Anonumous commited on
Commit
f4d05d1
1 Parent(s): 2b6344e

Add model files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<LM>": 50357,
3
+ "<SC1>": 50358,
4
+ "<SC2>": 50359,
5
+ "<SC3>": 50360,
6
+ "<SC4>": 50361,
7
+ "<SC5>": 50362,
8
+ "<SC6>": 50363,
9
+ "<extra_id_0>": 50257,
10
+ "<extra_id_10>": 50267,
11
+ "<extra_id_11>": 50268,
12
+ "<extra_id_12>": 50269,
13
+ "<extra_id_13>": 50270,
14
+ "<extra_id_14>": 50271,
15
+ "<extra_id_15>": 50272,
16
+ "<extra_id_16>": 50273,
17
+ "<extra_id_17>": 50274,
18
+ "<extra_id_18>": 50275,
19
+ "<extra_id_19>": 50276,
20
+ "<extra_id_1>": 50258,
21
+ "<extra_id_20>": 50277,
22
+ "<extra_id_21>": 50278,
23
+ "<extra_id_22>": 50279,
24
+ "<extra_id_23>": 50280,
25
+ "<extra_id_24>": 50281,
26
+ "<extra_id_25>": 50282,
27
+ "<extra_id_26>": 50283,
28
+ "<extra_id_27>": 50284,
29
+ "<extra_id_28>": 50285,
30
+ "<extra_id_29>": 50286,
31
+ "<extra_id_2>": 50259,
32
+ "<extra_id_30>": 50287,
33
+ "<extra_id_31>": 50288,
34
+ "<extra_id_32>": 50289,
35
+ "<extra_id_33>": 50290,
36
+ "<extra_id_34>": 50291,
37
+ "<extra_id_35>": 50292,
38
+ "<extra_id_36>": 50293,
39
+ "<extra_id_37>": 50294,
40
+ "<extra_id_38>": 50295,
41
+ "<extra_id_39>": 50296,
42
+ "<extra_id_3>": 50260,
43
+ "<extra_id_40>": 50297,
44
+ "<extra_id_41>": 50298,
45
+ "<extra_id_42>": 50299,
46
+ "<extra_id_43>": 50300,
47
+ "<extra_id_44>": 50301,
48
+ "<extra_id_45>": 50302,
49
+ "<extra_id_46>": 50303,
50
+ "<extra_id_47>": 50304,
51
+ "<extra_id_48>": 50305,
52
+ "<extra_id_49>": 50306,
53
+ "<extra_id_4>": 50261,
54
+ "<extra_id_50>": 50307,
55
+ "<extra_id_51>": 50308,
56
+ "<extra_id_52>": 50309,
57
+ "<extra_id_53>": 50310,
58
+ "<extra_id_54>": 50311,
59
+ "<extra_id_55>": 50312,
60
+ "<extra_id_56>": 50313,
61
+ "<extra_id_57>": 50314,
62
+ "<extra_id_58>": 50315,
63
+ "<extra_id_59>": 50316,
64
+ "<extra_id_5>": 50262,
65
+ "<extra_id_60>": 50317,
66
+ "<extra_id_61>": 50318,
67
+ "<extra_id_62>": 50319,
68
+ "<extra_id_63>": 50320,
69
+ "<extra_id_64>": 50321,
70
+ "<extra_id_65>": 50322,
71
+ "<extra_id_66>": 50323,
72
+ "<extra_id_67>": 50324,
73
+ "<extra_id_68>": 50325,
74
+ "<extra_id_69>": 50326,
75
+ "<extra_id_6>": 50263,
76
+ "<extra_id_70>": 50327,
77
+ "<extra_id_71>": 50328,
78
+ "<extra_id_72>": 50329,
79
+ "<extra_id_73>": 50330,
80
+ "<extra_id_74>": 50331,
81
+ "<extra_id_75>": 50332,
82
+ "<extra_id_76>": 50333,
83
+ "<extra_id_77>": 50334,
84
+ "<extra_id_78>": 50335,
85
+ "<extra_id_79>": 50336,
86
+ "<extra_id_7>": 50264,
87
+ "<extra_id_80>": 50337,
88
+ "<extra_id_81>": 50338,
89
+ "<extra_id_82>": 50339,
90
+ "<extra_id_83>": 50340,
91
+ "<extra_id_84>": 50341,
92
+ "<extra_id_85>": 50342,
93
+ "<extra_id_86>": 50343,
94
+ "<extra_id_87>": 50344,
95
+ "<extra_id_88>": 50345,
96
+ "<extra_id_89>": 50346,
97
+ "<extra_id_8>": 50265,
98
+ "<extra_id_90>": 50347,
99
+ "<extra_id_91>": 50348,
100
+ "<extra_id_92>": 50349,
101
+ "<extra_id_93>": 50350,
102
+ "<extra_id_94>": 50351,
103
+ "<extra_id_95>": 50352,
104
+ "<extra_id_96>": 50353,
105
+ "<extra_id_97>": 50354,
106
+ "<extra_id_98>": 50355,
107
+ "<extra_id_99>": 50356,
108
+ "<extra_id_9>": 50266
109
+ }
config (2).json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ai-forever/FRED-T5-1.7B",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "classifier_dropout": 0.0,
8
+ "d_ff": 4096,
9
+ "d_kv": 64,
10
+ "d_model": 1536,
11
+ "decoder_start_token_id": 0,
12
+ "dense_act_fn": "gelu_new",
13
+ "dropout_rate": 0.1,
14
+ "eos_token_id": 2,
15
+ "feed_forward_proj": "gated-gelu",
16
+ "gradient_checkpointing": false,
17
+ "initializer_factor": 1.0,
18
+ "is_encoder_decoder": true,
19
+ "is_gated_act": true,
20
+ "layer_norm_epsilon": 1e-06,
21
+ "model_type": "t5",
22
+ "num_decoder_layers": 24,
23
+ "num_heads": 24,
24
+ "num_layers": 24,
25
+ "output_past": true,
26
+ "pad_token_id": 0,
27
+ "relative_attention_max_distance": 128,
28
+ "relative_attention_num_buckets": 32,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.38.1",
32
+ "use_cache": true,
33
+ "vocab_size": 50364
34
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.38.1"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:539b37a9498cf8870dea0a8e66b1ea58dba3f5ac87bfc1e8bb078296a77430b6
3
+ size 4990875920
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c8a5c3bca5363ad315a0553c2229bf9649a4dbbe7278e49b44dc5710e8dc5bf
3
+ size 1970608832
model.safetensors.index.json ADDED
@@ -0,0 +1,565 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6961416192
4
+ },
5
+ "weight_map": {
6
+ "decoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
7
+ "decoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
8
+ "decoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
9
+ "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
10
+ "decoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
11
+ "decoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
12
+ "decoder.block.0.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
13
+ "decoder.block.0.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
14
+ "decoder.block.0.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
15
+ "decoder.block.0.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
16
+ "decoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
17
+ "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
18
+ "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
19
+ "decoder.block.0.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
20
+ "decoder.block.0.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
21
+ "decoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
22
+ "decoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
23
+ "decoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
24
+ "decoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
25
+ "decoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
26
+ "decoder.block.1.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
27
+ "decoder.block.1.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
28
+ "decoder.block.1.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
29
+ "decoder.block.1.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
30
+ "decoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
31
+ "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
32
+ "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
33
+ "decoder.block.1.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
34
+ "decoder.block.1.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
35
+ "decoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
36
+ "decoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
37
+ "decoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
38
+ "decoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
39
+ "decoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
40
+ "decoder.block.10.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
41
+ "decoder.block.10.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
42
+ "decoder.block.10.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
43
+ "decoder.block.10.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
44
+ "decoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
45
+ "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
46
+ "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
47
+ "decoder.block.10.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
48
+ "decoder.block.10.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
49
+ "decoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
50
+ "decoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
51
+ "decoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
52
+ "decoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
53
+ "decoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
54
+ "decoder.block.11.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
55
+ "decoder.block.11.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
56
+ "decoder.block.11.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
57
+ "decoder.block.11.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
58
+ "decoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
59
+ "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
60
+ "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
61
+ "decoder.block.11.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
62
+ "decoder.block.11.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
63
+ "decoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
64
+ "decoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
65
+ "decoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
66
+ "decoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
67
+ "decoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
68
+ "decoder.block.12.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
69
+ "decoder.block.12.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
70
+ "decoder.block.12.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
71
+ "decoder.block.12.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
72
+ "decoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
73
+ "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
74
+ "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
75
+ "decoder.block.12.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
76
+ "decoder.block.12.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
77
+ "decoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
78
+ "decoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
79
+ "decoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
80
+ "decoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
81
+ "decoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
82
+ "decoder.block.13.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
83
+ "decoder.block.13.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
84
+ "decoder.block.13.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
85
+ "decoder.block.13.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
86
+ "decoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
87
+ "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
88
+ "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
89
+ "decoder.block.13.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
90
+ "decoder.block.13.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
91
+ "decoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
92
+ "decoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
93
+ "decoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
94
+ "decoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
95
+ "decoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
96
+ "decoder.block.14.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
97
+ "decoder.block.14.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
98
+ "decoder.block.14.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
99
+ "decoder.block.14.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
100
+ "decoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
101
+ "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
102
+ "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
103
+ "decoder.block.14.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
104
+ "decoder.block.14.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
105
+ "decoder.block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
106
+ "decoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
107
+ "decoder.block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
108
+ "decoder.block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
109
+ "decoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
110
+ "decoder.block.15.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
111
+ "decoder.block.15.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
112
+ "decoder.block.15.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
113
+ "decoder.block.15.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
114
+ "decoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
115
+ "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
116
+ "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
117
+ "decoder.block.15.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
118
+ "decoder.block.15.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
119
+ "decoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
120
+ "decoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
121
+ "decoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
122
+ "decoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
123
+ "decoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
124
+ "decoder.block.16.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
125
+ "decoder.block.16.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
126
+ "decoder.block.16.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
127
+ "decoder.block.16.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
128
+ "decoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
129
+ "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
130
+ "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
131
+ "decoder.block.16.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
132
+ "decoder.block.16.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
133
+ "decoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
134
+ "decoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
135
+ "decoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
136
+ "decoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
137
+ "decoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
138
+ "decoder.block.17.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
139
+ "decoder.block.17.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
140
+ "decoder.block.17.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
141
+ "decoder.block.17.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
142
+ "decoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
143
+ "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
144
+ "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
145
+ "decoder.block.17.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
146
+ "decoder.block.17.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
147
+ "decoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
148
+ "decoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
149
+ "decoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
150
+ "decoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
151
+ "decoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
152
+ "decoder.block.18.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
153
+ "decoder.block.18.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
154
+ "decoder.block.18.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
155
+ "decoder.block.18.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
156
+ "decoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
157
+ "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
158
+ "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
159
+ "decoder.block.18.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
160
+ "decoder.block.18.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
161
+ "decoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
162
+ "decoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
163
+ "decoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
164
+ "decoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
165
+ "decoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
166
+ "decoder.block.19.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
167
+ "decoder.block.19.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
168
+ "decoder.block.19.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
169
+ "decoder.block.19.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
170
+ "decoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
171
+ "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
172
+ "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
173
+ "decoder.block.19.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
174
+ "decoder.block.19.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
175
+ "decoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
176
+ "decoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
177
+ "decoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
178
+ "decoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
179
+ "decoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
180
+ "decoder.block.2.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
181
+ "decoder.block.2.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
182
+ "decoder.block.2.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
183
+ "decoder.block.2.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
184
+ "decoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
185
+ "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
186
+ "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
187
+ "decoder.block.2.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
188
+ "decoder.block.2.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
189
+ "decoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
190
+ "decoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
191
+ "decoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
192
+ "decoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
193
+ "decoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
194
+ "decoder.block.20.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
195
+ "decoder.block.20.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
196
+ "decoder.block.20.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
197
+ "decoder.block.20.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
198
+ "decoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
199
+ "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
200
+ "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
201
+ "decoder.block.20.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
202
+ "decoder.block.20.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
203
+ "decoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
204
+ "decoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
205
+ "decoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
206
+ "decoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
207
+ "decoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
208
+ "decoder.block.21.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
209
+ "decoder.block.21.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
210
+ "decoder.block.21.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
211
+ "decoder.block.21.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
212
+ "decoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
213
+ "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
214
+ "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
215
+ "decoder.block.21.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
216
+ "decoder.block.21.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
217
+ "decoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
218
+ "decoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
219
+ "decoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
220
+ "decoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
221
+ "decoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
222
+ "decoder.block.22.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
223
+ "decoder.block.22.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
224
+ "decoder.block.22.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
225
+ "decoder.block.22.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
226
+ "decoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
227
+ "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
228
+ "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
229
+ "decoder.block.22.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
230
+ "decoder.block.22.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
231
+ "decoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
232
+ "decoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
233
+ "decoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
234
+ "decoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
235
+ "decoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
236
+ "decoder.block.23.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
237
+ "decoder.block.23.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
238
+ "decoder.block.23.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
239
+ "decoder.block.23.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
240
+ "decoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
241
+ "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
242
+ "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
243
+ "decoder.block.23.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
244
+ "decoder.block.23.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
245
+ "decoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
246
+ "decoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
247
+ "decoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
248
+ "decoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
249
+ "decoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
250
+ "decoder.block.3.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
251
+ "decoder.block.3.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
252
+ "decoder.block.3.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
253
+ "decoder.block.3.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
254
+ "decoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
255
+ "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
256
+ "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
257
+ "decoder.block.3.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
258
+ "decoder.block.3.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
259
+ "decoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
260
+ "decoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
261
+ "decoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
262
+ "decoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
263
+ "decoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
264
+ "decoder.block.4.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
265
+ "decoder.block.4.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
266
+ "decoder.block.4.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
267
+ "decoder.block.4.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
268
+ "decoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
269
+ "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
270
+ "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
271
+ "decoder.block.4.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
272
+ "decoder.block.4.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
273
+ "decoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
274
+ "decoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
275
+ "decoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
276
+ "decoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
277
+ "decoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
278
+ "decoder.block.5.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
279
+ "decoder.block.5.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
280
+ "decoder.block.5.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
281
+ "decoder.block.5.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
282
+ "decoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
283
+ "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
284
+ "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
285
+ "decoder.block.5.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
286
+ "decoder.block.5.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
287
+ "decoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
288
+ "decoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
289
+ "decoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
290
+ "decoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
291
+ "decoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
292
+ "decoder.block.6.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
293
+ "decoder.block.6.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
294
+ "decoder.block.6.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
295
+ "decoder.block.6.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
296
+ "decoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
297
+ "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
298
+ "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
299
+ "decoder.block.6.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
300
+ "decoder.block.6.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
301
+ "decoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
302
+ "decoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
303
+ "decoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
304
+ "decoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
305
+ "decoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
306
+ "decoder.block.7.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
307
+ "decoder.block.7.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
308
+ "decoder.block.7.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
309
+ "decoder.block.7.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
310
+ "decoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
311
+ "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
312
+ "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
313
+ "decoder.block.7.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
314
+ "decoder.block.7.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
315
+ "decoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
316
+ "decoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
317
+ "decoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
318
+ "decoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
319
+ "decoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
320
+ "decoder.block.8.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
321
+ "decoder.block.8.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
322
+ "decoder.block.8.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
323
+ "decoder.block.8.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
324
+ "decoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
325
+ "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
326
+ "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
327
+ "decoder.block.8.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
328
+ "decoder.block.8.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
329
+ "decoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
330
+ "decoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
331
+ "decoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
332
+ "decoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
333
+ "decoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
334
+ "decoder.block.9.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
335
+ "decoder.block.9.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
336
+ "decoder.block.9.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
337
+ "decoder.block.9.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
338
+ "decoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
339
+ "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
340
+ "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
341
+ "decoder.block.9.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
342
+ "decoder.block.9.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
343
+ "decoder.final_layer_norm.weight": "model-00002-of-00002.safetensors",
344
+ "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
345
+ "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
346
+ "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
347
+ "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
348
+ "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
349
+ "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
350
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
351
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
352
+ "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
353
+ "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
354
+ "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
355
+ "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
356
+ "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
357
+ "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
358
+ "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
359
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
360
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
361
+ "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
362
+ "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
363
+ "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
364
+ "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
365
+ "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
366
+ "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
367
+ "encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
368
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
369
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
370
+ "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
371
+ "encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
372
+ "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
373
+ "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
374
+ "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
375
+ "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
376
+ "encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
377
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
378
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
379
+ "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
380
+ "encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
381
+ "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
382
+ "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
383
+ "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
384
+ "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
385
+ "encoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
386
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
387
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
388
+ "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
389
+ "encoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
390
+ "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
391
+ "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
392
+ "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
393
+ "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
394
+ "encoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
395
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
396
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
397
+ "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
398
+ "encoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
399
+ "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
400
+ "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
401
+ "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
402
+ "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
403
+ "encoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
404
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
405
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
406
+ "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
407
+ "encoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
408
+ "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
409
+ "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
410
+ "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
411
+ "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
412
+ "encoder.block.15.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
413
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
414
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
415
+ "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
416
+ "encoder.block.15.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
417
+ "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
418
+ "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
419
+ "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
420
+ "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
421
+ "encoder.block.16.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
422
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
423
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
424
+ "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
425
+ "encoder.block.16.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
426
+ "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
427
+ "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
428
+ "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
429
+ "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
430
+ "encoder.block.17.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
431
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
432
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
433
+ "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
434
+ "encoder.block.17.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
435
+ "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
436
+ "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
437
+ "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
438
+ "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
439
+ "encoder.block.18.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
440
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
441
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
442
+ "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
443
+ "encoder.block.18.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
444
+ "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
445
+ "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
446
+ "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
447
+ "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
448
+ "encoder.block.19.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
449
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
450
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
451
+ "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
452
+ "encoder.block.19.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
453
+ "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
454
+ "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
455
+ "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
456
+ "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
457
+ "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
458
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
459
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
460
+ "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
461
+ "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
462
+ "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
463
+ "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
464
+ "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
465
+ "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
466
+ "encoder.block.20.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
467
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
468
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
469
+ "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
470
+ "encoder.block.20.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
471
+ "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
472
+ "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
473
+ "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
474
+ "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
475
+ "encoder.block.21.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
476
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
477
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
478
+ "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
479
+ "encoder.block.21.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
480
+ "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
481
+ "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
482
+ "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
483
+ "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
484
+ "encoder.block.22.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
485
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
486
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
487
+ "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
488
+ "encoder.block.22.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
489
+ "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
490
+ "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
491
+ "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
492
+ "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
493
+ "encoder.block.23.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
494
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
495
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
496
+ "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
497
+ "encoder.block.23.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
498
+ "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
499
+ "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
500
+ "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
501
+ "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
502
+ "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
503
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
504
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
505
+ "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
506
+ "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
507
+ "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
508
+ "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
509
+ "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
510
+ "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
511
+ "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
512
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
513
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
514
+ "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
515
+ "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
516
+ "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
517
+ "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
518
+ "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
519
+ "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
520
+ "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
521
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
522
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
523
+ "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
524
+ "encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
525
+ "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
526
+ "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
527
+ "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
528
+ "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
529
+ "encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
530
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
531
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
532
+ "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
533
+ "encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
534
+ "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
535
+ "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
536
+ "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
537
+ "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
538
+ "encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
539
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
540
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
541
+ "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
542
+ "encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
543
+ "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
544
+ "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
545
+ "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
546
+ "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
547
+ "encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
548
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
549
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
550
+ "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
551
+ "encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
552
+ "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
553
+ "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
554
+ "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
555
+ "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
556
+ "encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
557
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
558
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
559
+ "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
560
+ "encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
561
+ "encoder.final_layer_norm.weight": "model-00001-of-00002.safetensors",
562
+ "lm_head.weight": "model-00002-of-00002.safetensors",
563
+ "shared.weight": "model-00001-of-00002.safetensors"
564
+ }
565
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "mask_token": {
17
+ "content": "<mask>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "<pad>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "<unk>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,913 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<mask>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "50257": {
46
+ "content": "<extra_id_0>",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "50258": {
54
+ "content": "<extra_id_1>",
55
+ "lstrip": false,
56
+ "normalized": true,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "50259": {
62
+ "content": "<extra_id_2>",
63
+ "lstrip": false,
64
+ "normalized": true,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "50260": {
70
+ "content": "<extra_id_3>",
71
+ "lstrip": false,
72
+ "normalized": true,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "50261": {
78
+ "content": "<extra_id_4>",
79
+ "lstrip": false,
80
+ "normalized": true,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "50262": {
86
+ "content": "<extra_id_5>",
87
+ "lstrip": false,
88
+ "normalized": true,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "50263": {
94
+ "content": "<extra_id_6>",
95
+ "lstrip": false,
96
+ "normalized": true,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "50264": {
102
+ "content": "<extra_id_7>",
103
+ "lstrip": false,
104
+ "normalized": true,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "50265": {
110
+ "content": "<extra_id_8>",
111
+ "lstrip": false,
112
+ "normalized": true,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": false
116
+ },
117
+ "50266": {
118
+ "content": "<extra_id_9>",
119
+ "lstrip": false,
120
+ "normalized": true,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "50267": {
126
+ "content": "<extra_id_10>",
127
+ "lstrip": false,
128
+ "normalized": true,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "50268": {
134
+ "content": "<extra_id_11>",
135
+ "lstrip": false,
136
+ "normalized": true,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "50269": {
142
+ "content": "<extra_id_12>",
143
+ "lstrip": false,
144
+ "normalized": true,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "50270": {
150
+ "content": "<extra_id_13>",
151
+ "lstrip": false,
152
+ "normalized": true,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "50271": {
158
+ "content": "<extra_id_14>",
159
+ "lstrip": false,
160
+ "normalized": true,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "50272": {
166
+ "content": "<extra_id_15>",
167
+ "lstrip": false,
168
+ "normalized": true,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "50273": {
174
+ "content": "<extra_id_16>",
175
+ "lstrip": false,
176
+ "normalized": true,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "50274": {
182
+ "content": "<extra_id_17>",
183
+ "lstrip": false,
184
+ "normalized": true,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "50275": {
190
+ "content": "<extra_id_18>",
191
+ "lstrip": false,
192
+ "normalized": true,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "50276": {
198
+ "content": "<extra_id_19>",
199
+ "lstrip": false,
200
+ "normalized": true,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "50277": {
206
+ "content": "<extra_id_20>",
207
+ "lstrip": false,
208
+ "normalized": true,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "50278": {
214
+ "content": "<extra_id_21>",
215
+ "lstrip": false,
216
+ "normalized": true,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ },
221
+ "50279": {
222
+ "content": "<extra_id_22>",
223
+ "lstrip": false,
224
+ "normalized": true,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": false
228
+ },
229
+ "50280": {
230
+ "content": "<extra_id_23>",
231
+ "lstrip": false,
232
+ "normalized": true,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": false
236
+ },
237
+ "50281": {
238
+ "content": "<extra_id_24>",
239
+ "lstrip": false,
240
+ "normalized": true,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": false
244
+ },
245
+ "50282": {
246
+ "content": "<extra_id_25>",
247
+ "lstrip": false,
248
+ "normalized": true,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": false
252
+ },
253
+ "50283": {
254
+ "content": "<extra_id_26>",
255
+ "lstrip": false,
256
+ "normalized": true,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": false
260
+ },
261
+ "50284": {
262
+ "content": "<extra_id_27>",
263
+ "lstrip": false,
264
+ "normalized": true,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": false
268
+ },
269
+ "50285": {
270
+ "content": "<extra_id_28>",
271
+ "lstrip": false,
272
+ "normalized": true,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": false
276
+ },
277
+ "50286": {
278
+ "content": "<extra_id_29>",
279
+ "lstrip": false,
280
+ "normalized": true,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": false
284
+ },
285
+ "50287": {
286
+ "content": "<extra_id_30>",
287
+ "lstrip": false,
288
+ "normalized": true,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": false
292
+ },
293
+ "50288": {
294
+ "content": "<extra_id_31>",
295
+ "lstrip": false,
296
+ "normalized": true,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": false
300
+ },
301
+ "50289": {
302
+ "content": "<extra_id_32>",
303
+ "lstrip": false,
304
+ "normalized": true,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": false
308
+ },
309
+ "50290": {
310
+ "content": "<extra_id_33>",
311
+ "lstrip": false,
312
+ "normalized": true,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": false
316
+ },
317
+ "50291": {
318
+ "content": "<extra_id_34>",
319
+ "lstrip": false,
320
+ "normalized": true,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": false
324
+ },
325
+ "50292": {
326
+ "content": "<extra_id_35>",
327
+ "lstrip": false,
328
+ "normalized": true,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": false
332
+ },
333
+ "50293": {
334
+ "content": "<extra_id_36>",
335
+ "lstrip": false,
336
+ "normalized": true,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": false
340
+ },
341
+ "50294": {
342
+ "content": "<extra_id_37>",
343
+ "lstrip": false,
344
+ "normalized": true,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": false
348
+ },
349
+ "50295": {
350
+ "content": "<extra_id_38>",
351
+ "lstrip": false,
352
+ "normalized": true,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": false
356
+ },
357
+ "50296": {
358
+ "content": "<extra_id_39>",
359
+ "lstrip": false,
360
+ "normalized": true,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": false
364
+ },
365
+ "50297": {
366
+ "content": "<extra_id_40>",
367
+ "lstrip": false,
368
+ "normalized": true,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": false
372
+ },
373
+ "50298": {
374
+ "content": "<extra_id_41>",
375
+ "lstrip": false,
376
+ "normalized": true,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": false
380
+ },
381
+ "50299": {
382
+ "content": "<extra_id_42>",
383
+ "lstrip": false,
384
+ "normalized": true,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": false
388
+ },
389
+ "50300": {
390
+ "content": "<extra_id_43>",
391
+ "lstrip": false,
392
+ "normalized": true,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": false
396
+ },
397
+ "50301": {
398
+ "content": "<extra_id_44>",
399
+ "lstrip": false,
400
+ "normalized": true,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": false
404
+ },
405
+ "50302": {
406
+ "content": "<extra_id_45>",
407
+ "lstrip": false,
408
+ "normalized": true,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": false
412
+ },
413
+ "50303": {
414
+ "content": "<extra_id_46>",
415
+ "lstrip": false,
416
+ "normalized": true,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": false
420
+ },
421
+ "50304": {
422
+ "content": "<extra_id_47>",
423
+ "lstrip": false,
424
+ "normalized": true,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": false
428
+ },
429
+ "50305": {
430
+ "content": "<extra_id_48>",
431
+ "lstrip": false,
432
+ "normalized": true,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": false
436
+ },
437
+ "50306": {
438
+ "content": "<extra_id_49>",
439
+ "lstrip": false,
440
+ "normalized": true,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": false
444
+ },
445
+ "50307": {
446
+ "content": "<extra_id_50>",
447
+ "lstrip": false,
448
+ "normalized": true,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": false
452
+ },
453
+ "50308": {
454
+ "content": "<extra_id_51>",
455
+ "lstrip": false,
456
+ "normalized": true,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": false
460
+ },
461
+ "50309": {
462
+ "content": "<extra_id_52>",
463
+ "lstrip": false,
464
+ "normalized": true,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": false
468
+ },
469
+ "50310": {
470
+ "content": "<extra_id_53>",
471
+ "lstrip": false,
472
+ "normalized": true,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": false
476
+ },
477
+ "50311": {
478
+ "content": "<extra_id_54>",
479
+ "lstrip": false,
480
+ "normalized": true,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": false
484
+ },
485
+ "50312": {
486
+ "content": "<extra_id_55>",
487
+ "lstrip": false,
488
+ "normalized": true,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": false
492
+ },
493
+ "50313": {
494
+ "content": "<extra_id_56>",
495
+ "lstrip": false,
496
+ "normalized": true,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": false
500
+ },
501
+ "50314": {
502
+ "content": "<extra_id_57>",
503
+ "lstrip": false,
504
+ "normalized": true,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": false
508
+ },
509
+ "50315": {
510
+ "content": "<extra_id_58>",
511
+ "lstrip": false,
512
+ "normalized": true,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": false
516
+ },
517
+ "50316": {
518
+ "content": "<extra_id_59>",
519
+ "lstrip": false,
520
+ "normalized": true,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": false
524
+ },
525
+ "50317": {
526
+ "content": "<extra_id_60>",
527
+ "lstrip": false,
528
+ "normalized": true,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": false
532
+ },
533
+ "50318": {
534
+ "content": "<extra_id_61>",
535
+ "lstrip": false,
536
+ "normalized": true,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": false
540
+ },
541
+ "50319": {
542
+ "content": "<extra_id_62>",
543
+ "lstrip": false,
544
+ "normalized": true,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": false
548
+ },
549
+ "50320": {
550
+ "content": "<extra_id_63>",
551
+ "lstrip": false,
552
+ "normalized": true,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": false
556
+ },
557
+ "50321": {
558
+ "content": "<extra_id_64>",
559
+ "lstrip": false,
560
+ "normalized": true,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": false
564
+ },
565
+ "50322": {
566
+ "content": "<extra_id_65>",
567
+ "lstrip": false,
568
+ "normalized": true,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": false
572
+ },
573
+ "50323": {
574
+ "content": "<extra_id_66>",
575
+ "lstrip": false,
576
+ "normalized": true,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": false
580
+ },
581
+ "50324": {
582
+ "content": "<extra_id_67>",
583
+ "lstrip": false,
584
+ "normalized": true,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": false
588
+ },
589
+ "50325": {
590
+ "content": "<extra_id_68>",
591
+ "lstrip": false,
592
+ "normalized": true,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": false
596
+ },
597
+ "50326": {
598
+ "content": "<extra_id_69>",
599
+ "lstrip": false,
600
+ "normalized": true,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": false
604
+ },
605
+ "50327": {
606
+ "content": "<extra_id_70>",
607
+ "lstrip": false,
608
+ "normalized": true,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": false
612
+ },
613
+ "50328": {
614
+ "content": "<extra_id_71>",
615
+ "lstrip": false,
616
+ "normalized": true,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": false
620
+ },
621
+ "50329": {
622
+ "content": "<extra_id_72>",
623
+ "lstrip": false,
624
+ "normalized": true,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": false
628
+ },
629
+ "50330": {
630
+ "content": "<extra_id_73>",
631
+ "lstrip": false,
632
+ "normalized": true,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": false
636
+ },
637
+ "50331": {
638
+ "content": "<extra_id_74>",
639
+ "lstrip": false,
640
+ "normalized": true,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": false
644
+ },
645
+ "50332": {
646
+ "content": "<extra_id_75>",
647
+ "lstrip": false,
648
+ "normalized": true,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": false
652
+ },
653
+ "50333": {
654
+ "content": "<extra_id_76>",
655
+ "lstrip": false,
656
+ "normalized": true,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": false
660
+ },
661
+ "50334": {
662
+ "content": "<extra_id_77>",
663
+ "lstrip": false,
664
+ "normalized": true,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": false
668
+ },
669
+ "50335": {
670
+ "content": "<extra_id_78>",
671
+ "lstrip": false,
672
+ "normalized": true,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": false
676
+ },
677
+ "50336": {
678
+ "content": "<extra_id_79>",
679
+ "lstrip": false,
680
+ "normalized": true,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": false
684
+ },
685
+ "50337": {
686
+ "content": "<extra_id_80>",
687
+ "lstrip": false,
688
+ "normalized": true,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": false
692
+ },
693
+ "50338": {
694
+ "content": "<extra_id_81>",
695
+ "lstrip": false,
696
+ "normalized": true,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": false
700
+ },
701
+ "50339": {
702
+ "content": "<extra_id_82>",
703
+ "lstrip": false,
704
+ "normalized": true,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": false
708
+ },
709
+ "50340": {
710
+ "content": "<extra_id_83>",
711
+ "lstrip": false,
712
+ "normalized": true,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": false
716
+ },
717
+ "50341": {
718
+ "content": "<extra_id_84>",
719
+ "lstrip": false,
720
+ "normalized": true,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": false
724
+ },
725
+ "50342": {
726
+ "content": "<extra_id_85>",
727
+ "lstrip": false,
728
+ "normalized": true,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": false
732
+ },
733
+ "50343": {
734
+ "content": "<extra_id_86>",
735
+ "lstrip": false,
736
+ "normalized": true,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": false
740
+ },
741
+ "50344": {
742
+ "content": "<extra_id_87>",
743
+ "lstrip": false,
744
+ "normalized": true,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": false
748
+ },
749
+ "50345": {
750
+ "content": "<extra_id_88>",
751
+ "lstrip": false,
752
+ "normalized": true,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": false
756
+ },
757
+ "50346": {
758
+ "content": "<extra_id_89>",
759
+ "lstrip": false,
760
+ "normalized": true,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": false
764
+ },
765
+ "50347": {
766
+ "content": "<extra_id_90>",
767
+ "lstrip": false,
768
+ "normalized": true,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": false
772
+ },
773
+ "50348": {
774
+ "content": "<extra_id_91>",
775
+ "lstrip": false,
776
+ "normalized": true,
777
+ "rstrip": false,
778
+ "single_word": false,
779
+ "special": false
780
+ },
781
+ "50349": {
782
+ "content": "<extra_id_92>",
783
+ "lstrip": false,
784
+ "normalized": true,
785
+ "rstrip": false,
786
+ "single_word": false,
787
+ "special": false
788
+ },
789
+ "50350": {
790
+ "content": "<extra_id_93>",
791
+ "lstrip": false,
792
+ "normalized": true,
793
+ "rstrip": false,
794
+ "single_word": false,
795
+ "special": false
796
+ },
797
+ "50351": {
798
+ "content": "<extra_id_94>",
799
+ "lstrip": false,
800
+ "normalized": true,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": false
804
+ },
805
+ "50352": {
806
+ "content": "<extra_id_95>",
807
+ "lstrip": false,
808
+ "normalized": true,
809
+ "rstrip": false,
810
+ "single_word": false,
811
+ "special": false
812
+ },
813
+ "50353": {
814
+ "content": "<extra_id_96>",
815
+ "lstrip": false,
816
+ "normalized": true,
817
+ "rstrip": false,
818
+ "single_word": false,
819
+ "special": false
820
+ },
821
+ "50354": {
822
+ "content": "<extra_id_97>",
823
+ "lstrip": false,
824
+ "normalized": true,
825
+ "rstrip": false,
826
+ "single_word": false,
827
+ "special": false
828
+ },
829
+ "50355": {
830
+ "content": "<extra_id_98>",
831
+ "lstrip": false,
832
+ "normalized": true,
833
+ "rstrip": false,
834
+ "single_word": false,
835
+ "special": false
836
+ },
837
+ "50356": {
838
+ "content": "<extra_id_99>",
839
+ "lstrip": false,
840
+ "normalized": true,
841
+ "rstrip": false,
842
+ "single_word": false,
843
+ "special": false
844
+ },
845
+ "50357": {
846
+ "content": "<LM>",
847
+ "lstrip": false,
848
+ "normalized": true,
849
+ "rstrip": false,
850
+ "single_word": false,
851
+ "special": false
852
+ },
853
+ "50358": {
854
+ "content": "<SC1>",
855
+ "lstrip": false,
856
+ "normalized": true,
857
+ "rstrip": false,
858
+ "single_word": false,
859
+ "special": false
860
+ },
861
+ "50359": {
862
+ "content": "<SC2>",
863
+ "lstrip": false,
864
+ "normalized": true,
865
+ "rstrip": false,
866
+ "single_word": false,
867
+ "special": false
868
+ },
869
+ "50360": {
870
+ "content": "<SC3>",
871
+ "lstrip": false,
872
+ "normalized": true,
873
+ "rstrip": false,
874
+ "single_word": false,
875
+ "special": false
876
+ },
877
+ "50361": {
878
+ "content": "<SC4>",
879
+ "lstrip": false,
880
+ "normalized": true,
881
+ "rstrip": false,
882
+ "single_word": false,
883
+ "special": false
884
+ },
885
+ "50362": {
886
+ "content": "<SC5>",
887
+ "lstrip": false,
888
+ "normalized": true,
889
+ "rstrip": false,
890
+ "single_word": false,
891
+ "special": false
892
+ },
893
+ "50363": {
894
+ "content": "<SC6>",
895
+ "lstrip": false,
896
+ "normalized": true,
897
+ "rstrip": false,
898
+ "single_word": false,
899
+ "special": false
900
+ }
901
+ },
902
+ "bos_token": "<s>",
903
+ "clean_up_tokenization_spaces": true,
904
+ "eos_token": "</s>",
905
+ "errors": "replace",
906
+ "mask_token": "<mask>",
907
+ "model_max_length": 1000000000000000019884624838656,
908
+ "pad_token": "<pad>",
909
+ "tokenizer_class": "GPT2Tokenizer",
910
+ "trust_remote_code": false,
911
+ "unk_token": "<unk>",
912
+ "use_fast": true
913
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:383dc835caa130b04224e429a1dd4ddfae0a6be88c8dec1f1606f3ee7972abd0
3
+ size 5048
vocab.json ADDED
The diff for this file is too large to render. See raw diff