Sarpyy commited on
Commit
7cab55c
·
verified ·
1 Parent(s): dfb2872

Upload 6 files

Browse files
config.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "bos_token_id": 2,
6
+ "decoder": {
7
+ "_name_or_path": "dbmdz/bert-base-turkish-cased",
8
+ "add_cross_attention": true,
9
+ "architectures": null,
10
+ "attention_probs_dropout_prob": 0.1,
11
+ "bos_token_id": null,
12
+ "chunk_size_feed_forward": 0,
13
+ "classifier_dropout": null,
14
+ "dtype": "float32",
15
+ "eos_token_id": null,
16
+ "hidden_act": "gelu",
17
+ "hidden_dropout_prob": 0.1,
18
+ "hidden_size": 768,
19
+ "id2label": {
20
+ "0": "LABEL_0",
21
+ "1": "LABEL_1"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "is_decoder": true,
26
+ "is_encoder_decoder": false,
27
+ "label2id": {
28
+ "LABEL_0": 0,
29
+ "LABEL_1": 1
30
+ },
31
+ "layer_norm_eps": 1e-12,
32
+ "max_position_embeddings": 512,
33
+ "model_type": "bert",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "output_attentions": false,
37
+ "output_hidden_states": false,
38
+ "pad_token_id": 0,
39
+ "problem_type": null,
40
+ "return_dict": true,
41
+ "tie_word_embeddings": true,
42
+ "type_vocab_size": 2,
43
+ "use_cache": true,
44
+ "vocab_size": 32000
45
+ },
46
+ "decoder_start_token_id": 2,
47
+ "dtype": "float32",
48
+ "encoder": {
49
+ "_name_or_path": "dbmdz/bert-base-turkish-cased",
50
+ "add_cross_attention": false,
51
+ "architectures": null,
52
+ "attention_probs_dropout_prob": 0.1,
53
+ "bos_token_id": null,
54
+ "chunk_size_feed_forward": 0,
55
+ "classifier_dropout": null,
56
+ "dtype": "float32",
57
+ "eos_token_id": null,
58
+ "hidden_act": "gelu",
59
+ "hidden_dropout_prob": 0.1,
60
+ "hidden_size": 768,
61
+ "id2label": {
62
+ "0": "LABEL_0",
63
+ "1": "LABEL_1"
64
+ },
65
+ "initializer_range": 0.02,
66
+ "intermediate_size": 3072,
67
+ "is_decoder": false,
68
+ "is_encoder_decoder": false,
69
+ "label2id": {
70
+ "LABEL_0": 0,
71
+ "LABEL_1": 1
72
+ },
73
+ "layer_norm_eps": 1e-12,
74
+ "max_position_embeddings": 512,
75
+ "model_type": "bert",
76
+ "num_attention_heads": 12,
77
+ "num_hidden_layers": 12,
78
+ "output_attentions": false,
79
+ "output_hidden_states": false,
80
+ "pad_token_id": 0,
81
+ "problem_type": null,
82
+ "return_dict": true,
83
+ "tie_word_embeddings": true,
84
+ "type_vocab_size": 2,
85
+ "use_cache": true,
86
+ "vocab_size": 32000
87
+ },
88
+ "eos_token_id": 3,
89
+ "is_encoder_decoder": true,
90
+ "model_type": "encoder-decoder",
91
+ "pad_token_id": 0,
92
+ "transformers_version": "5.3.0",
93
+ "use_cache": false,
94
+ "vocab_size": 32000
95
+ }
generation_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": false,
3
+ "assistant_confidence_threshold": 0.4,
4
+ "assistant_lookbehind": 10,
5
+ "bos_token_id": 2,
6
+ "decoder_start_token_id": 2,
7
+ "diversity_penalty": 0.0,
8
+ "do_sample": false,
9
+ "early_stopping": false,
10
+ "encoder_no_repeat_ngram_size": 0,
11
+ "encoder_repetition_penalty": 1.0,
12
+ "eos_token_id": [
13
+ 3
14
+ ],
15
+ "epsilon_cutoff": 0.0,
16
+ "eta_cutoff": 0.0,
17
+ "length_penalty": 1.0,
18
+ "max_length": 20,
19
+ "min_length": 0,
20
+ "no_repeat_ngram_size": 0,
21
+ "num_assistant_tokens": 20,
22
+ "num_assistant_tokens_schedule": "constant",
23
+ "num_beam_groups": 1,
24
+ "num_beams": 1,
25
+ "num_return_sequences": 1,
26
+ "output_attentions": false,
27
+ "output_hidden_states": false,
28
+ "output_scores": false,
29
+ "pad_token_id": 0,
30
+ "remove_invalid_values": false,
31
+ "repetition_penalty": 1.0,
32
+ "return_dict_in_generate": false,
33
+ "target_lookbehind": 10,
34
+ "temperature": 1.0,
35
+ "top_k": 50,
36
+ "top_p": 1.0,
37
+ "transformers_version": "5.3.0",
38
+ "typical_p": 1.0,
39
+ "use_cache": true
40
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:074291db043ad5a848e71059723271244d455b803b679a1dad73facf86b727b4
3
+ size 998605528
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "[CLS]",
4
+ "cls_token": "[CLS]",
5
+ "do_lower_case": false,
6
+ "eos_token": "[SEP]",
7
+ "is_local": false,
8
+ "mask_token": "[MASK]",
9
+ "max_len": 512,
10
+ "model_max_length": 512,
11
+ "pad_token": "[PAD]",
12
+ "sep_token": "[SEP]",
13
+ "strip_accents": null,
14
+ "tokenize_chinese_chars": true,
15
+ "tokenizer_class": "BertTokenizer",
16
+ "unk_token": "[UNK]"
17
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:861ea471007435078d6843875e4e14c79e5b4cd6d16934d86ba25379f78306ba
3
+ size 5048