megalaa commited on
Commit
02b3ebe
1 Parent(s): 584e717

Upload 12 files

Browse files
args.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model_name": "multicoptic/entire_clean_corpus", "src_language": "cop", "tgt_language": "eng", "max_input_length": 128, "max_target_length": 128}
config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "megalaa/mul-cop-en-norm-group-greekified",
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
+ "bad_words_ids": [
12
+ [
13
+ 64171
14
+ ]
15
+ ],
16
+ "bos_token_id": 0,
17
+ "classif_dropout": 0.0,
18
+ "classifier_dropout": 0.0,
19
+ "custom_pipelines": {
20
+ "coptic-english-translation": {
21
+ "default": {
22
+ "model": {
23
+ "pt": "megalaa/mul-cop-en-norm-group-greekified"
24
+ }
25
+ },
26
+ "impl": "__main__.CopticEnglishPipeline",
27
+ "pt": [
28
+ "AutoModelForSeq2SeqLM"
29
+ ],
30
+ "tf": [],
31
+ "type": "text"
32
+ }
33
+ },
34
+ "d_model": 512,
35
+ "decoder_attention_heads": 8,
36
+ "decoder_ffn_dim": 2048,
37
+ "decoder_layerdrop": 0.0,
38
+ "decoder_layers": 6,
39
+ "decoder_start_token_id": 64171,
40
+ "decoder_vocab_size": 64172,
41
+ "dropout": 0.1,
42
+ "encoder_attention_heads": 8,
43
+ "encoder_ffn_dim": 2048,
44
+ "encoder_layerdrop": 0.0,
45
+ "encoder_layers": 6,
46
+ "eos_token_id": 0,
47
+ "extra_pos_embeddings": 64172,
48
+ "forced_eos_token_id": 0,
49
+ "id2label": {
50
+ "0": "LABEL_0",
51
+ "1": "LABEL_1",
52
+ "2": "LABEL_2"
53
+ },
54
+ "init_std": 0.02,
55
+ "is_encoder_decoder": true,
56
+ "label2id": {
57
+ "LABEL_0": 0,
58
+ "LABEL_1": 1,
59
+ "LABEL_2": 2
60
+ },
61
+ "max_length": 512,
62
+ "max_position_embeddings": 512,
63
+ "model_type": "marian",
64
+ "normalize_before": false,
65
+ "normalize_embedding": false,
66
+ "num_beams": 6,
67
+ "num_hidden_layers": 6,
68
+ "pad_token_id": 64171,
69
+ "scale_embedding": true,
70
+ "share_encoder_decoder_embeddings": true,
71
+ "static_position_embeddings": true,
72
+ "torch_dtype": "float32",
73
+ "transformers_version": "4.38.1",
74
+ "use_cache": true,
75
+ "vocab_size": 64172
76
+ }
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 64171
5
+ ]
6
+ ],
7
+ "bos_token_id": 0,
8
+ "decoder_start_token_id": 64171,
9
+ "eos_token_id": 0,
10
+ "forced_eos_token_id": 0,
11
+ "max_length": 512,
12
+ "num_beams": 6,
13
+ "pad_token_id": 64171,
14
+ "renormalize_logits": true,
15
+ "transformers_version": "4.38.1"
16
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a656385a4934e92523f0cd16f6b0657571813f44650db8ebaecd902af1057b84
3
+ size 308263984
source.spm ADDED
Binary file (707 kB). View file
 
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<pad>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
target.spm ADDED
Binary file (791 kB). View file
 
tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "64171": {
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": true,
29
+ "eos_token": "</s>",
30
+ "model_max_length": 512,
31
+ "pad_token": "<pad>",
32
+ "separate_vocabs": false,
33
+ "source_lang": "mul",
34
+ "sp_model_kwargs": {},
35
+ "target_lang": "eng",
36
+ "tokenizer_class": "MarianTokenizer",
37
+ "unk_token": "<unk>"
38
+ }
train_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"job_hash": "bb4b305756099fe6c9aaa35d10bd9c1c", "evaluation_strategy": "steps", "learning_rate": 5e-05, "per_device_train_batch_size": 96, "per_device_eval_batch_size": 96, "weight_decay": 0, "save_total_limit": 4, "num_train_epochs": 12, "num_train_steps": null, "predict_with_generate": true, "eval_steps": 238, "logging_steps": 50, "label_smoothing_factor": 0, "commit_hash": "e045ea0"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f298dfdadef22f93696233852cbe958659770927b0d88d4771e749a33ef7bfd
3
+ size 4603
vocab.json ADDED
The diff for this file is too large to render. See raw diff