":"<unk>"
|
11 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|