Hugging Face's logo

phucnn
/
mt5-full-v6.1

Transformers
Safetensors
Vietnamese
Lao
mt5
text2text-generation
Generated from Trainer
Model card Files
xet
Community
phucnn commited on
Commit
b884daf
·
verified ·
1 Parent(s): 6caa158

Model save

Browse files
Files changed (6) hide show
  1. README.md +84 -0
  2. generation_config.json +6 -0
  3. model-00001-of-00003.safetensors +3 -0
  4. model-00002-of-00003.safetensors +3 -0
  5. model-00003-of-00003.safetensors +3 -0
  6. model.safetensors.index.json +565 -0
README.md ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/mt5-xl
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - bleu
8
+ model-index:
9
+ - name: mt5-full-v6.1
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
+ # mt5-full-v6.1
17
+
18
+ This model is a fine-tuned version of [google/mt5-xl](https://huggingface.co/google/mt5-xl) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.8710
21
+ - Bleu: 8.1488
22
+ - Gen Len: 18.9785
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 5e-06
42
+ - train_batch_size: 2
43
+ - eval_batch_size: 2
44
+ - seed: 3435
45
+ - gradient_accumulation_steps: 2
46
+ - total_train_batch_size: 4
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: cosine
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 3
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Bleu | Gen Len | Validation Loss |
55
+ |:-------------:|:-----:|:------:|:------:|:-------:|:---------------:|
56
+ | 1.5671 | 0.14 | 5000 | 6.5196 | 18.9699 | 1.1691 |
57
+ | 1.2277 | 0.28 | 10000 | 7.082 | 18.9724 | 1.0592 |
58
+ | 1.1316 | 0.42 | 15000 | 7.3283 | 18.9825 | 1.0112 |
59
+ | 1.0833 | 0.56 | 20000 | 7.4462 | 18.977 | 0.9728 |
60
+ | 1.0339 | 0.7 | 25000 | 8.0126 | 18.982 | 0.9546 |
61
+ | 1.025 | 0.83 | 30000 | 7.7648 | 18.9805 | 0.9337 |
62
+ | 0.9733 | 0.97 | 35000 | 7.9496 | 18.9815 | 0.9228 |
63
+ | 0.9035 | 1.11 | 40000 | 7.689 | 18.9795 | 0.9162 |
64
+ | 0.9386 | 1.25 | 45000 | 7.6781 | 18.9825 | 0.9039 |
65
+ | 0.9073 | 1.39 | 50000 | 7.8607 | 18.9805 | 0.8986 |
66
+ | 0.8928 | 1.53 | 55000 | 8.0666 | 18.981 | 0.8942 |
67
+ | 0.884 | 1.67 | 60000 | 8.1679 | 18.9785 | 0.8874 |
68
+ | 0.8786 | 1.81 | 65000 | 7.8516 | 18.9805 | 0.8831 |
69
+ | 0.8899 | 1.95 | 70000 | 0.8789 | 7.9392 | 18.9785 |
70
+ | 0.8638 | 2.09 | 75000 | 0.8781 | 8.1623 | 18.979 |
71
+ | 0.8293 | 2.22 | 80000 | 0.8752 | 8.0989 | 18.98 |
72
+ | 0.8625 | 2.36 | 85000 | 0.8743 | 8.176 | 18.979 |
73
+ | 0.8605 | 2.5 | 90000 | 0.8721 | 8.0117 | 18.9805 |
74
+ | 0.8479 | 2.64 | 95000 | 0.8711 | 8.1008 | 18.978 |
75
+ | 0.8391 | 2.78 | 100000 | 0.8708 | 8.2041 | 18.9795 |
76
+ | 0.8649 | 2.92 | 105000 | 0.8710 | 8.1488 | 18.9785 |
77
+
78
+
79
+ ### Framework versions
80
+
81
+ - Transformers 4.37.1
82
+ - Pytorch 2.1.2+cu121
83
+ - Datasets 2.16.1
84
+ - Tokenizers 0.15.1
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.37.1"
6
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c234147629e1d98e973c104c9ae2831f919e8a38aded4b4c61c3411c4b378631
3
+ size 4993585936
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85e79bfa7c99aeb9b1227b4a97d611315235fd4c3d4b90e1a236756fc879ce76
3
+ size 4983336088
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c51fdd1633f0c8b6ff728d4ac7d5ae786393a9033afa19a4214e6704ed922697
3
+ size 4993625240
model.safetensors.index.json ADDED
@@ -0,0 +1,565 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14970478592
4
+ },
5
+ "weight_map": {
6
+ "decoder.block.0.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
7
+ "decoder.block.0.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
8
+ "decoder.block.0.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
9
+ "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00003.safetensors",
10
+ "decoder.block.0.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
11
+ "decoder.block.0.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
12
+ "decoder.block.0.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
13
+ "decoder.block.0.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
14
+ "decoder.block.0.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
15
+ "decoder.block.0.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
16
+ "decoder.block.0.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
17
+ "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
18
+ "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
19
+ "decoder.block.0.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
20
+ "decoder.block.0.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
21
+ "decoder.block.1.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
22
+ "decoder.block.1.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
23
+ "decoder.block.1.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
24
+ "decoder.block.1.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
25
+ "decoder.block.1.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
26
+ "decoder.block.1.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
27
+ "decoder.block.1.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
28
+ "decoder.block.1.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
29
+ "decoder.block.1.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
30
+ "decoder.block.1.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
31
+ "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
32
+ "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
33
+ "decoder.block.1.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
34
+ "decoder.block.1.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
35
+ "decoder.block.10.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
36
+ "decoder.block.10.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
37
+ "decoder.block.10.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
38
+ "decoder.block.10.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
39
+ "decoder.block.10.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
40
+ "decoder.block.10.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
41
+ "decoder.block.10.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
42
+ "decoder.block.10.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
43
+ "decoder.block.10.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
44
+ "decoder.block.10.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
45
+ "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
46
+ "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
47
+ "decoder.block.10.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
48
+ "decoder.block.10.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
49
+ "decoder.block.11.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
50
+ "decoder.block.11.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
51
+ "decoder.block.11.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
52
+ "decoder.block.11.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
53
+ "decoder.block.11.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
54
+ "decoder.block.11.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
55
+ "decoder.block.11.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
56
+ "decoder.block.11.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
57
+ "decoder.block.11.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
58
+ "decoder.block.11.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
59
+ "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
60
+ "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
61
+ "decoder.block.11.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
62
+ "decoder.block.11.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
63
+ "decoder.block.12.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
64
+ "decoder.block.12.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
65
+ "decoder.block.12.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
66
+ "decoder.block.12.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
67
+ "decoder.block.12.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
68
+ "decoder.block.12.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
69
+ "decoder.block.12.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
70
+ "decoder.block.12.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
71
+ "decoder.block.12.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
72
+ "decoder.block.12.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
73
+ "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
74
+ "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
75
+ "decoder.block.12.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
76
+ "decoder.block.12.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
77
+ "decoder.block.13.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
78
+ "decoder.block.13.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
79
+ "decoder.block.13.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
80
+ "decoder.block.13.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
81
+ "decoder.block.13.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
82
+ "decoder.block.13.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
83
+ "decoder.block.13.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
84
+ "decoder.block.13.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
85
+ "decoder.block.13.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
86
+ "decoder.block.13.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
87
+ "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
88
+ "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
89
+ "decoder.block.13.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
90
+ "decoder.block.13.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
91
+ "decoder.block.14.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
92
+ "decoder.block.14.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
93
+ "decoder.block.14.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
94
+ "decoder.block.14.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
95
+ "decoder.block.14.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
96
+ "decoder.block.14.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
97
+ "decoder.block.14.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
98
+ "decoder.block.14.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
99
+ "decoder.block.14.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
100
+ "decoder.block.14.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
101
+ "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
102
+ "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
103
+ "decoder.block.14.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
104
+ "decoder.block.14.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
105
+ "decoder.block.15.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
106
+ "decoder.block.15.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
107
+ "decoder.block.15.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
108
+ "decoder.block.15.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
109
+ "decoder.block.15.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
110
+ "decoder.block.15.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
111
+ "decoder.block.15.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
112
+ "decoder.block.15.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
113
+ "decoder.block.15.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
114
+ "decoder.block.15.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
115
+ "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
116
+ "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
117
+ "decoder.block.15.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
118
+ "decoder.block.15.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
119
+ "decoder.block.16.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
120
+ "decoder.block.16.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
121
+ "decoder.block.16.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
122
+ "decoder.block.16.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
123
+ "decoder.block.16.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
124
+ "decoder.block.16.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
125
+ "decoder.block.16.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
126
+ "decoder.block.16.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
127
+ "decoder.block.16.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
128
+ "decoder.block.16.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
129
+ "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
130
+ "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
131
+ "decoder.block.16.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
132
+ "decoder.block.16.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
133
+ "decoder.block.17.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
134
+ "decoder.block.17.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
135
+ "decoder.block.17.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
136
+ "decoder.block.17.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
137
+ "decoder.block.17.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
138
+ "decoder.block.17.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
139
+ "decoder.block.17.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
140
+ "decoder.block.17.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
141
+ "decoder.block.17.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
142
+ "decoder.block.17.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
143
+ "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
144
+ "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
145
+ "decoder.block.17.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
146
+ "decoder.block.17.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
147
+ "decoder.block.18.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
148
+ "decoder.block.18.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
149
+ "decoder.block.18.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
150
+ "decoder.block.18.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
151
+ "decoder.block.18.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
152
+ "decoder.block.18.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
153
+ "decoder.block.18.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
154
+ "decoder.block.18.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
155
+ "decoder.block.18.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
156
+ "decoder.block.18.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
157
+ "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
158
+ "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
159
+ "decoder.block.18.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
160
+ "decoder.block.18.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
161
+ "decoder.block.19.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
162
+ "decoder.block.19.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
163
+ "decoder.block.19.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
164
+ "decoder.block.19.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
165
+ "decoder.block.19.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
166
+ "decoder.block.19.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
167
+ "decoder.block.19.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
168
+ "decoder.block.19.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
169
+ "decoder.block.19.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
170
+ "decoder.block.19.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
171
+ "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
172
+ "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
173
+ "decoder.block.19.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
174
+ "decoder.block.19.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
175
+ "decoder.block.2.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
176
+ "decoder.block.2.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
177
+ "decoder.block.2.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
178
+ "decoder.block.2.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
179
+ "decoder.block.2.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
180
+ "decoder.block.2.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
181
+ "decoder.block.2.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
182
+ "decoder.block.2.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
183
+ "decoder.block.2.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
184
+ "decoder.block.2.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
185
+ "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
186
+ "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
187
+ "decoder.block.2.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
188
+ "decoder.block.2.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
189
+ "decoder.block.20.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
190
+ "decoder.block.20.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
191
+ "decoder.block.20.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
192
+ "decoder.block.20.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
193
+ "decoder.block.20.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
194
+ "decoder.block.20.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
195
+ "decoder.block.20.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
196
+ "decoder.block.20.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
197
+ "decoder.block.20.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
198
+ "decoder.block.20.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
199
+ "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
200
+ "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
201
+ "decoder.block.20.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
202
+ "decoder.block.20.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
203
+ "decoder.block.21.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
204
+ "decoder.block.21.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
205
+ "decoder.block.21.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
206
+ "decoder.block.21.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
207
+ "decoder.block.21.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
208
+ "decoder.block.21.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
209
+ "decoder.block.21.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
210
+ "decoder.block.21.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
211
+ "decoder.block.21.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
212
+ "decoder.block.21.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
213
+ "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
214
+ "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
215
+ "decoder.block.21.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
216
+ "decoder.block.21.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
217
+ "decoder.block.22.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
218
+ "decoder.block.22.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
219
+ "decoder.block.22.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
220
+ "decoder.block.22.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
221
+ "decoder.block.22.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
222
+ "decoder.block.22.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
223
+ "decoder.block.22.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
224
+ "decoder.block.22.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
225
+ "decoder.block.22.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
226
+ "decoder.block.22.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
227
+ "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
228
+ "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
229
+ "decoder.block.22.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
230
+ "decoder.block.22.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
231
+ "decoder.block.23.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
232
+ "decoder.block.23.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
233
+ "decoder.block.23.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
234
+ "decoder.block.23.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
235
+ "decoder.block.23.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
236
+ "decoder.block.23.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
237
+ "decoder.block.23.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
238
+ "decoder.block.23.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
239
+ "decoder.block.23.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
240
+ "decoder.block.23.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
241
+ "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
242
+ "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
243
+ "decoder.block.23.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
244
+ "decoder.block.23.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
245
+ "decoder.block.3.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
246
+ "decoder.block.3.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
247
+ "decoder.block.3.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
248
+ "decoder.block.3.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
249
+ "decoder.block.3.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
250
+ "decoder.block.3.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
251
+ "decoder.block.3.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
252
+ "decoder.block.3.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
253
+ "decoder.block.3.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
254
+ "decoder.block.3.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
255
+ "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
256
+ "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
257
+ "decoder.block.3.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
258
+ "decoder.block.3.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
259
+ "decoder.block.4.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
260
+ "decoder.block.4.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
261
+ "decoder.block.4.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
262
+ "decoder.block.4.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
263
+ "decoder.block.4.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
264
+ "decoder.block.4.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
265
+ "decoder.block.4.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
266
+ "decoder.block.4.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
267
+ "decoder.block.4.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
268
+ "decoder.block.4.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
269
+ "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
270
+ "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
271
+ "decoder.block.4.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
272
+ "decoder.block.4.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
273
+ "decoder.block.5.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
274
+ "decoder.block.5.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
275
+ "decoder.block.5.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
276
+ "decoder.block.5.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
277
+ "decoder.block.5.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
278
+ "decoder.block.5.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
279
+ "decoder.block.5.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
280
+ "decoder.block.5.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
281
+ "decoder.block.5.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
282
+ "decoder.block.5.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
283
+ "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
284
+ "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
285
+ "decoder.block.5.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
286
+ "decoder.block.5.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
287
+ "decoder.block.6.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
288
+ "decoder.block.6.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
289
+ "decoder.block.6.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
290
+ "decoder.block.6.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
291
+ "decoder.block.6.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
292
+ "decoder.block.6.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
293
+ "decoder.block.6.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
294
+ "decoder.block.6.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
295
+ "decoder.block.6.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
296
+ "decoder.block.6.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
297
+ "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
298
+ "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
299
+ "decoder.block.6.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
300
+ "decoder.block.6.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
301
+ "decoder.block.7.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
302
+ "decoder.block.7.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
303
+ "decoder.block.7.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
304
+ "decoder.block.7.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
305
+ "decoder.block.7.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
306
+ "decoder.block.7.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
307
+ "decoder.block.7.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
308
+ "decoder.block.7.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
309
+ "decoder.block.7.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
310
+ "decoder.block.7.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
311
+ "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
312
+ "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
313
+ "decoder.block.7.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
314
+ "decoder.block.7.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
315
+ "decoder.block.8.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
316
+ "decoder.block.8.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
317
+ "decoder.block.8.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
318
+ "decoder.block.8.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
319
+ "decoder.block.8.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
320
+ "decoder.block.8.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
321
+ "decoder.block.8.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
322
+ "decoder.block.8.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
323
+ "decoder.block.8.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
324
+ "decoder.block.8.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
325
+ "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
326
+ "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
327
+ "decoder.block.8.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
328
+ "decoder.block.8.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
329
+ "decoder.block.9.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
330
+ "decoder.block.9.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
331
+ "decoder.block.9.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
332
+ "decoder.block.9.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
333
+ "decoder.block.9.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
334
+ "decoder.block.9.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
335
+ "decoder.block.9.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
336
+ "decoder.block.9.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
337
+ "decoder.block.9.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
338
+ "decoder.block.9.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
339
+ "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
340
+ "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
341
+ "decoder.block.9.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
342
+ "decoder.block.9.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
343
+ "decoder.final_layer_norm.weight": "model-00003-of-00003.safetensors",
344
+ "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
345
+ "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
346
+ "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
347
+ "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
348
+ "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
349
+ "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
350
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
351
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
352
+ "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
353
+ "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
354
+ "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
355
+ "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
356
+ "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
357
+ "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
358
+ "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
359
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
360
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
361
+ "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
362
+ "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
363
+ "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
364
+ "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
365
+ "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
366
+ "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
367
+ "encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
368
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
369
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
370
+ "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
371
+ "encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
372
+ "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
373
+ "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
374
+ "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
375
+ "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
376
+ "encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
377
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
378
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
379
+ "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
380
+ "encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
381
+ "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
382
+ "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
383
+ "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
384
+ "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
385
+ "encoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
386
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
387
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
388
+ "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
389
+ "encoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
390
+ "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
391
+ "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
392
+ "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
393
+ "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
394
+ "encoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
395
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
396
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
397
+ "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
398
+ "encoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
399
+ "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
400
+ "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
401
+ "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
402
+ "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
403
+ "encoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
404
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
405
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
406
+ "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
407
+ "encoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
408
+ "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
409
+ "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
410
+ "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
411
+ "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
412
+ "encoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
413
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
414
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
415
+ "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
416
+ "encoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
417
+ "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
418
+ "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
419
+ "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
420
+ "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
421
+ "encoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
422
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
423
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
424
+ "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
425
+ "encoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
426
+ "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
427
+ "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
428
+ "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
429
+ "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
430
+ "encoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
431
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
432
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
433
+ "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
434
+ "encoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
435
+ "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
436
+ "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
437
+ "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
438
+ "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
439
+ "encoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
440
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
441
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
442
+ "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
443
+ "encoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
444
+ "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
445
+ "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
446
+ "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
447
+ "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
448
+ "encoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
449
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
450
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
451
+ "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
452
+ "encoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
453
+ "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
454
+ "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
455
+ "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
456
+ "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
457
+ "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
458
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
459
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
460
+ "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
461
+ "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
462
+ "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
463
+ "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
464
+ "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
465
+ "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
466
+ "encoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
467
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
468
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
469
+ "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
470
+ "encoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
471
+ "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
472
+ "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
473
+ "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
474
+ "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
475
+ "encoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
476
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
477
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
478
+ "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
479
+ "encoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
480
+ "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
481
+ "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
482
+ "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
483
+ "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
484
+ "encoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
485
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
486
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
487
+ "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
488
+ "encoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
489
+ "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
490
+ "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
491
+ "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
492
+ "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
493
+ "encoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
494
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
495
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
496
+ "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
497
+ "encoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
498
+ "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
499
+ "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
500
+ "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
501
+ "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
502
+ "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
503
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
504
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
505
+ "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
506
+ "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
507
+ "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
508
+ "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
509
+ "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
510
+ "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
511
+ "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
512
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
513
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
514
+ "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
515
+ "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
516
+ "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
517
+ "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
518
+ "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
519
+ "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
520
+ "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
521
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
522
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
523
+ "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
524
+ "encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
525
+ "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
526
+ "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
527
+ "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
528
+ "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
529
+ "encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
530
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
531
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
532
+ "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
533
+ "encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
534
+ "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
535
+ "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
536
+ "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
537
+ "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
538
+ "encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
539
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
540
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
541
+ "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
542
+ "encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
543
+ "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
544
+ "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
545
+ "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
546
+ "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
547
+ "encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
548
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
549
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
550
+ "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
551
+ "encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
552
+ "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
553
+ "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
554
+ "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
555
+ "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
556
+ "encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
557
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
558
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
559
+ "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
560
+ "encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
561
+ "encoder.final_layer_norm.weight": "model-00002-of-00003.safetensors",
562
+ "lm_head.weight": "model-00003-of-00003.safetensors",
563
+ "shared.weight": "model-00001-of-00003.safetensors"
564
+ }
565
+ }