Hugging Face's logo

Darsala
/
Georgian-Translation

Translation
Safetensors
Georgian
English
encoder-decoder
Georgian
NMT
MT
Eval Results
Model card Files
xet
Community
Darsala commited on
Commit
45cf465
·
verified ·
1 Parent(s): 63d0cff

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. config.json +58 -0
  2. decoder/special_tokens_map.json +39 -0
  3. decoder/tokenizer.json +0 -0
  4. decoder/tokenizer_config.json +58 -0
  5. decoder/vocab.txt +0 -0
  6. encoder/special_tokens_map.json +9 -0
  7. encoder/tokenizer.json +0 -0
  8. encoder/tokenizer_config.json +58 -0
  9. encoder/vocab.txt +0 -0
  10. generation_config.json +8 -0
  11. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "add_cross_attention": true,
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "bos_token_id": 2,
9
+ "classifier_dropout": null,
10
+ "eos_token_id": 3,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 4096,
16
+ "is_decoder": true,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "bert",
20
+ "num_attention_heads": 16,
21
+ "num_hidden_layers": 6,
22
+ "position_embedding_type": "relative_key_query",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 52000
26
+ },
27
+ "decoder_start_token_id": 2,
28
+ "encoder": {
29
+ "_name_or_path": "bert-base-uncased",
30
+ "architectures": [
31
+ "BertForMaskedLM"
32
+ ],
33
+ "attention_probs_dropout_prob": 0.1,
34
+ "classifier_dropout": null,
35
+ "gradient_checkpointing": false,
36
+ "hidden_act": "gelu",
37
+ "hidden_dropout_prob": 0.1,
38
+ "hidden_size": 768,
39
+ "initializer_range": 0.02,
40
+ "intermediate_size": 3072,
41
+ "layer_norm_eps": 1e-12,
42
+ "max_position_embeddings": 512,
43
+ "model_type": "bert",
44
+ "num_attention_heads": 12,
45
+ "num_hidden_layers": 12,
46
+ "position_embedding_type": "absolute",
47
+ "torch_dtype": "float32",
48
+ "type_vocab_size": 2,
49
+ "use_cache": true,
50
+ "vocab_size": 30522
51
+ },
52
+ "eos_token_id": 3,
53
+ "is_encoder_decoder": true,
54
+ "model_type": "encoder-decoder",
55
+ "pad_token_id": 0,
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.53.1"
58
+ }
decoder/special_tokens_map.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": {
4
+ "content": "[CLS]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "eos_token": "[SEP]",
11
+ "mask_token": {
12
+ "content": "[MASK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "pad_token": {
19
+ "content": "[PAD]",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "sep_token": {
26
+ "content": "[SEP]",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "unk_token": {
33
+ "content": "[UNK]",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ }
39
+ }
decoder/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
decoder/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
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
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "extra_special_tokens": {},
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 512,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
decoder/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
encoder/special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "[UNK]"
9
+ }
encoder/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
encoder/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": true,
48
+ "eos_token": "[SEP]",
49
+ "extra_special_tokens": {},
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 512,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
encoder/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "decoder_start_token_id": 2,
4
+ "eos_token_id": 3,
5
+ "max_length": 256,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.53.1"
8
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e32ee93f8f0037b5f70beaddc1e06ddbcf9779cb0f40b745be9e93d2de29756
3
+ size 1065336856