mohamedtolba
commited on
Commit
•
2f54a14
1
Parent(s):
c4a89fb
End of training
Browse files- .gitattributes +2 -0
- .gitignore +1 -0
- config.json +46 -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 +12 -0
- training_args.bin +3 -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
|
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Helsinki-NLP/opus-mt-tc-big-en-ar",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "relu",
|
5 |
+
"architectures": [
|
6 |
+
"MarianMTModel"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"bad_words_ids": [
|
10 |
+
[
|
11 |
+
61246
|
12 |
+
]
|
13 |
+
],
|
14 |
+
"bos_token_id": 0,
|
15 |
+
"classifier_dropout": 0.0,
|
16 |
+
"d_model": 1024,
|
17 |
+
"decoder_attention_heads": 16,
|
18 |
+
"decoder_ffn_dim": 4096,
|
19 |
+
"decoder_layerdrop": 0.0,
|
20 |
+
"decoder_layers": 6,
|
21 |
+
"decoder_start_token_id": 61246,
|
22 |
+
"decoder_vocab_size": 61247,
|
23 |
+
"dropout": 0.1,
|
24 |
+
"encoder_attention_heads": 16,
|
25 |
+
"encoder_ffn_dim": 4096,
|
26 |
+
"encoder_layerdrop": 0.0,
|
27 |
+
"encoder_layers": 6,
|
28 |
+
"eos_token_id": 25897,
|
29 |
+
"forced_eos_token_id": 25897,
|
30 |
+
"init_std": 0.02,
|
31 |
+
"is_encoder_decoder": true,
|
32 |
+
"max_length": 512,
|
33 |
+
"max_position_embeddings": 1024,
|
34 |
+
"model_type": "marian",
|
35 |
+
"normalize_embedding": false,
|
36 |
+
"num_beams": 4,
|
37 |
+
"num_hidden_layers": 6,
|
38 |
+
"pad_token_id": 61246,
|
39 |
+
"scale_embedding": true,
|
40 |
+
"share_encoder_decoder_embeddings": true,
|
41 |
+
"static_position_embeddings": true,
|
42 |
+
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.31.0",
|
44 |
+
"use_cache": true,
|
45 |
+
"vocab_size": 61247
|
46 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bad_words_ids": [
|
3 |
+
[
|
4 |
+
61246
|
5 |
+
]
|
6 |
+
],
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"decoder_start_token_id": 61246,
|
9 |
+
"eos_token_id": 25897,
|
10 |
+
"forced_eos_token_id": 25897,
|
11 |
+
"max_length": 512,
|
12 |
+
"num_beams": 4,
|
13 |
+
"pad_token_id": 61246,
|
14 |
+
"renormalize_logits": true,
|
15 |
+
"transformers_version": "4.31.0"
|
16 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad7c7f46d5f906a1cd12ae6b400a4850806e5d48112bfbfcdfbe5ad4c70b1f78
|
3 |
+
size 956628741
|
source.spm
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a9b220e324e29d4fbab530747ab82968a79d5408f1b3210f0f6d812d148b7d2
|
3 |
+
size 806127
|
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:db09c46631638384f2b13ccdececb1c88103f0e59c14d5def247975007e7eaac
|
3 |
+
size 916373
|
tokenizer_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "en",
|
8 |
+
"sp_model_kwargs": {},
|
9 |
+
"target_lang": "ar",
|
10 |
+
"tokenizer_class": "MarianTokenizer",
|
11 |
+
"unk_token": "<unk>"
|
12 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:357506e89a33cc7ea477e0feff94642e41c80f933a0c2fd536688d00b1170fd1
|
3 |
+
size 4155
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|