Upload 8 files
Browse files- .gitattributes +2 -0
- added_tokens.json +4 -0
- config.json +42 -0
- generation_config.json +16 -0
- source.spm +3 -0
- special_tokens_map.json +21 -0
- target.spm +3 -0
- tokenizer_config.json +11 -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
|
added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
">>fil<<": 59760,
|
| 3 |
+
">>pam<<": 59761
|
| 4 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Helsinki-NLP/opus-mt-tc-bible-big-phi-deu_eng_fra_por_spa",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "relu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"MarianMTModel"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"bos_token_id": 0,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"d_model": 1024,
|
| 12 |
+
"decoder_attention_heads": 16,
|
| 13 |
+
"decoder_ffn_dim": 4096,
|
| 14 |
+
"decoder_layerdrop": 0.0,
|
| 15 |
+
"decoder_layers": 6,
|
| 16 |
+
"decoder_start_token_id": 59759,
|
| 17 |
+
"decoder_vocab_size": 59762,
|
| 18 |
+
"dropout": 0.1,
|
| 19 |
+
"encoder_attention_heads": 16,
|
| 20 |
+
"encoder_ffn_dim": 4096,
|
| 21 |
+
"encoder_layerdrop": 0.0,
|
| 22 |
+
"encoder_layers": 6,
|
| 23 |
+
"eos_token_id": 355,
|
| 24 |
+
"forced_eos_token_id": null,
|
| 25 |
+
"init_std": 0.02,
|
| 26 |
+
"is_encoder_decoder": true,
|
| 27 |
+
"max_length": null,
|
| 28 |
+
"max_position_embeddings": 1024,
|
| 29 |
+
"model_type": "marian",
|
| 30 |
+
"normalize_embedding": false,
|
| 31 |
+
"num_beams": null,
|
| 32 |
+
"num_hidden_layers": 6,
|
| 33 |
+
"pad_token_id": 59759,
|
| 34 |
+
"scale_embedding": true,
|
| 35 |
+
"share_encoder_decoder_embeddings": true,
|
| 36 |
+
"static_position_embeddings": true,
|
| 37 |
+
"target_lang": "deu+eng+fra+por+spa+fil+pam",
|
| 38 |
+
"torch_dtype": "float32",
|
| 39 |
+
"transformers_version": "4.49.0",
|
| 40 |
+
"use_cache": true,
|
| 41 |
+
"vocab_size": 59762
|
| 42 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bad_words_ids": [
|
| 4 |
+
[
|
| 5 |
+
59759
|
| 6 |
+
]
|
| 7 |
+
],
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"decoder_start_token_id": 59759,
|
| 10 |
+
"eos_token_id": 355,
|
| 11 |
+
"forced_eos_token_id": 355,
|
| 12 |
+
"max_length": 512,
|
| 13 |
+
"num_beams": 4,
|
| 14 |
+
"pad_token_id": 59759,
|
| 15 |
+
"transformers_version": "4.45.1"
|
| 16 |
+
}
|
source.spm
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0faae32b9b3446cb1b85c2c18ae3888f20b2461f64dbe4d335ae2d3cdf3f6766
|
| 3 |
+
size 787583
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": ">>fil<<",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": ">>pam<<",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
}
|
| 17 |
+
],
|
| 18 |
+
"eos_token": "</s>",
|
| 19 |
+
"pad_token": "<pad>",
|
| 20 |
+
"unk_token": "<unk>"
|
| 21 |
+
}
|
target.spm
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b3ef4bd2511e5b6a4a7ffda8a7c387ba0e670061b874537d4d7ae16cfd8bcb4
|
| 3 |
+
size 811703
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"source_lang": "phi+fil+pam",
|
| 3 |
+
"target_lang": "deu+eng+fra+por+spa+fil+pam",
|
| 4 |
+
"unk_token": "<unk>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"model_max_length": 512,
|
| 8 |
+
"sp_model_kwargs": {},
|
| 9 |
+
"separate_vocabs": false,
|
| 10 |
+
"name_or_path": "./pam-fil-bidirectional-model/final"
|
| 11 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|