Hugging Face's logo

contemmcm
/
2baf0c7fc011b0a22c6984d13a635a31

Transformers
Safetensors
mbart
text2text-generation
Generated from Trainer
Model card Files
xet
Community
contemmcm commited on
Commit
8d5743b
·
verified ·
1 Parent(s): 770a245

End of training

Browse files
Files changed (12) hide show
  1. .gitattributes +1 -0
  2. README.md +79 -0
  3. config.json +61 -0
  4. generation_config.json +14 -0
  5. model-00001-of-00002.safetensors +3 -0
  6. model-00002-of-00002.safetensors +3 -0
  7. model.safetensors.index.json +527 -0
  8. sentencepiece.bpe.model +3 -0
  9. special_tokens_map.json +69 -0
  10. tokenizer.json +3 -0
  11. tokenizer_config.json +529 -0
  12. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: facebook/mbart-large-50-many-to-one-mmt
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - bleu
8
+ model-index:
9
+ - name: 2baf0c7fc011b0a22c6984d13a635a31
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # 2baf0c7fc011b0a22c6984d13a635a31
17
+
18
+ This model is a fine-tuned version of [facebook/mbart-large-50-many-to-one-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-one-mmt) on the Helsinki-NLP/opus_books [en-es] dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 2.2368
21
+ - Data Size: 1.0
22
+ - Epoch Runtime: 604.6076
23
+ - Bleu: 9.1969
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 5e-05
43
+ - train_batch_size: 8
44
+ - eval_batch_size: 8
45
+ - seed: 42
46
+ - distributed_type: multi-GPU
47
+ - num_devices: 4
48
+ - total_train_batch_size: 32
49
+ - total_eval_batch_size: 32
50
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
51
+ - lr_scheduler_type: constant
52
+ - num_epochs: 50
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Data Size | Epoch Runtime | Bleu |
57
+ |:-------------:|:-----:|:-----:|:---------------:|:---------:|:-------------:|:------:|
58
+ | No log | 0 | 0 | 5.8102 | 0 | 48.1224 | 0.6052 |
59
+ | No log | 1 | 2336 | 4.1491 | 0.0078 | 52.6214 | 1.5574 |
60
+ | 0.0627 | 2 | 4672 | 3.6285 | 0.0156 | 58.7082 | 2.6285 |
61
+ | 0.0805 | 3 | 7008 | 3.2199 | 0.0312 | 67.5729 | 3.4881 |
62
+ | 2.9332 | 4 | 9344 | 2.8721 | 0.0625 | 83.5089 | 4.6759 |
63
+ | 2.6498 | 5 | 11680 | 2.5635 | 0.125 | 117.1398 | 5.4796 |
64
+ | 2.2932 | 6 | 14016 | 2.2973 | 0.25 | 190.0217 | 6.9013 |
65
+ | 2.0659 | 7 | 16352 | 2.0638 | 0.5 | 329.6237 | 7.8104 |
66
+ | 1.8034 | 8.0 | 18688 | 1.9001 | 1.0 | 607.7954 | 8.3532 |
67
+ | 1.523 | 9.0 | 21024 | 1.8715 | 1.0 | 608.0761 | 9.7238 |
68
+ | 1.3197 | 10.0 | 23360 | 1.8835 | 1.0 | 608.2041 | 9.1238 |
69
+ | 1.1199 | 11.0 | 25696 | 1.9745 | 1.0 | 603.7367 | 8.8339 |
70
+ | 0.9434 | 12.0 | 28032 | 2.0606 | 1.0 | 606.0338 | 9.1520 |
71
+ | 0.7766 | 13.0 | 30368 | 2.2368 | 1.0 | 604.6076 | 9.1969 |
72
+
73
+
74
+ ### Framework versions
75
+
76
+ - Transformers 4.57.0
77
+ - Pytorch 2.8.0+cu128
78
+ - Datasets 4.2.0
79
+ - Tokenizers 0.22.1
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_num_labels": 3,
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": true,
7
+ "architectures": [
8
+ "MBartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.0,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "dtype": "float32",
22
+ "encoder_attention_heads": 16,
23
+ "encoder_ffn_dim": 4096,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 12,
26
+ "eos_token_id": 2,
27
+ "forced_eos_token_id": 2,
28
+ "gradient_checkpointing": false,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1",
32
+ "2": "LABEL_2"
33
+ },
34
+ "init_std": 0.02,
35
+ "is_encoder_decoder": true,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_2": 2
40
+ },
41
+ "max_length": null,
42
+ "max_position_embeddings": 1024,
43
+ "model_type": "mbart",
44
+ "normalize_before": true,
45
+ "normalize_embedding": true,
46
+ "num_beams": null,
47
+ "num_hidden_layers": 12,
48
+ "output_past": true,
49
+ "pad_token_id": 1,
50
+ "scale_embedding": true,
51
+ "static_position_embeddings": false,
52
+ "task_specific_params": {
53
+ "translation_en_to_ro": {
54
+ "decoder_start_token_id": 250020
55
+ }
56
+ },
57
+ "tokenizer_class": "MBart50Tokenizer",
58
+ "transformers_version": "4.57.0",
59
+ "use_cache": true,
60
+ "vocab_size": 250054
61
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "eos_token_id": [
6
+ 2
7
+ ],
8
+ "forced_bos_token_id": 250004,
9
+ "forced_eos_token_id": 2,
10
+ "max_length": 200,
11
+ "num_beams": 5,
12
+ "pad_token_id": 1,
13
+ "transformers_version": "4.57.0"
14
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b12034c0c2124f88ac2ab531e3ea0be599ea0dd58f8c0954fc492d269bc0439
3
+ size 4493022128
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49d573acd9284237397613024569e4e60f63bd55d451b32e5470a91da5eb1ec4
3
+ size 1024221312
model.safetensors.index.json ADDED
@@ -0,0 +1,527 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 152719872,
4
+ "total_size": 5517181720
5
+ },
6
+ "weight_map": {
7
+ "final_logits_bias": "model-00001-of-00002.safetensors",
8
+ "lm_head.weight": "model-00002-of-00002.safetensors",
9
+ "model.decoder.embed_positions.weight": "model-00001-of-00002.safetensors",
10
+ "model.decoder.embed_tokens.weight": "model-00001-of-00002.safetensors",
11
+ "model.decoder.layer_norm.bias": "model-00001-of-00002.safetensors",
12
+ "model.decoder.layer_norm.weight": "model-00001-of-00002.safetensors",
13
+ "model.decoder.layernorm_embedding.bias": "model-00001-of-00002.safetensors",
14
+ "model.decoder.layernorm_embedding.weight": "model-00001-of-00002.safetensors",
15
+ "model.decoder.layers.0.encoder_attn.k_proj.bias": "model-00001-of-00002.safetensors",
16
+ "model.decoder.layers.0.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.decoder.layers.0.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
18
+ "model.decoder.layers.0.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.decoder.layers.0.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
20
+ "model.decoder.layers.0.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.decoder.layers.0.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
22
+ "model.decoder.layers.0.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.decoder.layers.0.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
24
+ "model.decoder.layers.0.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
25
+ "model.decoder.layers.0.fc1.bias": "model-00001-of-00002.safetensors",
26
+ "model.decoder.layers.0.fc1.weight": "model-00001-of-00002.safetensors",
27
+ "model.decoder.layers.0.fc2.bias": "model-00001-of-00002.safetensors",
28
+ "model.decoder.layers.0.fc2.weight": "model-00001-of-00002.safetensors",
29
+ "model.decoder.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors",
30
+ "model.decoder.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors",
31
+ "model.decoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
32
+ "model.decoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.decoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
34
+ "model.decoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.decoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
36
+ "model.decoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.decoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
38
+ "model.decoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.decoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
40
+ "model.decoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
41
+ "model.decoder.layers.1.encoder_attn.k_proj.bias": "model-00001-of-00002.safetensors",
42
+ "model.decoder.layers.1.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.decoder.layers.1.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
44
+ "model.decoder.layers.1.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.decoder.layers.1.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
46
+ "model.decoder.layers.1.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.decoder.layers.1.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
48
+ "model.decoder.layers.1.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.decoder.layers.1.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
50
+ "model.decoder.layers.1.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
51
+ "model.decoder.layers.1.fc1.bias": "model-00001-of-00002.safetensors",
52
+ "model.decoder.layers.1.fc1.weight": "model-00001-of-00002.safetensors",
53
+ "model.decoder.layers.1.fc2.bias": "model-00001-of-00002.safetensors",
54
+ "model.decoder.layers.1.fc2.weight": "model-00001-of-00002.safetensors",
55
+ "model.decoder.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors",
56
+ "model.decoder.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors",
57
+ "model.decoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
58
+ "model.decoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.decoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
60
+ "model.decoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.decoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
62
+ "model.decoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.decoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
64
+ "model.decoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.decoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
66
+ "model.decoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
67
+ "model.decoder.layers.10.encoder_attn.k_proj.bias": "model-00001-of-00002.safetensors",
68
+ "model.decoder.layers.10.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.decoder.layers.10.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
70
+ "model.decoder.layers.10.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.decoder.layers.10.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
72
+ "model.decoder.layers.10.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.decoder.layers.10.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
74
+ "model.decoder.layers.10.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.decoder.layers.10.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
76
+ "model.decoder.layers.10.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
77
+ "model.decoder.layers.10.fc1.bias": "model-00001-of-00002.safetensors",
78
+ "model.decoder.layers.10.fc1.weight": "model-00001-of-00002.safetensors",
79
+ "model.decoder.layers.10.fc2.bias": "model-00001-of-00002.safetensors",
80
+ "model.decoder.layers.10.fc2.weight": "model-00001-of-00002.safetensors",
81
+ "model.decoder.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors",
82
+ "model.decoder.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors",
83
+ "model.decoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
84
+ "model.decoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.decoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
86
+ "model.decoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.decoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
88
+ "model.decoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.decoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
90
+ "model.decoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.decoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
92
+ "model.decoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
93
+ "model.decoder.layers.11.encoder_attn.k_proj.bias": "model-00001-of-00002.safetensors",
94
+ "model.decoder.layers.11.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.decoder.layers.11.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
96
+ "model.decoder.layers.11.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.decoder.layers.11.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
98
+ "model.decoder.layers.11.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.decoder.layers.11.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
100
+ "model.decoder.layers.11.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.decoder.layers.11.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
102
+ "model.decoder.layers.11.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
103
+ "model.decoder.layers.11.fc1.bias": "model-00001-of-00002.safetensors",
104
+ "model.decoder.layers.11.fc1.weight": "model-00001-of-00002.safetensors",
105
+ "model.decoder.layers.11.fc2.bias": "model-00001-of-00002.safetensors",
106
+ "model.decoder.layers.11.fc2.weight": "model-00001-of-00002.safetensors",
107
+ "model.decoder.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors",
108
+ "model.decoder.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors",
109
+ "model.decoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
110
+ "model.decoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.decoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
112
+ "model.decoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.decoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
114
+ "model.decoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.decoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
116
+ "model.decoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.decoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
118
+ "model.decoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
119
+ "model.decoder.layers.2.encoder_attn.k_proj.bias": "model-00001-of-00002.safetensors",
120
+ "model.decoder.layers.2.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.decoder.layers.2.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
122
+ "model.decoder.layers.2.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.decoder.layers.2.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
124
+ "model.decoder.layers.2.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.decoder.layers.2.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
126
+ "model.decoder.layers.2.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.decoder.layers.2.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
128
+ "model.decoder.layers.2.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
129
+ "model.decoder.layers.2.fc1.bias": "model-00001-of-00002.safetensors",
130
+ "model.decoder.layers.2.fc1.weight": "model-00001-of-00002.safetensors",
131
+ "model.decoder.layers.2.fc2.bias": "model-00001-of-00002.safetensors",
132
+ "model.decoder.layers.2.fc2.weight": "model-00001-of-00002.safetensors",
133
+ "model.decoder.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors",
134
+ "model.decoder.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors",
135
+ "model.decoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
136
+ "model.decoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.decoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
138
+ "model.decoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
139
+ "model.decoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
140
+ "model.decoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.decoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
142
+ "model.decoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.decoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
144
+ "model.decoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
145
+ "model.decoder.layers.3.encoder_attn.k_proj.bias": "model-00001-of-00002.safetensors",
146
+ "model.decoder.layers.3.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.decoder.layers.3.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
148
+ "model.decoder.layers.3.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.decoder.layers.3.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
150
+ "model.decoder.layers.3.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.decoder.layers.3.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
152
+ "model.decoder.layers.3.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
153
+ "model.decoder.layers.3.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
154
+ "model.decoder.layers.3.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
155
+ "model.decoder.layers.3.fc1.bias": "model-00001-of-00002.safetensors",
156
+ "model.decoder.layers.3.fc1.weight": "model-00001-of-00002.safetensors",
157
+ "model.decoder.layers.3.fc2.bias": "model-00001-of-00002.safetensors",
158
+ "model.decoder.layers.3.fc2.weight": "model-00001-of-00002.safetensors",
159
+ "model.decoder.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors",
160
+ "model.decoder.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors",
161
+ "model.decoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
162
+ "model.decoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
163
+ "model.decoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
164
+ "model.decoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.decoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
166
+ "model.decoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
167
+ "model.decoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
168
+ "model.decoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
169
+ "model.decoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
170
+ "model.decoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
171
+ "model.decoder.layers.4.encoder_attn.k_proj.bias": "model-00001-of-00002.safetensors",
172
+ "model.decoder.layers.4.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
173
+ "model.decoder.layers.4.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
174
+ "model.decoder.layers.4.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.decoder.layers.4.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
176
+ "model.decoder.layers.4.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
177
+ "model.decoder.layers.4.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
178
+ "model.decoder.layers.4.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
179
+ "model.decoder.layers.4.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
180
+ "model.decoder.layers.4.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
181
+ "model.decoder.layers.4.fc1.bias": "model-00001-of-00002.safetensors",
182
+ "model.decoder.layers.4.fc1.weight": "model-00001-of-00002.safetensors",
183
+ "model.decoder.layers.4.fc2.bias": "model-00001-of-00002.safetensors",
184
+ "model.decoder.layers.4.fc2.weight": "model-00001-of-00002.safetensors",
185
+ "model.decoder.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors",
186
+ "model.decoder.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors",
187
+ "model.decoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
188
+ "model.decoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
189
+ "model.decoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
190
+ "model.decoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.decoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
192
+ "model.decoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
193
+ "model.decoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
194
+ "model.decoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
195
+ "model.decoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
196
+ "model.decoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
197
+ "model.decoder.layers.5.encoder_attn.k_proj.bias": "model-00001-of-00002.safetensors",
198
+ "model.decoder.layers.5.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
199
+ "model.decoder.layers.5.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
200
+ "model.decoder.layers.5.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
201
+ "model.decoder.layers.5.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
202
+ "model.decoder.layers.5.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.decoder.layers.5.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
204
+ "model.decoder.layers.5.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.decoder.layers.5.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
206
+ "model.decoder.layers.5.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
207
+ "model.decoder.layers.5.fc1.bias": "model-00001-of-00002.safetensors",
208
+ "model.decoder.layers.5.fc1.weight": "model-00001-of-00002.safetensors",
209
+ "model.decoder.layers.5.fc2.bias": "model-00001-of-00002.safetensors",
210
+ "model.decoder.layers.5.fc2.weight": "model-00001-of-00002.safetensors",
211
+ "model.decoder.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors",
212
+ "model.decoder.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors",
213
+ "model.decoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
214
+ "model.decoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
215
+ "model.decoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
216
+ "model.decoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.decoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
218
+ "model.decoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
219
+ "model.decoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
220
+ "model.decoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.decoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
222
+ "model.decoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
223
+ "model.decoder.layers.6.encoder_attn.k_proj.bias": "model-00001-of-00002.safetensors",
224
+ "model.decoder.layers.6.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
225
+ "model.decoder.layers.6.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
226
+ "model.decoder.layers.6.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
227
+ "model.decoder.layers.6.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
228
+ "model.decoder.layers.6.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
229
+ "model.decoder.layers.6.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
230
+ "model.decoder.layers.6.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.decoder.layers.6.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
232
+ "model.decoder.layers.6.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
233
+ "model.decoder.layers.6.fc1.bias": "model-00001-of-00002.safetensors",
234
+ "model.decoder.layers.6.fc1.weight": "model-00001-of-00002.safetensors",
235
+ "model.decoder.layers.6.fc2.bias": "model-00001-of-00002.safetensors",
236
+ "model.decoder.layers.6.fc2.weight": "model-00001-of-00002.safetensors",
237
+ "model.decoder.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors",
238
+ "model.decoder.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors",
239
+ "model.decoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
240
+ "model.decoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
241
+ "model.decoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
242
+ "model.decoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
243
+ "model.decoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
244
+ "model.decoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.decoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
246
+ "model.decoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
247
+ "model.decoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
248
+ "model.decoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
249
+ "model.decoder.layers.7.encoder_attn.k_proj.bias": "model-00001-of-00002.safetensors",
250
+ "model.decoder.layers.7.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
251
+ "model.decoder.layers.7.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
252
+ "model.decoder.layers.7.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.decoder.layers.7.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
254
+ "model.decoder.layers.7.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
255
+ "model.decoder.layers.7.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
256
+ "model.decoder.layers.7.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.decoder.layers.7.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
258
+ "model.decoder.layers.7.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
259
+ "model.decoder.layers.7.fc1.bias": "model-00001-of-00002.safetensors",
260
+ "model.decoder.layers.7.fc1.weight": "model-00001-of-00002.safetensors",
261
+ "model.decoder.layers.7.fc2.bias": "model-00001-of-00002.safetensors",
262
+ "model.decoder.layers.7.fc2.weight": "model-00001-of-00002.safetensors",
263
+ "model.decoder.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors",
264
+ "model.decoder.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors",
265
+ "model.decoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
266
+ "model.decoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
267
+ "model.decoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
268
+ "model.decoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.decoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
270
+ "model.decoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
271
+ "model.decoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
272
+ "model.decoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.decoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
274
+ "model.decoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
275
+ "model.decoder.layers.8.encoder_attn.k_proj.bias": "model-00001-of-00002.safetensors",
276
+ "model.decoder.layers.8.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
277
+ "model.decoder.layers.8.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
278
+ "model.decoder.layers.8.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
279
+ "model.decoder.layers.8.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
280
+ "model.decoder.layers.8.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
281
+ "model.decoder.layers.8.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
282
+ "model.decoder.layers.8.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
283
+ "model.decoder.layers.8.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
284
+ "model.decoder.layers.8.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
285
+ "model.decoder.layers.8.fc1.bias": "model-00001-of-00002.safetensors",
286
+ "model.decoder.layers.8.fc1.weight": "model-00001-of-00002.safetensors",
287
+ "model.decoder.layers.8.fc2.bias": "model-00001-of-00002.safetensors",
288
+ "model.decoder.layers.8.fc2.weight": "model-00001-of-00002.safetensors",
289
+ "model.decoder.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors",
290
+ "model.decoder.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors",
291
+ "model.decoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
292
+ "model.decoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
293
+ "model.decoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
294
+ "model.decoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
295
+ "model.decoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
296
+ "model.decoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
297
+ "model.decoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
298
+ "model.decoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
299
+ "model.decoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
300
+ "model.decoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
301
+ "model.decoder.layers.9.encoder_attn.k_proj.bias": "model-00001-of-00002.safetensors",
302
+ "model.decoder.layers.9.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
303
+ "model.decoder.layers.9.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
304
+ "model.decoder.layers.9.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
305
+ "model.decoder.layers.9.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
306
+ "model.decoder.layers.9.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
307
+ "model.decoder.layers.9.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
308
+ "model.decoder.layers.9.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
309
+ "model.decoder.layers.9.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
310
+ "model.decoder.layers.9.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
311
+ "model.decoder.layers.9.fc1.bias": "model-00001-of-00002.safetensors",
312
+ "model.decoder.layers.9.fc1.weight": "model-00001-of-00002.safetensors",
313
+ "model.decoder.layers.9.fc2.bias": "model-00001-of-00002.safetensors",
314
+ "model.decoder.layers.9.fc2.weight": "model-00001-of-00002.safetensors",
315
+ "model.decoder.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors",
316
+ "model.decoder.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors",
317
+ "model.decoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
318
+ "model.decoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
319
+ "model.decoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
320
+ "model.decoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
321
+ "model.decoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
322
+ "model.decoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
323
+ "model.decoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
324
+ "model.decoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
325
+ "model.decoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
326
+ "model.decoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
327
+ "model.encoder.embed_positions.weight": "model-00001-of-00002.safetensors",
328
+ "model.encoder.embed_tokens.weight": "model-00001-of-00002.safetensors",
329
+ "model.encoder.layer_norm.bias": "model-00001-of-00002.safetensors",
330
+ "model.encoder.layer_norm.weight": "model-00001-of-00002.safetensors",
331
+ "model.encoder.layernorm_embedding.bias": "model-00001-of-00002.safetensors",
332
+ "model.encoder.layernorm_embedding.weight": "model-00001-of-00002.safetensors",
333
+ "model.encoder.layers.0.fc1.bias": "model-00001-of-00002.safetensors",
334
+ "model.encoder.layers.0.fc1.weight": "model-00001-of-00002.safetensors",
335
+ "model.encoder.layers.0.fc2.bias": "model-00001-of-00002.safetensors",
336
+ "model.encoder.layers.0.fc2.weight": "model-00001-of-00002.safetensors",
337
+ "model.encoder.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors",
338
+ "model.encoder.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors",
339
+ "model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
340
+ "model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
341
+ "model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
342
+ "model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
343
+ "model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
344
+ "model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
345
+ "model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
346
+ "model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
347
+ "model.encoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
348
+ "model.encoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
349
+ "model.encoder.layers.1.fc1.bias": "model-00001-of-00002.safetensors",
350
+ "model.encoder.layers.1.fc1.weight": "model-00001-of-00002.safetensors",
351
+ "model.encoder.layers.1.fc2.bias": "model-00001-of-00002.safetensors",
352
+ "model.encoder.layers.1.fc2.weight": "model-00001-of-00002.safetensors",
353
+ "model.encoder.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors",
354
+ "model.encoder.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors",
355
+ "model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
356
+ "model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
357
+ "model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
358
+ "model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
359
+ "model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
360
+ "model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
361
+ "model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
362
+ "model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
363
+ "model.encoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
364
+ "model.encoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
365
+ "model.encoder.layers.10.fc1.bias": "model-00001-of-00002.safetensors",
366
+ "model.encoder.layers.10.fc1.weight": "model-00001-of-00002.safetensors",
367
+ "model.encoder.layers.10.fc2.bias": "model-00001-of-00002.safetensors",
368
+ "model.encoder.layers.10.fc2.weight": "model-00001-of-00002.safetensors",
369
+ "model.encoder.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors",
370
+ "model.encoder.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors",
371
+ "model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
372
+ "model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
373
+ "model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
374
+ "model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
375
+ "model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
376
+ "model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
377
+ "model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
378
+ "model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
379
+ "model.encoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
380
+ "model.encoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
381
+ "model.encoder.layers.11.fc1.bias": "model-00001-of-00002.safetensors",
382
+ "model.encoder.layers.11.fc1.weight": "model-00001-of-00002.safetensors",
383
+ "model.encoder.layers.11.fc2.bias": "model-00001-of-00002.safetensors",
384
+ "model.encoder.layers.11.fc2.weight": "model-00001-of-00002.safetensors",
385
+ "model.encoder.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors",
386
+ "model.encoder.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors",
387
+ "model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
388
+ "model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
389
+ "model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
390
+ "model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
391
+ "model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
392
+ "model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
393
+ "model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
394
+ "model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
395
+ "model.encoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
396
+ "model.encoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
397
+ "model.encoder.layers.2.fc1.bias": "model-00001-of-00002.safetensors",
398
+ "model.encoder.layers.2.fc1.weight": "model-00001-of-00002.safetensors",
399
+ "model.encoder.layers.2.fc2.bias": "model-00001-of-00002.safetensors",
400
+ "model.encoder.layers.2.fc2.weight": "model-00001-of-00002.safetensors",
401
+ "model.encoder.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors",
402
+ "model.encoder.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors",
403
+ "model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
404
+ "model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
405
+ "model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
406
+ "model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
407
+ "model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
408
+ "model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
409
+ "model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
410
+ "model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
411
+ "model.encoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
412
+ "model.encoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
413
+ "model.encoder.layers.3.fc1.bias": "model-00001-of-00002.safetensors",
414
+ "model.encoder.layers.3.fc1.weight": "model-00001-of-00002.safetensors",
415
+ "model.encoder.layers.3.fc2.bias": "model-00001-of-00002.safetensors",
416
+ "model.encoder.layers.3.fc2.weight": "model-00001-of-00002.safetensors",
417
+ "model.encoder.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors",
418
+ "model.encoder.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors",
419
+ "model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
420
+ "model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
421
+ "model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
422
+ "model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
423
+ "model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
424
+ "model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
425
+ "model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
426
+ "model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
427
+ "model.encoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
428
+ "model.encoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
429
+ "model.encoder.layers.4.fc1.bias": "model-00001-of-00002.safetensors",
430
+ "model.encoder.layers.4.fc1.weight": "model-00001-of-00002.safetensors",
431
+ "model.encoder.layers.4.fc2.bias": "model-00001-of-00002.safetensors",
432
+ "model.encoder.layers.4.fc2.weight": "model-00001-of-00002.safetensors",
433
+ "model.encoder.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors",
434
+ "model.encoder.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors",
435
+ "model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
436
+ "model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
437
+ "model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
438
+ "model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
439
+ "model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
440
+ "model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
441
+ "model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
442
+ "model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
443
+ "model.encoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
444
+ "model.encoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
445
+ "model.encoder.layers.5.fc1.bias": "model-00001-of-00002.safetensors",
446
+ "model.encoder.layers.5.fc1.weight": "model-00001-of-00002.safetensors",
447
+ "model.encoder.layers.5.fc2.bias": "model-00001-of-00002.safetensors",
448
+ "model.encoder.layers.5.fc2.weight": "model-00001-of-00002.safetensors",
449
+ "model.encoder.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors",
450
+ "model.encoder.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors",
451
+ "model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
452
+ "model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
453
+ "model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
454
+ "model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
455
+ "model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
456
+ "model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
457
+ "model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
458
+ "model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
459
+ "model.encoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
460
+ "model.encoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
461
+ "model.encoder.layers.6.fc1.bias": "model-00001-of-00002.safetensors",
462
+ "model.encoder.layers.6.fc1.weight": "model-00001-of-00002.safetensors",
463
+ "model.encoder.layers.6.fc2.bias": "model-00001-of-00002.safetensors",
464
+ "model.encoder.layers.6.fc2.weight": "model-00001-of-00002.safetensors",
465
+ "model.encoder.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors",
466
+ "model.encoder.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors",
467
+ "model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
468
+ "model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
469
+ "model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
470
+ "model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
471
+ "model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
472
+ "model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
473
+ "model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
474
+ "model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
475
+ "model.encoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
476
+ "model.encoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
477
+ "model.encoder.layers.7.fc1.bias": "model-00001-of-00002.safetensors",
478
+ "model.encoder.layers.7.fc1.weight": "model-00001-of-00002.safetensors",
479
+ "model.encoder.layers.7.fc2.bias": "model-00001-of-00002.safetensors",
480
+ "model.encoder.layers.7.fc2.weight": "model-00001-of-00002.safetensors",
481
+ "model.encoder.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors",
482
+ "model.encoder.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors",
483
+ "model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
484
+ "model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
485
+ "model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
486
+ "model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
487
+ "model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
488
+ "model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
489
+ "model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
490
+ "model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
491
+ "model.encoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
492
+ "model.encoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
493
+ "model.encoder.layers.8.fc1.bias": "model-00001-of-00002.safetensors",
494
+ "model.encoder.layers.8.fc1.weight": "model-00001-of-00002.safetensors",
495
+ "model.encoder.layers.8.fc2.bias": "model-00001-of-00002.safetensors",
496
+ "model.encoder.layers.8.fc2.weight": "model-00001-of-00002.safetensors",
497
+ "model.encoder.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors",
498
+ "model.encoder.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors",
499
+ "model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
500
+ "model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
501
+ "model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
502
+ "model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
503
+ "model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
504
+ "model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
505
+ "model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
506
+ "model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
507
+ "model.encoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
508
+ "model.encoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
509
+ "model.encoder.layers.9.fc1.bias": "model-00001-of-00002.safetensors",
510
+ "model.encoder.layers.9.fc1.weight": "model-00001-of-00002.safetensors",
511
+ "model.encoder.layers.9.fc2.bias": "model-00001-of-00002.safetensors",
512
+ "model.encoder.layers.9.fc2.weight": "model-00001-of-00002.safetensors",
513
+ "model.encoder.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors",
514
+ "model.encoder.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors",
515
+ "model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
516
+ "model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
517
+ "model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
518
+ "model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
519
+ "model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
520
+ "model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
521
+ "model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
522
+ "model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
523
+ "model.encoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
524
+ "model.encoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
525
+ "model.shared.weight": "model-00001-of-00002.safetensors"
526
+ }
527
+ }
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "ar_AR",
4
+ "cs_CZ",
5
+ "de_DE",
6
+ "en_XX",
7
+ "es_XX",
8
+ "et_EE",
9
+ "fi_FI",
10
+ "fr_XX",
11
+ "gu_IN",
12
+ "hi_IN",
13
+ "it_IT",
14
+ "ja_XX",
15
+ "kk_KZ",
16
+ "ko_KR",
17
+ "lt_LT",
18
+ "lv_LV",
19
+ "my_MM",
20
+ "ne_NP",
21
+ "nl_XX",
22
+ "ro_RO",
23
+ "ru_RU",
24
+ "si_LK",
25
+ "tr_TR",
26
+ "vi_VN",
27
+ "zh_CN",
28
+ "af_ZA",
29
+ "az_AZ",
30
+ "bn_IN",
31
+ "fa_IR",
32
+ "he_IL",
33
+ "hr_HR",
34
+ "id_ID",
35
+ "ka_GE",
36
+ "km_KH",
37
+ "mk_MK",
38
+ "ml_IN",
39
+ "mn_MN",
40
+ "mr_IN",
41
+ "pl_PL",
42
+ "ps_AF",
43
+ "pt_XX",
44
+ "sv_SE",
45
+ "sw_KE",
46
+ "ta_IN",
47
+ "te_IN",
48
+ "th_TH",
49
+ "tl_XX",
50
+ "uk_UA",
51
+ "ur_PK",
52
+ "xh_ZA",
53
+ "gl_ES",
54
+ "sl_SI"
55
+ ],
56
+ "bos_token": "<s>",
57
+ "cls_token": "<s>",
58
+ "eos_token": "</s>",
59
+ "mask_token": {
60
+ "content": "<mask>",
61
+ "lstrip": true,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ "pad_token": "<pad>",
67
+ "sep_token": "</s>",
68
+ "unk_token": "<unk>"
69
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86f983b6563a9468794455498914bda0eaf9a60e5c9cd5a21669a24a625e490d
3
+ size 17109921
tokenizer_config.json ADDED
@@ -0,0 +1,529 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "ar_AR",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "250002": {
44
+ "content": "cs_CZ",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "250003": {
52
+ "content": "de_DE",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "250004": {
60
+ "content": "en_XX",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "250005": {
68
+ "content": "es_XX",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "250006": {
76
+ "content": "et_EE",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "250007": {
84
+ "content": "fi_FI",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "250008": {
92
+ "content": "fr_XX",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "250009": {
100
+ "content": "gu_IN",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "250010": {
108
+ "content": "hi_IN",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "250011": {
116
+ "content": "it_IT",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "250012": {
124
+ "content": "ja_XX",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "250013": {
132
+ "content": "kk_KZ",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "250014": {
140
+ "content": "ko_KR",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "250015": {
148
+ "content": "lt_LT",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "250016": {
156
+ "content": "lv_LV",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "250017": {
164
+ "content": "my_MM",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "250018": {
172
+ "content": "ne_NP",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "250019": {
180
+ "content": "nl_XX",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "250020": {
188
+ "content": "ro_RO",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "250021": {
196
+ "content": "ru_RU",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "250022": {
204
+ "content": "si_LK",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "250023": {
212
+ "content": "tr_TR",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "250024": {
220
+ "content": "vi_VN",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "250025": {
228
+ "content": "zh_CN",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "250026": {
236
+ "content": "af_ZA",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "250027": {
244
+ "content": "az_AZ",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "250028": {
252
+ "content": "bn_IN",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "250029": {
260
+ "content": "fa_IR",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "250030": {
268
+ "content": "he_IL",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "250031": {
276
+ "content": "hr_HR",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "250032": {
284
+ "content": "id_ID",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "250033": {
292
+ "content": "ka_GE",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "250034": {
300
+ "content": "km_KH",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "250035": {
308
+ "content": "mk_MK",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "250036": {
316
+ "content": "ml_IN",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "250037": {
324
+ "content": "mn_MN",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "250038": {
332
+ "content": "mr_IN",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "250039": {
340
+ "content": "pl_PL",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "250040": {
348
+ "content": "ps_AF",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "250041": {
356
+ "content": "pt_XX",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "250042": {
364
+ "content": "sv_SE",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "250043": {
372
+ "content": "sw_KE",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "250044": {
380
+ "content": "ta_IN",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "250045": {
388
+ "content": "te_IN",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "250046": {
396
+ "content": "th_TH",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "250047": {
404
+ "content": "tl_XX",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "250048": {
412
+ "content": "uk_UA",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "250049": {
420
+ "content": "ur_PK",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "250050": {
428
+ "content": "xh_ZA",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "250051": {
436
+ "content": "gl_ES",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "250052": {
444
+ "content": "sl_SI",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "250053": {
452
+ "content": "<mask>",
453
+ "lstrip": true,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ }
459
+ },
460
+ "additional_special_tokens": [
461
+ "ar_AR",
462
+ "cs_CZ",
463
+ "de_DE",
464
+ "en_XX",
465
+ "es_XX",
466
+ "et_EE",
467
+ "fi_FI",
468
+ "fr_XX",
469
+ "gu_IN",
470
+ "hi_IN",
471
+ "it_IT",
472
+ "ja_XX",
473
+ "kk_KZ",
474
+ "ko_KR",
475
+ "lt_LT",
476
+ "lv_LV",
477
+ "my_MM",
478
+ "ne_NP",
479
+ "nl_XX",
480
+ "ro_RO",
481
+ "ru_RU",
482
+ "si_LK",
483
+ "tr_TR",
484
+ "vi_VN",
485
+ "zh_CN",
486
+ "af_ZA",
487
+ "az_AZ",
488
+ "bn_IN",
489
+ "fa_IR",
490
+ "he_IL",
491
+ "hr_HR",
492
+ "id_ID",
493
+ "ka_GE",
494
+ "km_KH",
495
+ "mk_MK",
496
+ "ml_IN",
497
+ "mn_MN",
498
+ "mr_IN",
499
+ "pl_PL",
500
+ "ps_AF",
501
+ "pt_XX",
502
+ "sv_SE",
503
+ "sw_KE",
504
+ "ta_IN",
505
+ "te_IN",
506
+ "th_TH",
507
+ "tl_XX",
508
+ "uk_UA",
509
+ "ur_PK",
510
+ "xh_ZA",
511
+ "gl_ES",
512
+ "sl_SI"
513
+ ],
514
+ "bos_token": "<s>",
515
+ "clean_up_tokenization_spaces": false,
516
+ "cls_token": "<s>",
517
+ "eos_token": "</s>",
518
+ "extra_special_tokens": {},
519
+ "language_codes": "ML50",
520
+ "mask_token": "<mask>",
521
+ "model_max_length": 1000000000000000019884624838656,
522
+ "pad_token": "<pad>",
523
+ "sep_token": "</s>",
524
+ "sp_model_kwargs": {},
525
+ "src_lang": "en_XX",
526
+ "tgt_lang": "es_XX",
527
+ "tokenizer_class": "MBart50Tokenizer",
528
+ "unk_token": "<unk>"
529
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29f382464303629a7fa25c545c77340325250097bfbeff358fdc7f6b58bf16f0
3
+ size 6097