johnsonwa84 commited on
Commit
9e8cdca
·
verified ·
1 Parent(s): 5d6b82e

Upload 8 files

Browse files
.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
+ Helsinki-en-es-SpanglishFT/source.spm filter=lfs diff=lfs merge=lfs -text
37
+ Helsinki-en-es-SpanglishFT/target.spm filter=lfs diff=lfs merge=lfs -text
Helsinki-en-es-SpanglishFT/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-en-es",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "swish",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "MarianMTModel"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.0,
13
+ "classifier_dropout": 0.0,
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": 65000,
20
+ "decoder_vocab_size": 65001,
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
+ "extra_pos_embeddings": 65001,
28
+ "force_bos_token_to_be_generated": false,
29
+ "forced_eos_token_id": 0,
30
+ "gradient_checkpointing": false,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1",
34
+ "2": "LABEL_2"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_encoder_decoder": true,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_2": 2
42
+ },
43
+ "max_length": null,
44
+ "max_position_embeddings": 512,
45
+ "model_type": "marian",
46
+ "normalize_before": false,
47
+ "normalize_embedding": false,
48
+ "num_beams": null,
49
+ "num_hidden_layers": 6,
50
+ "pad_token_id": 65000,
51
+ "scale_embedding": true,
52
+ "share_encoder_decoder_embeddings": true,
53
+ "static_position_embeddings": true,
54
+ "torch_dtype": "float32",
55
+ "transformers_version": "4.49.0",
56
+ "use_cache": true,
57
+ "vocab_size": 65001
58
+ }
Helsinki-en-es-SpanglishFT/generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 65000
5
+ ]
6
+ ],
7
+ "bos_token_id": 0,
8
+ "decoder_start_token_id": 65000,
9
+ "eos_token_id": 0,
10
+ "forced_eos_token_id": 0,
11
+ "max_length": 512,
12
+ "num_beams": 4,
13
+ "pad_token_id": 65000,
14
+ "renormalize_logits": true,
15
+ "transformers_version": "4.49.0"
16
+ }
Helsinki-en-es-SpanglishFT/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48a2b4798ae9d424cbfbac535258ec1ea78a857956b5c7601458768db61b005c
3
+ size 309965092
Helsinki-en-es-SpanglishFT/source.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dd547c24816a335e7b0b2e63376a8f1b3cbfc671eda5ab808dd44fdadaa8791
3
+ size 801636
Helsinki-en-es-SpanglishFT/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
Helsinki-en-es-SpanglishFT/target.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e236ee6d866b635c0142114f8647f39831f9d92534aa2aad75c942f6a78ad0e3
3
+ size 825924
Helsinki-en-es-SpanglishFT/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
+ "65000": {
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": false,
29
+ "eos_token": "</s>",
30
+ "extra_special_tokens": {},
31
+ "model_max_length": 512,
32
+ "pad_token": "<pad>",
33
+ "separate_vocabs": false,
34
+ "source_lang": "eng",
35
+ "sp_model_kwargs": {},
36
+ "target_lang": "spa",
37
+ "tokenizer_class": "MarianTokenizer",
38
+ "unk_token": "<unk>"
39
+ }
Helsinki-en-es-SpanglishFT/vocab.json ADDED
The diff for this file is too large to render. See raw diff