Hugging Face's logo

anhtux1x
/
Madlad400-Zh-Vi-2k-data5

Text2Text Generation
Transformers
Safetensors
t5
text-generation-inference
Inference Endpoints
Model card Files Community
anhtux1x commited on
Commit
cd8434c
•
1 Parent(s): 7864e5d

Upload T5ForConditionalGeneration

Browse files
Files changed (6) hide show
  1. config.json +34 -0
  2. generation_config.json +7 -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 +749 -0
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "anhtux1x/Madlad400-Zh-Vi-2k-data4",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 8192,
8
+ "d_kv": 128,
9
+ "d_model": 1024,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 2,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "n_positions": 512,
21
+ "num_decoder_layers": 32,
22
+ "num_heads": 16,
23
+ "num_layers": 32,
24
+ "output_past": true,
25
+ "pad_token_id": 1,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "task_specific_params": {},
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.41.2",
32
+ "use_cache": true,
33
+ "vocab_size": 256000
34
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.41.2"
7
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00755fc8c450f6a1841835aab014d5fdc8c5c5e09ff13559a111f83df260199e
3
+ size 4974721232
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:045e692c321085e722999137c6b5164c46d5a464d9e05d44069b741906932a7a
3
+ size 5000027936
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1e8af320e075284a6a42e249f8873ece9f8a3b999793ee85fe66a27fac86dee
3
+ size 1786838272
model.safetensors.index.json ADDED
@@ -0,0 +1,749 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 11761496064
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-00002-of-00003.safetensors",
75
+ "decoder.block.12.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
76
+ "decoder.block.12.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
77
+ "decoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
78
+ "decoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
79
+ "decoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
80
+ "decoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
81
+ "decoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
82
+ "decoder.block.13.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
83
+ "decoder.block.13.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
84
+ "decoder.block.13.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
85
+ "decoder.block.13.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
86
+ "decoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
87
+ "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
88
+ "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
89
+ "decoder.block.13.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
90
+ "decoder.block.13.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
91
+ "decoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
92
+ "decoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
93
+ "decoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
94
+ "decoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
95
+ "decoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
96
+ "decoder.block.14.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
97
+ "decoder.block.14.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
98
+ "decoder.block.14.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
99
+ "decoder.block.14.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
100
+ "decoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
101
+ "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
102
+ "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
103
+ "decoder.block.14.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
104
+ "decoder.block.14.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
105
+ "decoder.block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
106
+ "decoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
107
+ "decoder.block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
108
+ "decoder.block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
109
+ "decoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
110
+ "decoder.block.15.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
111
+ "decoder.block.15.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
112
+ "decoder.block.15.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
113
+ "decoder.block.15.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
114
+ "decoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
115
+ "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
116
+ "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
117
+ "decoder.block.15.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
118
+ "decoder.block.15.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
119
+ "decoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
120
+ "decoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
121
+ "decoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
122
+ "decoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
123
+ "decoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
124
+ "decoder.block.16.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
125
+ "decoder.block.16.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
126
+ "decoder.block.16.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
127
+ "decoder.block.16.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
128
+ "decoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
129
+ "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
130
+ "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
131
+ "decoder.block.16.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
132
+ "decoder.block.16.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
133
+ "decoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
134
+ "decoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
135
+ "decoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
136
+ "decoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
137
+ "decoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
138
+ "decoder.block.17.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
139
+ "decoder.block.17.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
140
+ "decoder.block.17.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
141
+ "decoder.block.17.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
142
+ "decoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
143
+ "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
144
+ "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
145
+ "decoder.block.17.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
146
+ "decoder.block.17.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
147
+ "decoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
148
+ "decoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
149
+ "decoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
150
+ "decoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
151
+ "decoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
152
+ "decoder.block.18.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
153
+ "decoder.block.18.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
154
+ "decoder.block.18.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
155
+ "decoder.block.18.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
156
+ "decoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
157
+ "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
158
+ "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
159
+ "decoder.block.18.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
160
+ "decoder.block.18.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
161
+ "decoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
162
+ "decoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
163
+ "decoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
164
+ "decoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
165
+ "decoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
166
+ "decoder.block.19.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
167
+ "decoder.block.19.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
168
+ "decoder.block.19.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
169
+ "decoder.block.19.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
170
+ "decoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
171
+ "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
172
+ "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
173
+ "decoder.block.19.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
174
+ "decoder.block.19.layer.2.layer_norm.weight": "model-00002-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-00002-of-00003.safetensors",
190
+ "decoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
191
+ "decoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
192
+ "decoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
193
+ "decoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
194
+ "decoder.block.20.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
195
+ "decoder.block.20.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
196
+ "decoder.block.20.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
197
+ "decoder.block.20.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
198
+ "decoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
199
+ "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
200
+ "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
201
+ "decoder.block.20.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
202
+ "decoder.block.20.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
203
+ "decoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
204
+ "decoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
205
+ "decoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
206
+ "decoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
207
+ "decoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
208
+ "decoder.block.21.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
209
+ "decoder.block.21.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
210
+ "decoder.block.21.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
211
+ "decoder.block.21.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
212
+ "decoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
213
+ "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
214
+ "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
215
+ "decoder.block.21.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
216
+ "decoder.block.21.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
217
+ "decoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
218
+ "decoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
219
+ "decoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
220
+ "decoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
221
+ "decoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
222
+ "decoder.block.22.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
223
+ "decoder.block.22.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
224
+ "decoder.block.22.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
225
+ "decoder.block.22.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
226
+ "decoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
227
+ "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
228
+ "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
229
+ "decoder.block.22.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
230
+ "decoder.block.22.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
231
+ "decoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
232
+ "decoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
233
+ "decoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
234
+ "decoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
235
+ "decoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
236
+ "decoder.block.23.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
237
+ "decoder.block.23.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
238
+ "decoder.block.23.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
239
+ "decoder.block.23.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
240
+ "decoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
241
+ "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
242
+ "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
243
+ "decoder.block.23.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
244
+ "decoder.block.23.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
245
+ "decoder.block.24.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
246
+ "decoder.block.24.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
247
+ "decoder.block.24.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
248
+ "decoder.block.24.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
249
+ "decoder.block.24.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
250
+ "decoder.block.24.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
251
+ "decoder.block.24.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
252
+ "decoder.block.24.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
253
+ "decoder.block.24.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
254
+ "decoder.block.24.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
255
+ "decoder.block.24.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
256
+ "decoder.block.24.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
257
+ "decoder.block.24.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
258
+ "decoder.block.24.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
259
+ "decoder.block.25.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
260
+ "decoder.block.25.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
261
+ "decoder.block.25.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
262
+ "decoder.block.25.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
263
+ "decoder.block.25.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
264
+ "decoder.block.25.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
265
+ "decoder.block.25.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
266
+ "decoder.block.25.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
267
+ "decoder.block.25.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
268
+ "decoder.block.25.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
269
+ "decoder.block.25.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
270
+ "decoder.block.25.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
271
+ "decoder.block.25.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
272
+ "decoder.block.25.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
273
+ "decoder.block.26.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
274
+ "decoder.block.26.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
275
+ "decoder.block.26.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
276
+ "decoder.block.26.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
277
+ "decoder.block.26.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
278
+ "decoder.block.26.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
279
+ "decoder.block.26.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
280
+ "decoder.block.26.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
281
+ "decoder.block.26.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
282
+ "decoder.block.26.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
283
+ "decoder.block.26.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
284
+ "decoder.block.26.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
285
+ "decoder.block.26.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
286
+ "decoder.block.26.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
287
+ "decoder.block.27.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
288
+ "decoder.block.27.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
289
+ "decoder.block.27.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
290
+ "decoder.block.27.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
291
+ "decoder.block.27.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
292
+ "decoder.block.27.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
293
+ "decoder.block.27.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
294
+ "decoder.block.27.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
295
+ "decoder.block.27.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
296
+ "decoder.block.27.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
297
+ "decoder.block.27.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
298
+ "decoder.block.27.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
299
+ "decoder.block.27.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
300
+ "decoder.block.27.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
301
+ "decoder.block.28.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
302
+ "decoder.block.28.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
303
+ "decoder.block.28.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
304
+ "decoder.block.28.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
305
+ "decoder.block.28.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
306
+ "decoder.block.28.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
307
+ "decoder.block.28.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
308
+ "decoder.block.28.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
309
+ "decoder.block.28.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
310
+ "decoder.block.28.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
311
+ "decoder.block.28.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
312
+ "decoder.block.28.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
313
+ "decoder.block.28.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
314
+ "decoder.block.28.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
315
+ "decoder.block.29.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
316
+ "decoder.block.29.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
317
+ "decoder.block.29.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
318
+ "decoder.block.29.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
319
+ "decoder.block.29.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
320
+ "decoder.block.29.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
321
+ "decoder.block.29.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
322
+ "decoder.block.29.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
323
+ "decoder.block.29.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
324
+ "decoder.block.29.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
325
+ "decoder.block.29.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
326
+ "decoder.block.29.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
327
+ "decoder.block.29.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
328
+ "decoder.block.29.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
329
+ "decoder.block.3.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
330
+ "decoder.block.3.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
331
+ "decoder.block.3.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
332
+ "decoder.block.3.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
333
+ "decoder.block.3.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
334
+ "decoder.block.3.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
335
+ "decoder.block.3.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
336
+ "decoder.block.3.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
337
+ "decoder.block.3.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
338
+ "decoder.block.3.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
339
+ "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
340
+ "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
341
+ "decoder.block.3.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
342
+ "decoder.block.3.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
343
+ "decoder.block.30.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
344
+ "decoder.block.30.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
345
+ "decoder.block.30.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
346
+ "decoder.block.30.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
347
+ "decoder.block.30.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
348
+ "decoder.block.30.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
349
+ "decoder.block.30.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
350
+ "decoder.block.30.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
351
+ "decoder.block.30.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
352
+ "decoder.block.30.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
353
+ "decoder.block.30.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
354
+ "decoder.block.30.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
355
+ "decoder.block.30.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
356
+ "decoder.block.30.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
357
+ "decoder.block.31.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
358
+ "decoder.block.31.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
359
+ "decoder.block.31.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
360
+ "decoder.block.31.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
361
+ "decoder.block.31.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
362
+ "decoder.block.31.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
363
+ "decoder.block.31.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
364
+ "decoder.block.31.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
365
+ "decoder.block.31.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
366
+ "decoder.block.31.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
367
+ "decoder.block.31.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
368
+ "decoder.block.31.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
369
+ "decoder.block.31.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
370
+ "decoder.block.31.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
371
+ "decoder.block.4.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
372
+ "decoder.block.4.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
373
+ "decoder.block.4.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
374
+ "decoder.block.4.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
375
+ "decoder.block.4.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
376
+ "decoder.block.4.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
377
+ "decoder.block.4.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
378
+ "decoder.block.4.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
379
+ "decoder.block.4.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
380
+ "decoder.block.4.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
381
+ "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
382
+ "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
383
+ "decoder.block.4.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
384
+ "decoder.block.4.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
385
+ "decoder.block.5.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
386
+ "decoder.block.5.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
387
+ "decoder.block.5.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
388
+ "decoder.block.5.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
389
+ "decoder.block.5.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
390
+ "decoder.block.5.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
391
+ "decoder.block.5.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
392
+ "decoder.block.5.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
393
+ "decoder.block.5.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
394
+ "decoder.block.5.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
395
+ "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
396
+ "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
397
+ "decoder.block.5.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
398
+ "decoder.block.5.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
399
+ "decoder.block.6.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
400
+ "decoder.block.6.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
401
+ "decoder.block.6.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
402
+ "decoder.block.6.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
403
+ "decoder.block.6.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
404
+ "decoder.block.6.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
405
+ "decoder.block.6.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
406
+ "decoder.block.6.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
407
+ "decoder.block.6.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
408
+ "decoder.block.6.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
409
+ "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
410
+ "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
411
+ "decoder.block.6.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
412
+ "decoder.block.6.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
413
+ "decoder.block.7.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
414
+ "decoder.block.7.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
415
+ "decoder.block.7.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
416
+ "decoder.block.7.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
417
+ "decoder.block.7.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
418
+ "decoder.block.7.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
419
+ "decoder.block.7.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
420
+ "decoder.block.7.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
421
+ "decoder.block.7.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
422
+ "decoder.block.7.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
423
+ "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
424
+ "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
425
+ "decoder.block.7.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
426
+ "decoder.block.7.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
427
+ "decoder.block.8.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
428
+ "decoder.block.8.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
429
+ "decoder.block.8.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
430
+ "decoder.block.8.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
431
+ "decoder.block.8.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
432
+ "decoder.block.8.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
433
+ "decoder.block.8.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
434
+ "decoder.block.8.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
435
+ "decoder.block.8.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
436
+ "decoder.block.8.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
437
+ "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
438
+ "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
439
+ "decoder.block.8.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
440
+ "decoder.block.8.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
441
+ "decoder.block.9.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
442
+ "decoder.block.9.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
443
+ "decoder.block.9.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
444
+ "decoder.block.9.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
445
+ "decoder.block.9.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
446
+ "decoder.block.9.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
447
+ "decoder.block.9.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
448
+ "decoder.block.9.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
449
+ "decoder.block.9.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
450
+ "decoder.block.9.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
451
+ "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
452
+ "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
453
+ "decoder.block.9.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
454
+ "decoder.block.9.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
455
+ "decoder.final_layer_norm.weight": "model-00003-of-00003.safetensors",
456
+ "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
457
+ "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
458
+ "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
459
+ "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
460
+ "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
461
+ "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
462
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
463
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
464
+ "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
465
+ "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
466
+ "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
467
+ "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
468
+ "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
469
+ "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
470
+ "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
471
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
472
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
473
+ "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
474
+ "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
475
+ "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
476
+ "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
477
+ "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
478
+ "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
479
+ "encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
480
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
481
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
482
+ "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
483
+ "encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
484
+ "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
485
+ "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
486
+ "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
487
+ "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
488
+ "encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
489
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
490
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
491
+ "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
492
+ "encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
493
+ "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
494
+ "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
495
+ "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
496
+ "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
497
+ "encoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
498
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
499
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
500
+ "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
501
+ "encoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
502
+ "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
503
+ "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
504
+ "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
505
+ "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
506
+ "encoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
507
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
508
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
509
+ "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
510
+ "encoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
511
+ "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
512
+ "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
513
+ "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
514
+ "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
515
+ "encoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
516
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
517
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
518
+ "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
519
+ "encoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
520
+ "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
521
+ "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
522
+ "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
523
+ "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
524
+ "encoder.block.15.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
525
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
526
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
527
+ "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
528
+ "encoder.block.15.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
529
+ "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
530
+ "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
531
+ "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
532
+ "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
533
+ "encoder.block.16.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
534
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
535
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
536
+ "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
537
+ "encoder.block.16.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
538
+ "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
539
+ "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
540
+ "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
541
+ "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
542
+ "encoder.block.17.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
543
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
544
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
545
+ "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
546
+ "encoder.block.17.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
547
+ "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
548
+ "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
549
+ "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
550
+ "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
551
+ "encoder.block.18.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
552
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
553
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
554
+ "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
555
+ "encoder.block.18.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
556
+ "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
557
+ "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
558
+ "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
559
+ "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
560
+ "encoder.block.19.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
561
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
562
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
563
+ "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
564
+ "encoder.block.19.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
565
+ "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
566
+ "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
567
+ "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
568
+ "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
569
+ "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
570
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
571
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
572
+ "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
573
+ "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
574
+ "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
575
+ "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
576
+ "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
577
+ "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
578
+ "encoder.block.20.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
579
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
580
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
581
+ "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
582
+ "encoder.block.20.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
583
+ "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
584
+ "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
585
+ "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
586
+ "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
587
+ "encoder.block.21.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
588
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
589
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
590
+ "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
591
+ "encoder.block.21.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
592
+ "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
593
+ "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
594
+ "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
595
+ "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
596
+ "encoder.block.22.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
597
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
598
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
599
+ "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
600
+ "encoder.block.22.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
601
+ "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
602
+ "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
603
+ "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
604
+ "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
605
+ "encoder.block.23.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
606
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
607
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
608
+ "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
609
+ "encoder.block.23.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
610
+ "encoder.block.24.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
611
+ "encoder.block.24.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
612
+ "encoder.block.24.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
613
+ "encoder.block.24.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
614
+ "encoder.block.24.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
615
+ "encoder.block.24.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
616
+ "encoder.block.24.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
617
+ "encoder.block.24.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
618
+ "encoder.block.24.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
619
+ "encoder.block.25.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
620
+ "encoder.block.25.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
621
+ "encoder.block.25.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
622
+ "encoder.block.25.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
623
+ "encoder.block.25.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
624
+ "encoder.block.25.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
625
+ "encoder.block.25.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
626
+ "encoder.block.25.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
627
+ "encoder.block.25.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
628
+ "encoder.block.26.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
629
+ "encoder.block.26.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
630
+ "encoder.block.26.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
631
+ "encoder.block.26.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
632
+ "encoder.block.26.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
633
+ "encoder.block.26.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
634
+ "encoder.block.26.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
635
+ "encoder.block.26.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
636
+ "encoder.block.26.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
637
+ "encoder.block.27.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
638
+ "encoder.block.27.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
639
+ "encoder.block.27.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
640
+ "encoder.block.27.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
641
+ "encoder.block.27.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
642
+ "encoder.block.27.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
643
+ "encoder.block.27.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
644
+ "encoder.block.27.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
645
+ "encoder.block.27.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
646
+ "encoder.block.28.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
647
+ "encoder.block.28.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
648
+ "encoder.block.28.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
649
+ "encoder.block.28.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
650
+ "encoder.block.28.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
651
+ "encoder.block.28.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
652
+ "encoder.block.28.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
653
+ "encoder.block.28.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
654
+ "encoder.block.28.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
655
+ "encoder.block.29.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
656
+ "encoder.block.29.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
657
+ "encoder.block.29.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
658
+ "encoder.block.29.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
659
+ "encoder.block.29.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
660
+ "encoder.block.29.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
661
+ "encoder.block.29.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
662
+ "encoder.block.29.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
663
+ "encoder.block.29.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
664
+ "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
665
+ "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
666
+ "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
667
+ "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
668
+ "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
669
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
670
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
671
+ "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
672
+ "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
673
+ "encoder.block.30.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
674
+ "encoder.block.30.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
675
+ "encoder.block.30.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
676
+ "encoder.block.30.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
677
+ "encoder.block.30.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
678
+ "encoder.block.30.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
679
+ "encoder.block.30.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
680
+ "encoder.block.30.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
681
+ "encoder.block.30.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
682
+ "encoder.block.31.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
683
+ "encoder.block.31.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
684
+ "encoder.block.31.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
685
+ "encoder.block.31.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
686
+ "encoder.block.31.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
687
+ "encoder.block.31.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
688
+ "encoder.block.31.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
689
+ "encoder.block.31.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
690
+ "encoder.block.31.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
691
+ "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
692
+ "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
693
+ "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
694
+ "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
695
+ "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
696
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
697
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
698
+ "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
699
+ "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
700
+ "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
701
+ "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
702
+ "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
703
+ "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
704
+ "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
705
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
706
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
707
+ "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
708
+ "encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
709
+ "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
710
+ "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
711
+ "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
712
+ "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
713
+ "encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
714
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
715
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
716
+ "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
717
+ "encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
718
+ "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
719
+ "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
720
+ "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
721
+ "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
722
+ "encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
723
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
724
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
725
+ "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
726
+ "encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
727
+ "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
728
+ "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
729
+ "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
730
+ "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
731
+ "encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
732
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
733
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
734
+ "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
735
+ "encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
736
+ "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
737
+ "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
738
+ "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
739
+ "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
740
+ "encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
741
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
742
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
743
+ "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
744
+ "encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
745
+ "encoder.final_layer_norm.weight": "model-00002-of-00003.safetensors",
746
+ "lm_head.weight": "model-00003-of-00003.safetensors",
747
+ "shared.weight": "model-00001-of-00003.safetensors"
748
+ }
749
+ }