Hugging Face's logo

OpenNLG
/
OpenBA-V1-Chat

Feature Extraction
Transformers
PyTorch
openba
custom_code
Model card Files Community
openba commited on
Commit
abeba61
•
1 Parent(s): d054b18

initialize

Browse files
Files changed (10) hide show
  1. README.md +0 -3
  2. added_tokens.json +5 -0
  3. config.json +35 -0
  4. pytorch_model-00001-of-00003.bin +3 -0
  5. pytorch_model-00002-of-00003.bin +3 -0
  6. pytorch_model-00003-of-00003.bin +3 -0
  7. pytorch_model.bin.index.json +782 -0
  8. special_tokens_map.json +107 -0
  9. spiece.model +3 -0
  10. tokenizer_config.json +113 -0
README.md DELETED
@@ -1,3 +0,0 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<R>": 250200,
3
+ "<S>": 250201,
4
+ "<X>": 250202
5
+ }
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_ffn_bias": false,
3
+ "add_lm_head_bias": true,
4
+ "add_qkv_bias": true,
5
+ "architectures": [
6
+ "OpenBAForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "auto_map": {
10
+ "AutoConfig": "configuration_openba.OpenBAConfig",
11
+ "AutoModel": "modeling_openba.OpenBAForConditionalGeneration",
12
+ "AutoModelForCausalLM": "modeling_openba.OpenBAForConditionalGeneration",
13
+ "AutoModelForSeq2SeqLM": "modeling_openba.OpenBAForConditionalGeneration"
14
+ },
15
+ "decoder_max_seq_length": 256,
16
+ "decoder_start_token_id": 0,
17
+ "eos_token_id": 1,
18
+ "ffn_hidden_size": 16384,
19
+ "hidden_dropout": 0.1,
20
+ "hidden_size": 4096,
21
+ "initializer_factor": 1.0,
22
+ "is_encoder_decoder": true,
23
+ "kv_channels": 128,
24
+ "max_seq_length": 1024,
25
+ "model_type": "openba",
26
+ "num_decoder_layers": 36,
27
+ "num_heads": 40,
28
+ "num_layers": 12,
29
+ "pad_token_id": 0,
30
+ "tie_word_embeddings": false,
31
+ "tokenizer_class": "OpenBATokenizer",
32
+ "transformers_version": "4.30.2",
33
+ "use_cache": true,
34
+ "vocab_size": 250880
35
+ }
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3b8d14f2db81970df6efd3a2eafc67d8de866b406043d2e23e9c30c26cfd1b6
3
+ size 9996790582
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26bb300a4cbd3fea0811c59d0b2a5fba0f16ce363ef38220af0074d7e8f549d6
3
+ size 9962486872
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ed3376c9e3b8a46e81371293e1f0251729f7361a055f0be7141eab6818b7621
3
+ size 9180588837
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,782 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 29139601408
4
+ },
5
+ "weight_map": {
6
+ "decoder.block.0.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
7
+ "decoder.block.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
8
+ "decoder.block.0.inter_attn.kv.bias": "pytorch_model-00001-of-00003.bin",
9
+ "decoder.block.0.inter_attn.kv.weight": "pytorch_model-00001-of-00003.bin",
10
+ "decoder.block.0.inter_attn.o.bias": "pytorch_model-00001-of-00003.bin",
11
+ "decoder.block.0.inter_attn.o.weight": "pytorch_model-00001-of-00003.bin",
12
+ "decoder.block.0.inter_attn.q.bias": "pytorch_model-00001-of-00003.bin",
13
+ "decoder.block.0.inter_attn.q.weight": "pytorch_model-00001-of-00003.bin",
14
+ "decoder.block.0.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
15
+ "decoder.block.0.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
16
+ "decoder.block.0.post_attn_layernorm.bias": "pytorch_model-00001-of-00003.bin",
17
+ "decoder.block.0.post_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
18
+ "decoder.block.0.post_inter_attn_layernorm.bias": "pytorch_model-00001-of-00003.bin",
19
+ "decoder.block.0.post_inter_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
20
+ "decoder.block.0.self_attn.o.bias": "pytorch_model-00001-of-00003.bin",
21
+ "decoder.block.0.self_attn.o.weight": "pytorch_model-00001-of-00003.bin",
22
+ "decoder.block.0.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
23
+ "decoder.block.0.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
24
+ "decoder.block.1.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
25
+ "decoder.block.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
26
+ "decoder.block.1.inter_attn.kv.bias": "pytorch_model-00001-of-00003.bin",
27
+ "decoder.block.1.inter_attn.kv.weight": "pytorch_model-00001-of-00003.bin",
28
+ "decoder.block.1.inter_attn.o.bias": "pytorch_model-00001-of-00003.bin",
29
+ "decoder.block.1.inter_attn.o.weight": "pytorch_model-00001-of-00003.bin",
30
+ "decoder.block.1.inter_attn.q.bias": "pytorch_model-00001-of-00003.bin",
31
+ "decoder.block.1.inter_attn.q.weight": "pytorch_model-00001-of-00003.bin",
32
+ "decoder.block.1.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
33
+ "decoder.block.1.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
34
+ "decoder.block.1.post_attn_layernorm.bias": "pytorch_model-00001-of-00003.bin",
35
+ "decoder.block.1.post_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
36
+ "decoder.block.1.post_inter_attn_layernorm.bias": "pytorch_model-00001-of-00003.bin",
37
+ "decoder.block.1.post_inter_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
38
+ "decoder.block.1.self_attn.o.bias": "pytorch_model-00001-of-00003.bin",
39
+ "decoder.block.1.self_attn.o.weight": "pytorch_model-00001-of-00003.bin",
40
+ "decoder.block.1.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
41
+ "decoder.block.1.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
42
+ "decoder.block.10.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
43
+ "decoder.block.10.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
44
+ "decoder.block.10.inter_attn.kv.bias": "pytorch_model-00002-of-00003.bin",
45
+ "decoder.block.10.inter_attn.kv.weight": "pytorch_model-00002-of-00003.bin",
46
+ "decoder.block.10.inter_attn.o.bias": "pytorch_model-00002-of-00003.bin",
47
+ "decoder.block.10.inter_attn.o.weight": "pytorch_model-00002-of-00003.bin",
48
+ "decoder.block.10.inter_attn.q.bias": "pytorch_model-00002-of-00003.bin",
49
+ "decoder.block.10.inter_attn.q.weight": "pytorch_model-00002-of-00003.bin",
50
+ "decoder.block.10.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
51
+ "decoder.block.10.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
52
+ "decoder.block.10.post_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
53
+ "decoder.block.10.post_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
54
+ "decoder.block.10.post_inter_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
55
+ "decoder.block.10.post_inter_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
56
+ "decoder.block.10.self_attn.o.bias": "pytorch_model-00002-of-00003.bin",
57
+ "decoder.block.10.self_attn.o.weight": "pytorch_model-00002-of-00003.bin",
58
+ "decoder.block.10.self_attn.qkv.bias": "pytorch_model-00002-of-00003.bin",
59
+ "decoder.block.10.self_attn.qkv.weight": "pytorch_model-00002-of-00003.bin",
60
+ "decoder.block.11.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
61
+ "decoder.block.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
62
+ "decoder.block.11.inter_attn.kv.bias": "pytorch_model-00002-of-00003.bin",
63
+ "decoder.block.11.inter_attn.kv.weight": "pytorch_model-00002-of-00003.bin",
64
+ "decoder.block.11.inter_attn.o.bias": "pytorch_model-00002-of-00003.bin",
65
+ "decoder.block.11.inter_attn.o.weight": "pytorch_model-00002-of-00003.bin",
66
+ "decoder.block.11.inter_attn.q.bias": "pytorch_model-00002-of-00003.bin",
67
+ "decoder.block.11.inter_attn.q.weight": "pytorch_model-00002-of-00003.bin",
68
+ "decoder.block.11.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
69
+ "decoder.block.11.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
70
+ "decoder.block.11.post_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
71
+ "decoder.block.11.post_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
72
+ "decoder.block.11.post_inter_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
73
+ "decoder.block.11.post_inter_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
74
+ "decoder.block.11.self_attn.o.bias": "pytorch_model-00002-of-00003.bin",
75
+ "decoder.block.11.self_attn.o.weight": "pytorch_model-00002-of-00003.bin",
76
+ "decoder.block.11.self_attn.qkv.bias": "pytorch_model-00002-of-00003.bin",
77
+ "decoder.block.11.self_attn.qkv.weight": "pytorch_model-00002-of-00003.bin",
78
+ "decoder.block.12.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
79
+ "decoder.block.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
80
+ "decoder.block.12.inter_attn.kv.bias": "pytorch_model-00002-of-00003.bin",
81
+ "decoder.block.12.inter_attn.kv.weight": "pytorch_model-00002-of-00003.bin",
82
+ "decoder.block.12.inter_attn.o.bias": "pytorch_model-00002-of-00003.bin",
83
+ "decoder.block.12.inter_attn.o.weight": "pytorch_model-00002-of-00003.bin",
84
+ "decoder.block.12.inter_attn.q.bias": "pytorch_model-00002-of-00003.bin",
85
+ "decoder.block.12.inter_attn.q.weight": "pytorch_model-00002-of-00003.bin",
86
+ "decoder.block.12.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
87
+ "decoder.block.12.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
88
+ "decoder.block.12.post_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
89
+ "decoder.block.12.post_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
90
+ "decoder.block.12.post_inter_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
91
+ "decoder.block.12.post_inter_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
92
+ "decoder.block.12.self_attn.o.bias": "pytorch_model-00002-of-00003.bin",
93
+ "decoder.block.12.self_attn.o.weight": "pytorch_model-00002-of-00003.bin",
94
+ "decoder.block.12.self_attn.qkv.bias": "pytorch_model-00002-of-00003.bin",
95
+ "decoder.block.12.self_attn.qkv.weight": "pytorch_model-00002-of-00003.bin",
96
+ "decoder.block.13.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
97
+ "decoder.block.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
98
+ "decoder.block.13.inter_attn.kv.bias": "pytorch_model-00002-of-00003.bin",
99
+ "decoder.block.13.inter_attn.kv.weight": "pytorch_model-00002-of-00003.bin",
100
+ "decoder.block.13.inter_attn.o.bias": "pytorch_model-00002-of-00003.bin",
101
+ "decoder.block.13.inter_attn.o.weight": "pytorch_model-00002-of-00003.bin",
102
+ "decoder.block.13.inter_attn.q.bias": "pytorch_model-00002-of-00003.bin",
103
+ "decoder.block.13.inter_attn.q.weight": "pytorch_model-00002-of-00003.bin",
104
+ "decoder.block.13.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
105
+ "decoder.block.13.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
106
+ "decoder.block.13.post_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
107
+ "decoder.block.13.post_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
108
+ "decoder.block.13.post_inter_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
109
+ "decoder.block.13.post_inter_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
110
+ "decoder.block.13.self_attn.o.bias": "pytorch_model-00002-of-00003.bin",
111
+ "decoder.block.13.self_attn.o.weight": "pytorch_model-00002-of-00003.bin",
112
+ "decoder.block.13.self_attn.qkv.bias": "pytorch_model-00002-of-00003.bin",
113
+ "decoder.block.13.self_attn.qkv.weight": "pytorch_model-00002-of-00003.bin",
114
+ "decoder.block.14.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
115
+ "decoder.block.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
116
+ "decoder.block.14.inter_attn.kv.bias": "pytorch_model-00002-of-00003.bin",
117
+ "decoder.block.14.inter_attn.kv.weight": "pytorch_model-00002-of-00003.bin",
118
+ "decoder.block.14.inter_attn.o.bias": "pytorch_model-00002-of-00003.bin",
119
+ "decoder.block.14.inter_attn.o.weight": "pytorch_model-00002-of-00003.bin",
120
+ "decoder.block.14.inter_attn.q.bias": "pytorch_model-00002-of-00003.bin",
121
+ "decoder.block.14.inter_attn.q.weight": "pytorch_model-00002-of-00003.bin",
122
+ "decoder.block.14.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
123
+ "decoder.block.14.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
124
+ "decoder.block.14.post_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
125
+ "decoder.block.14.post_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
126
+ "decoder.block.14.post_inter_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
127
+ "decoder.block.14.post_inter_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
128
+ "decoder.block.14.self_attn.o.bias": "pytorch_model-00002-of-00003.bin",
129
+ "decoder.block.14.self_attn.o.weight": "pytorch_model-00002-of-00003.bin",
130
+ "decoder.block.14.self_attn.qkv.bias": "pytorch_model-00002-of-00003.bin",
131
+ "decoder.block.14.self_attn.qkv.weight": "pytorch_model-00002-of-00003.bin",
132
+ "decoder.block.15.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
133
+ "decoder.block.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
134
+ "decoder.block.15.inter_attn.kv.bias": "pytorch_model-00002-of-00003.bin",
135
+ "decoder.block.15.inter_attn.kv.weight": "pytorch_model-00002-of-00003.bin",
136
+ "decoder.block.15.inter_attn.o.bias": "pytorch_model-00002-of-00003.bin",
137
+ "decoder.block.15.inter_attn.o.weight": "pytorch_model-00002-of-00003.bin",
138
+ "decoder.block.15.inter_attn.q.bias": "pytorch_model-00002-of-00003.bin",
139
+ "decoder.block.15.inter_attn.q.weight": "pytorch_model-00002-of-00003.bin",
140
+ "decoder.block.15.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
141
+ "decoder.block.15.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
142
+ "decoder.block.15.post_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
143
+ "decoder.block.15.post_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
144
+ "decoder.block.15.post_inter_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
145
+ "decoder.block.15.post_inter_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
146
+ "decoder.block.15.self_attn.o.bias": "pytorch_model-00002-of-00003.bin",
147
+ "decoder.block.15.self_attn.o.weight": "pytorch_model-00002-of-00003.bin",
148
+ "decoder.block.15.self_attn.qkv.bias": "pytorch_model-00002-of-00003.bin",
149
+ "decoder.block.15.self_attn.qkv.weight": "pytorch_model-00002-of-00003.bin",
150
+ "decoder.block.16.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
151
+ "decoder.block.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
152
+ "decoder.block.16.inter_attn.kv.bias": "pytorch_model-00002-of-00003.bin",
153
+ "decoder.block.16.inter_attn.kv.weight": "pytorch_model-00002-of-00003.bin",
154
+ "decoder.block.16.inter_attn.o.bias": "pytorch_model-00002-of-00003.bin",
155
+ "decoder.block.16.inter_attn.o.weight": "pytorch_model-00002-of-00003.bin",
156
+ "decoder.block.16.inter_attn.q.bias": "pytorch_model-00002-of-00003.bin",
157
+ "decoder.block.16.inter_attn.q.weight": "pytorch_model-00002-of-00003.bin",
158
+ "decoder.block.16.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
159
+ "decoder.block.16.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
160
+ "decoder.block.16.post_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
161
+ "decoder.block.16.post_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
162
+ "decoder.block.16.post_inter_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
163
+ "decoder.block.16.post_inter_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
164
+ "decoder.block.16.self_attn.o.bias": "pytorch_model-00002-of-00003.bin",
165
+ "decoder.block.16.self_attn.o.weight": "pytorch_model-00002-of-00003.bin",
166
+ "decoder.block.16.self_attn.qkv.bias": "pytorch_model-00002-of-00003.bin",
167
+ "decoder.block.16.self_attn.qkv.weight": "pytorch_model-00002-of-00003.bin",
168
+ "decoder.block.17.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
169
+ "decoder.block.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
170
+ "decoder.block.17.inter_attn.kv.bias": "pytorch_model-00002-of-00003.bin",
171
+ "decoder.block.17.inter_attn.kv.weight": "pytorch_model-00002-of-00003.bin",
172
+ "decoder.block.17.inter_attn.o.bias": "pytorch_model-00002-of-00003.bin",
173
+ "decoder.block.17.inter_attn.o.weight": "pytorch_model-00002-of-00003.bin",
174
+ "decoder.block.17.inter_attn.q.bias": "pytorch_model-00002-of-00003.bin",
175
+ "decoder.block.17.inter_attn.q.weight": "pytorch_model-00002-of-00003.bin",
176
+ "decoder.block.17.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
177
+ "decoder.block.17.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
178
+ "decoder.block.17.post_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
179
+ "decoder.block.17.post_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
180
+ "decoder.block.17.post_inter_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
181
+ "decoder.block.17.post_inter_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
182
+ "decoder.block.17.self_attn.o.bias": "pytorch_model-00002-of-00003.bin",
183
+ "decoder.block.17.self_attn.o.weight": "pytorch_model-00002-of-00003.bin",
184
+ "decoder.block.17.self_attn.qkv.bias": "pytorch_model-00002-of-00003.bin",
185
+ "decoder.block.17.self_attn.qkv.weight": "pytorch_model-00002-of-00003.bin",
186
+ "decoder.block.18.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
187
+ "decoder.block.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
188
+ "decoder.block.18.inter_attn.kv.bias": "pytorch_model-00002-of-00003.bin",
189
+ "decoder.block.18.inter_attn.kv.weight": "pytorch_model-00002-of-00003.bin",
190
+ "decoder.block.18.inter_attn.o.bias": "pytorch_model-00002-of-00003.bin",
191
+ "decoder.block.18.inter_attn.o.weight": "pytorch_model-00002-of-00003.bin",
192
+ "decoder.block.18.inter_attn.q.bias": "pytorch_model-00002-of-00003.bin",
193
+ "decoder.block.18.inter_attn.q.weight": "pytorch_model-00002-of-00003.bin",
194
+ "decoder.block.18.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
195
+ "decoder.block.18.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
196
+ "decoder.block.18.post_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
197
+ "decoder.block.18.post_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
198
+ "decoder.block.18.post_inter_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
199
+ "decoder.block.18.post_inter_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
200
+ "decoder.block.18.self_attn.o.bias": "pytorch_model-00002-of-00003.bin",
201
+ "decoder.block.18.self_attn.o.weight": "pytorch_model-00002-of-00003.bin",
202
+ "decoder.block.18.self_attn.qkv.bias": "pytorch_model-00002-of-00003.bin",
203
+ "decoder.block.18.self_attn.qkv.weight": "pytorch_model-00002-of-00003.bin",
204
+ "decoder.block.19.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
205
+ "decoder.block.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
206
+ "decoder.block.19.inter_attn.kv.bias": "pytorch_model-00002-of-00003.bin",
207
+ "decoder.block.19.inter_attn.kv.weight": "pytorch_model-00002-of-00003.bin",
208
+ "decoder.block.19.inter_attn.o.bias": "pytorch_model-00002-of-00003.bin",
209
+ "decoder.block.19.inter_attn.o.weight": "pytorch_model-00002-of-00003.bin",
210
+ "decoder.block.19.inter_attn.q.bias": "pytorch_model-00002-of-00003.bin",
211
+ "decoder.block.19.inter_attn.q.weight": "pytorch_model-00002-of-00003.bin",
212
+ "decoder.block.19.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
213
+ "decoder.block.19.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
214
+ "decoder.block.19.post_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
215
+ "decoder.block.19.post_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
216
+ "decoder.block.19.post_inter_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
217
+ "decoder.block.19.post_inter_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
218
+ "decoder.block.19.self_attn.o.bias": "pytorch_model-00002-of-00003.bin",
219
+ "decoder.block.19.self_attn.o.weight": "pytorch_model-00002-of-00003.bin",
220
+ "decoder.block.19.self_attn.qkv.bias": "pytorch_model-00002-of-00003.bin",
221
+ "decoder.block.19.self_attn.qkv.weight": "pytorch_model-00002-of-00003.bin",
222
+ "decoder.block.2.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
223
+ "decoder.block.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
224
+ "decoder.block.2.inter_attn.kv.bias": "pytorch_model-00001-of-00003.bin",
225
+ "decoder.block.2.inter_attn.kv.weight": "pytorch_model-00001-of-00003.bin",
226
+ "decoder.block.2.inter_attn.o.bias": "pytorch_model-00001-of-00003.bin",
227
+ "decoder.block.2.inter_attn.o.weight": "pytorch_model-00001-of-00003.bin",
228
+ "decoder.block.2.inter_attn.q.bias": "pytorch_model-00001-of-00003.bin",
229
+ "decoder.block.2.inter_attn.q.weight": "pytorch_model-00001-of-00003.bin",
230
+ "decoder.block.2.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
231
+ "decoder.block.2.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
232
+ "decoder.block.2.post_attn_layernorm.bias": "pytorch_model-00001-of-00003.bin",
233
+ "decoder.block.2.post_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
234
+ "decoder.block.2.post_inter_attn_layernorm.bias": "pytorch_model-00001-of-00003.bin",
235
+ "decoder.block.2.post_inter_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
236
+ "decoder.block.2.self_attn.o.bias": "pytorch_model-00001-of-00003.bin",
237
+ "decoder.block.2.self_attn.o.weight": "pytorch_model-00001-of-00003.bin",
238
+ "decoder.block.2.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
239
+ "decoder.block.2.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
240
+ "decoder.block.20.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
241
+ "decoder.block.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
242
+ "decoder.block.20.inter_attn.kv.bias": "pytorch_model-00002-of-00003.bin",
243
+ "decoder.block.20.inter_attn.kv.weight": "pytorch_model-00002-of-00003.bin",
244
+ "decoder.block.20.inter_attn.o.bias": "pytorch_model-00002-of-00003.bin",
245
+ "decoder.block.20.inter_attn.o.weight": "pytorch_model-00002-of-00003.bin",
246
+ "decoder.block.20.inter_attn.q.bias": "pytorch_model-00002-of-00003.bin",
247
+ "decoder.block.20.inter_attn.q.weight": "pytorch_model-00002-of-00003.bin",
248
+ "decoder.block.20.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
249
+ "decoder.block.20.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
250
+ "decoder.block.20.post_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
251
+ "decoder.block.20.post_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
252
+ "decoder.block.20.post_inter_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
253
+ "decoder.block.20.post_inter_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
254
+ "decoder.block.20.self_attn.o.bias": "pytorch_model-00002-of-00003.bin",
255
+ "decoder.block.20.self_attn.o.weight": "pytorch_model-00002-of-00003.bin",
256
+ "decoder.block.20.self_attn.qkv.bias": "pytorch_model-00002-of-00003.bin",
257
+ "decoder.block.20.self_attn.qkv.weight": "pytorch_model-00002-of-00003.bin",
258
+ "decoder.block.21.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
259
+ "decoder.block.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
260
+ "decoder.block.21.inter_attn.kv.bias": "pytorch_model-00002-of-00003.bin",
261
+ "decoder.block.21.inter_attn.kv.weight": "pytorch_model-00002-of-00003.bin",
262
+ "decoder.block.21.inter_attn.o.bias": "pytorch_model-00002-of-00003.bin",
263
+ "decoder.block.21.inter_attn.o.weight": "pytorch_model-00002-of-00003.bin",
264
+ "decoder.block.21.inter_attn.q.bias": "pytorch_model-00002-of-00003.bin",
265
+ "decoder.block.21.inter_attn.q.weight": "pytorch_model-00002-of-00003.bin",
266
+ "decoder.block.21.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
267
+ "decoder.block.21.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
268
+ "decoder.block.21.post_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
269
+ "decoder.block.21.post_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
270
+ "decoder.block.21.post_inter_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
271
+ "decoder.block.21.post_inter_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
272
+ "decoder.block.21.self_attn.o.bias": "pytorch_model-00002-of-00003.bin",
273
+ "decoder.block.21.self_attn.o.weight": "pytorch_model-00002-of-00003.bin",
274
+ "decoder.block.21.self_attn.qkv.bias": "pytorch_model-00002-of-00003.bin",
275
+ "decoder.block.21.self_attn.qkv.weight": "pytorch_model-00002-of-00003.bin",
276
+ "decoder.block.22.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
277
+ "decoder.block.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
278
+ "decoder.block.22.inter_attn.kv.bias": "pytorch_model-00002-of-00003.bin",
279
+ "decoder.block.22.inter_attn.kv.weight": "pytorch_model-00002-of-00003.bin",
280
+ "decoder.block.22.inter_attn.o.bias": "pytorch_model-00002-of-00003.bin",
281
+ "decoder.block.22.inter_attn.o.weight": "pytorch_model-00002-of-00003.bin",
282
+ "decoder.block.22.inter_attn.q.bias": "pytorch_model-00002-of-00003.bin",
283
+ "decoder.block.22.inter_attn.q.weight": "pytorch_model-00002-of-00003.bin",
284
+ "decoder.block.22.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
285
+ "decoder.block.22.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
286
+ "decoder.block.22.post_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
287
+ "decoder.block.22.post_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
288
+ "decoder.block.22.post_inter_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
289
+ "decoder.block.22.post_inter_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
290
+ "decoder.block.22.self_attn.o.bias": "pytorch_model-00002-of-00003.bin",
291
+ "decoder.block.22.self_attn.o.weight": "pytorch_model-00002-of-00003.bin",
292
+ "decoder.block.22.self_attn.qkv.bias": "pytorch_model-00002-of-00003.bin",
293
+ "decoder.block.22.self_attn.qkv.weight": "pytorch_model-00002-of-00003.bin",
294
+ "decoder.block.23.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
295
+ "decoder.block.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
296
+ "decoder.block.23.inter_attn.kv.bias": "pytorch_model-00002-of-00003.bin",
297
+ "decoder.block.23.inter_attn.kv.weight": "pytorch_model-00002-of-00003.bin",
298
+ "decoder.block.23.inter_attn.o.bias": "pytorch_model-00002-of-00003.bin",
299
+ "decoder.block.23.inter_attn.o.weight": "pytorch_model-00002-of-00003.bin",
300
+ "decoder.block.23.inter_attn.q.bias": "pytorch_model-00002-of-00003.bin",
301
+ "decoder.block.23.inter_attn.q.weight": "pytorch_model-00002-of-00003.bin",
302
+ "decoder.block.23.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
303
+ "decoder.block.23.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
304
+ "decoder.block.23.post_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
305
+ "decoder.block.23.post_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
306
+ "decoder.block.23.post_inter_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
307
+ "decoder.block.23.post_inter_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
308
+ "decoder.block.23.self_attn.o.bias": "pytorch_model-00002-of-00003.bin",
309
+ "decoder.block.23.self_attn.o.weight": "pytorch_model-00002-of-00003.bin",
310
+ "decoder.block.23.self_attn.qkv.bias": "pytorch_model-00002-of-00003.bin",
311
+ "decoder.block.23.self_attn.qkv.weight": "pytorch_model-00002-of-00003.bin",
312
+ "decoder.block.24.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
313
+ "decoder.block.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
314
+ "decoder.block.24.inter_attn.kv.bias": "pytorch_model-00002-of-00003.bin",
315
+ "decoder.block.24.inter_attn.kv.weight": "pytorch_model-00002-of-00003.bin",
316
+ "decoder.block.24.inter_attn.o.bias": "pytorch_model-00002-of-00003.bin",
317
+ "decoder.block.24.inter_attn.o.weight": "pytorch_model-00002-of-00003.bin",
318
+ "decoder.block.24.inter_attn.q.bias": "pytorch_model-00002-of-00003.bin",
319
+ "decoder.block.24.inter_attn.q.weight": "pytorch_model-00002-of-00003.bin",
320
+ "decoder.block.24.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
321
+ "decoder.block.24.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
322
+ "decoder.block.24.post_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
323
+ "decoder.block.24.post_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
324
+ "decoder.block.24.post_inter_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
325
+ "decoder.block.24.post_inter_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
326
+ "decoder.block.24.self_attn.o.bias": "pytorch_model-00002-of-00003.bin",
327
+ "decoder.block.24.self_attn.o.weight": "pytorch_model-00002-of-00003.bin",
328
+ "decoder.block.24.self_attn.qkv.bias": "pytorch_model-00002-of-00003.bin",
329
+ "decoder.block.24.self_attn.qkv.weight": "pytorch_model-00002-of-00003.bin",
330
+ "decoder.block.25.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
331
+ "decoder.block.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
332
+ "decoder.block.25.inter_attn.kv.bias": "pytorch_model-00002-of-00003.bin",
333
+ "decoder.block.25.inter_attn.kv.weight": "pytorch_model-00002-of-00003.bin",
334
+ "decoder.block.25.inter_attn.o.bias": "pytorch_model-00002-of-00003.bin",
335
+ "decoder.block.25.inter_attn.o.weight": "pytorch_model-00002-of-00003.bin",
336
+ "decoder.block.25.inter_attn.q.bias": "pytorch_model-00002-of-00003.bin",
337
+ "decoder.block.25.inter_attn.q.weight": "pytorch_model-00002-of-00003.bin",
338
+ "decoder.block.25.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
339
+ "decoder.block.25.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
340
+ "decoder.block.25.post_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
341
+ "decoder.block.25.post_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
342
+ "decoder.block.25.post_inter_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
343
+ "decoder.block.25.post_inter_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
344
+ "decoder.block.25.self_attn.o.bias": "pytorch_model-00002-of-00003.bin",
345
+ "decoder.block.25.self_attn.o.weight": "pytorch_model-00002-of-00003.bin",
346
+ "decoder.block.25.self_attn.qkv.bias": "pytorch_model-00002-of-00003.bin",
347
+ "decoder.block.25.self_attn.qkv.weight": "pytorch_model-00002-of-00003.bin",
348
+ "decoder.block.26.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
349
+ "decoder.block.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
350
+ "decoder.block.26.inter_attn.kv.bias": "pytorch_model-00002-of-00003.bin",
351
+ "decoder.block.26.inter_attn.kv.weight": "pytorch_model-00002-of-00003.bin",
352
+ "decoder.block.26.inter_attn.o.bias": "pytorch_model-00002-of-00003.bin",
353
+ "decoder.block.26.inter_attn.o.weight": "pytorch_model-00002-of-00003.bin",
354
+ "decoder.block.26.inter_attn.q.bias": "pytorch_model-00002-of-00003.bin",
355
+ "decoder.block.26.inter_attn.q.weight": "pytorch_model-00002-of-00003.bin",
356
+ "decoder.block.26.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
357
+ "decoder.block.26.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
358
+ "decoder.block.26.post_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
359
+ "decoder.block.26.post_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
360
+ "decoder.block.26.post_inter_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
361
+ "decoder.block.26.post_inter_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
362
+ "decoder.block.26.self_attn.o.bias": "pytorch_model-00002-of-00003.bin",
363
+ "decoder.block.26.self_attn.o.weight": "pytorch_model-00002-of-00003.bin",
364
+ "decoder.block.26.self_attn.qkv.bias": "pytorch_model-00002-of-00003.bin",
365
+ "decoder.block.26.self_attn.qkv.weight": "pytorch_model-00002-of-00003.bin",
366
+ "decoder.block.27.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
367
+ "decoder.block.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
368
+ "decoder.block.27.inter_attn.kv.bias": "pytorch_model-00002-of-00003.bin",
369
+ "decoder.block.27.inter_attn.kv.weight": "pytorch_model-00002-of-00003.bin",
370
+ "decoder.block.27.inter_attn.o.bias": "pytorch_model-00002-of-00003.bin",
371
+ "decoder.block.27.inter_attn.o.weight": "pytorch_model-00002-of-00003.bin",
372
+ "decoder.block.27.inter_attn.q.bias": "pytorch_model-00002-of-00003.bin",
373
+ "decoder.block.27.inter_attn.q.weight": "pytorch_model-00002-of-00003.bin",
374
+ "decoder.block.27.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
375
+ "decoder.block.27.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
376
+ "decoder.block.27.post_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
377
+ "decoder.block.27.post_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
378
+ "decoder.block.27.post_inter_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
379
+ "decoder.block.27.post_inter_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
380
+ "decoder.block.27.self_attn.o.bias": "pytorch_model-00002-of-00003.bin",
381
+ "decoder.block.27.self_attn.o.weight": "pytorch_model-00002-of-00003.bin",
382
+ "decoder.block.27.self_attn.qkv.bias": "pytorch_model-00002-of-00003.bin",
383
+ "decoder.block.27.self_attn.qkv.weight": "pytorch_model-00002-of-00003.bin",
384
+ "decoder.block.28.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
385
+ "decoder.block.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
386
+ "decoder.block.28.inter_attn.kv.bias": "pytorch_model-00002-of-00003.bin",
387
+ "decoder.block.28.inter_attn.kv.weight": "pytorch_model-00002-of-00003.bin",
388
+ "decoder.block.28.inter_attn.o.bias": "pytorch_model-00002-of-00003.bin",
389
+ "decoder.block.28.inter_attn.o.weight": "pytorch_model-00002-of-00003.bin",
390
+ "decoder.block.28.inter_attn.q.bias": "pytorch_model-00002-of-00003.bin",
391
+ "decoder.block.28.inter_attn.q.weight": "pytorch_model-00002-of-00003.bin",
392
+ "decoder.block.28.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
393
+ "decoder.block.28.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
394
+ "decoder.block.28.post_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
395
+ "decoder.block.28.post_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
396
+ "decoder.block.28.post_inter_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
397
+ "decoder.block.28.post_inter_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
398
+ "decoder.block.28.self_attn.o.bias": "pytorch_model-00002-of-00003.bin",
399
+ "decoder.block.28.self_attn.o.weight": "pytorch_model-00002-of-00003.bin",
400
+ "decoder.block.28.self_attn.qkv.bias": "pytorch_model-00002-of-00003.bin",
401
+ "decoder.block.28.self_attn.qkv.weight": "pytorch_model-00002-of-00003.bin",
402
+ "decoder.block.29.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
403
+ "decoder.block.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
404
+ "decoder.block.29.inter_attn.kv.bias": "pytorch_model-00002-of-00003.bin",
405
+ "decoder.block.29.inter_attn.kv.weight": "pytorch_model-00002-of-00003.bin",
406
+ "decoder.block.29.inter_attn.o.bias": "pytorch_model-00003-of-00003.bin",
407
+ "decoder.block.29.inter_attn.o.weight": "pytorch_model-00003-of-00003.bin",
408
+ "decoder.block.29.inter_attn.q.bias": "pytorch_model-00002-of-00003.bin",
409
+ "decoder.block.29.inter_attn.q.weight": "pytorch_model-00002-of-00003.bin",
410
+ "decoder.block.29.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
411
+ "decoder.block.29.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
412
+ "decoder.block.29.post_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
413
+ "decoder.block.29.post_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
414
+ "decoder.block.29.post_inter_attn_layernorm.bias": "pytorch_model-00003-of-00003.bin",
415
+ "decoder.block.29.post_inter_attn_layernorm.weight": "pytorch_model-00003-of-00003.bin",
416
+ "decoder.block.29.self_attn.o.bias": "pytorch_model-00002-of-00003.bin",
417
+ "decoder.block.29.self_attn.o.weight": "pytorch_model-00002-of-00003.bin",
418
+ "decoder.block.29.self_attn.qkv.bias": "pytorch_model-00002-of-00003.bin",
419
+ "decoder.block.29.self_attn.qkv.weight": "pytorch_model-00002-of-00003.bin",
420
+ "decoder.block.3.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
421
+ "decoder.block.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
422
+ "decoder.block.3.inter_attn.kv.bias": "pytorch_model-00001-of-00003.bin",
423
+ "decoder.block.3.inter_attn.kv.weight": "pytorch_model-00001-of-00003.bin",
424
+ "decoder.block.3.inter_attn.o.bias": "pytorch_model-00001-of-00003.bin",
425
+ "decoder.block.3.inter_attn.o.weight": "pytorch_model-00001-of-00003.bin",
426
+ "decoder.block.3.inter_attn.q.bias": "pytorch_model-00001-of-00003.bin",
427
+ "decoder.block.3.inter_attn.q.weight": "pytorch_model-00001-of-00003.bin",
428
+ "decoder.block.3.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
429
+ "decoder.block.3.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
430
+ "decoder.block.3.post_attn_layernorm.bias": "pytorch_model-00001-of-00003.bin",
431
+ "decoder.block.3.post_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
432
+ "decoder.block.3.post_inter_attn_layernorm.bias": "pytorch_model-00001-of-00003.bin",
433
+ "decoder.block.3.post_inter_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
434
+ "decoder.block.3.self_attn.o.bias": "pytorch_model-00001-of-00003.bin",
435
+ "decoder.block.3.self_attn.o.weight": "pytorch_model-00001-of-00003.bin",
436
+ "decoder.block.3.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
437
+ "decoder.block.3.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
438
+ "decoder.block.30.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
439
+ "decoder.block.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
440
+ "decoder.block.30.inter_attn.kv.bias": "pytorch_model-00003-of-00003.bin",
441
+ "decoder.block.30.inter_attn.kv.weight": "pytorch_model-00003-of-00003.bin",
442
+ "decoder.block.30.inter_attn.o.bias": "pytorch_model-00003-of-00003.bin",
443
+ "decoder.block.30.inter_attn.o.weight": "pytorch_model-00003-of-00003.bin",
444
+ "decoder.block.30.inter_attn.q.bias": "pytorch_model-00003-of-00003.bin",
445
+ "decoder.block.30.inter_attn.q.weight": "pytorch_model-00003-of-00003.bin",
446
+ "decoder.block.30.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
447
+ "decoder.block.30.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
448
+ "decoder.block.30.post_attn_layernorm.bias": "pytorch_model-00003-of-00003.bin",
449
+ "decoder.block.30.post_attn_layernorm.weight": "pytorch_model-00003-of-00003.bin",
450
+ "decoder.block.30.post_inter_attn_layernorm.bias": "pytorch_model-00003-of-00003.bin",
451
+ "decoder.block.30.post_inter_attn_layernorm.weight": "pytorch_model-00003-of-00003.bin",
452
+ "decoder.block.30.self_attn.o.bias": "pytorch_model-00003-of-00003.bin",
453
+ "decoder.block.30.self_attn.o.weight": "pytorch_model-00003-of-00003.bin",
454
+ "decoder.block.30.self_attn.qkv.bias": "pytorch_model-00003-of-00003.bin",
455
+ "decoder.block.30.self_attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
456
+ "decoder.block.31.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
457
+ "decoder.block.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
458
+ "decoder.block.31.inter_attn.kv.bias": "pytorch_model-00003-of-00003.bin",
459
+ "decoder.block.31.inter_attn.kv.weight": "pytorch_model-00003-of-00003.bin",
460
+ "decoder.block.31.inter_attn.o.bias": "pytorch_model-00003-of-00003.bin",
461
+ "decoder.block.31.inter_attn.o.weight": "pytorch_model-00003-of-00003.bin",
462
+ "decoder.block.31.inter_attn.q.bias": "pytorch_model-00003-of-00003.bin",
463
+ "decoder.block.31.inter_attn.q.weight": "pytorch_model-00003-of-00003.bin",
464
+ "decoder.block.31.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
465
+ "decoder.block.31.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
466
+ "decoder.block.31.post_attn_layernorm.bias": "pytorch_model-00003-of-00003.bin",
467
+ "decoder.block.31.post_attn_layernorm.weight": "pytorch_model-00003-of-00003.bin",
468
+ "decoder.block.31.post_inter_attn_layernorm.bias": "pytorch_model-00003-of-00003.bin",
469
+ "decoder.block.31.post_inter_attn_layernorm.weight": "pytorch_model-00003-of-00003.bin",
470
+ "decoder.block.31.self_attn.o.bias": "pytorch_model-00003-of-00003.bin",
471
+ "decoder.block.31.self_attn.o.weight": "pytorch_model-00003-of-00003.bin",
472
+ "decoder.block.31.self_attn.qkv.bias": "pytorch_model-00003-of-00003.bin",
473
+ "decoder.block.31.self_attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
474
+ "decoder.block.32.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
475
+ "decoder.block.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
476
+ "decoder.block.32.inter_attn.kv.bias": "pytorch_model-00003-of-00003.bin",
477
+ "decoder.block.32.inter_attn.kv.weight": "pytorch_model-00003-of-00003.bin",
478
+ "decoder.block.32.inter_attn.o.bias": "pytorch_model-00003-of-00003.bin",
479
+ "decoder.block.32.inter_attn.o.weight": "pytorch_model-00003-of-00003.bin",
480
+ "decoder.block.32.inter_attn.q.bias": "pytorch_model-00003-of-00003.bin",
481
+ "decoder.block.32.inter_attn.q.weight": "pytorch_model-00003-of-00003.bin",
482
+ "decoder.block.32.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
483
+ "decoder.block.32.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
484
+ "decoder.block.32.post_attn_layernorm.bias": "pytorch_model-00003-of-00003.bin",
485
+ "decoder.block.32.post_attn_layernorm.weight": "pytorch_model-00003-of-00003.bin",
486
+ "decoder.block.32.post_inter_attn_layernorm.bias": "pytorch_model-00003-of-00003.bin",
487
+ "decoder.block.32.post_inter_attn_layernorm.weight": "pytorch_model-00003-of-00003.bin",
488
+ "decoder.block.32.self_attn.o.bias": "pytorch_model-00003-of-00003.bin",
489
+ "decoder.block.32.self_attn.o.weight": "pytorch_model-00003-of-00003.bin",
490
+ "decoder.block.32.self_attn.qkv.bias": "pytorch_model-00003-of-00003.bin",
491
+ "decoder.block.32.self_attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
492
+ "decoder.block.33.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
493
+ "decoder.block.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
494
+ "decoder.block.33.inter_attn.kv.bias": "pytorch_model-00003-of-00003.bin",
495
+ "decoder.block.33.inter_attn.kv.weight": "pytorch_model-00003-of-00003.bin",
496
+ "decoder.block.33.inter_attn.o.bias": "pytorch_model-00003-of-00003.bin",
497
+ "decoder.block.33.inter_attn.o.weight": "pytorch_model-00003-of-00003.bin",
498
+ "decoder.block.33.inter_attn.q.bias": "pytorch_model-00003-of-00003.bin",
499
+ "decoder.block.33.inter_attn.q.weight": "pytorch_model-00003-of-00003.bin",
500
+ "decoder.block.33.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
501
+ "decoder.block.33.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
502
+ "decoder.block.33.post_attn_layernorm.bias": "pytorch_model-00003-of-00003.bin",
503
+ "decoder.block.33.post_attn_layernorm.weight": "pytorch_model-00003-of-00003.bin",
504
+ "decoder.block.33.post_inter_attn_layernorm.bias": "pytorch_model-00003-of-00003.bin",
505
+ "decoder.block.33.post_inter_attn_layernorm.weight": "pytorch_model-00003-of-00003.bin",
506
+ "decoder.block.33.self_attn.o.bias": "pytorch_model-00003-of-00003.bin",
507
+ "decoder.block.33.self_attn.o.weight": "pytorch_model-00003-of-00003.bin",
508
+ "decoder.block.33.self_attn.qkv.bias": "pytorch_model-00003-of-00003.bin",
509
+ "decoder.block.33.self_attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
510
+ "decoder.block.34.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
511
+ "decoder.block.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
512
+ "decoder.block.34.inter_attn.kv.bias": "pytorch_model-00003-of-00003.bin",
513
+ "decoder.block.34.inter_attn.kv.weight": "pytorch_model-00003-of-00003.bin",
514
+ "decoder.block.34.inter_attn.o.bias": "pytorch_model-00003-of-00003.bin",
515
+ "decoder.block.34.inter_attn.o.weight": "pytorch_model-00003-of-00003.bin",
516
+ "decoder.block.34.inter_attn.q.bias": "pytorch_model-00003-of-00003.bin",
517
+ "decoder.block.34.inter_attn.q.weight": "pytorch_model-00003-of-00003.bin",
518
+ "decoder.block.34.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
519
+ "decoder.block.34.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
520
+ "decoder.block.34.post_attn_layernorm.bias": "pytorch_model-00003-of-00003.bin",
521
+ "decoder.block.34.post_attn_layernorm.weight": "pytorch_model-00003-of-00003.bin",
522
+ "decoder.block.34.post_inter_attn_layernorm.bias": "pytorch_model-00003-of-00003.bin",
523
+ "decoder.block.34.post_inter_attn_layernorm.weight": "pytorch_model-00003-of-00003.bin",
524
+ "decoder.block.34.self_attn.o.bias": "pytorch_model-00003-of-00003.bin",
525
+ "decoder.block.34.self_attn.o.weight": "pytorch_model-00003-of-00003.bin",
526
+ "decoder.block.34.self_attn.qkv.bias": "pytorch_model-00003-of-00003.bin",
527
+ "decoder.block.34.self_attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
528
+ "decoder.block.35.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
529
+ "decoder.block.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
530
+ "decoder.block.35.inter_attn.kv.bias": "pytorch_model-00003-of-00003.bin",
531
+ "decoder.block.35.inter_attn.kv.weight": "pytorch_model-00003-of-00003.bin",
532
+ "decoder.block.35.inter_attn.o.bias": "pytorch_model-00003-of-00003.bin",
533
+ "decoder.block.35.inter_attn.o.weight": "pytorch_model-00003-of-00003.bin",
534
+ "decoder.block.35.inter_attn.q.bias": "pytorch_model-00003-of-00003.bin",
535
+ "decoder.block.35.inter_attn.q.weight": "pytorch_model-00003-of-00003.bin",
536
+ "decoder.block.35.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
537
+ "decoder.block.35.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
538
+ "decoder.block.35.post_attn_layernorm.bias": "pytorch_model-00003-of-00003.bin",
539
+ "decoder.block.35.post_attn_layernorm.weight": "pytorch_model-00003-of-00003.bin",
540
+ "decoder.block.35.post_inter_attn_layernorm.bias": "pytorch_model-00003-of-00003.bin",
541
+ "decoder.block.35.post_inter_attn_layernorm.weight": "pytorch_model-00003-of-00003.bin",
542
+ "decoder.block.35.self_attn.o.bias": "pytorch_model-00003-of-00003.bin",
543
+ "decoder.block.35.self_attn.o.weight": "pytorch_model-00003-of-00003.bin",
544
+ "decoder.block.35.self_attn.qkv.bias": "pytorch_model-00003-of-00003.bin",
545
+ "decoder.block.35.self_attn.qkv.weight": "pytorch_model-00003-of-00003.bin",
546
+ "decoder.block.4.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
547
+ "decoder.block.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
548
+ "decoder.block.4.inter_attn.kv.bias": "pytorch_model-00001-of-00003.bin",
549
+ "decoder.block.4.inter_attn.kv.weight": "pytorch_model-00001-of-00003.bin",
550
+ "decoder.block.4.inter_attn.o.bias": "pytorch_model-00001-of-00003.bin",
551
+ "decoder.block.4.inter_attn.o.weight": "pytorch_model-00001-of-00003.bin",
552
+ "decoder.block.4.inter_attn.q.bias": "pytorch_model-00001-of-00003.bin",
553
+ "decoder.block.4.inter_attn.q.weight": "pytorch_model-00001-of-00003.bin",
554
+ "decoder.block.4.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
555
+ "decoder.block.4.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
556
+ "decoder.block.4.post_attn_layernorm.bias": "pytorch_model-00001-of-00003.bin",
557
+ "decoder.block.4.post_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
558
+ "decoder.block.4.post_inter_attn_layernorm.bias": "pytorch_model-00001-of-00003.bin",
559
+ "decoder.block.4.post_inter_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
560
+ "decoder.block.4.self_attn.o.bias": "pytorch_model-00001-of-00003.bin",
561
+ "decoder.block.4.self_attn.o.weight": "pytorch_model-00001-of-00003.bin",
562
+ "decoder.block.4.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
563
+ "decoder.block.4.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
564
+ "decoder.block.5.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
565
+ "decoder.block.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
566
+ "decoder.block.5.inter_attn.kv.bias": "pytorch_model-00001-of-00003.bin",
567
+ "decoder.block.5.inter_attn.kv.weight": "pytorch_model-00001-of-00003.bin",
568
+ "decoder.block.5.inter_attn.o.bias": "pytorch_model-00001-of-00003.bin",
569
+ "decoder.block.5.inter_attn.o.weight": "pytorch_model-00001-of-00003.bin",
570
+ "decoder.block.5.inter_attn.q.bias": "pytorch_model-00001-of-00003.bin",
571
+ "decoder.block.5.inter_attn.q.weight": "pytorch_model-00001-of-00003.bin",
572
+ "decoder.block.5.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
573
+ "decoder.block.5.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
574
+ "decoder.block.5.post_attn_layernorm.bias": "pytorch_model-00001-of-00003.bin",
575
+ "decoder.block.5.post_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
576
+ "decoder.block.5.post_inter_attn_layernorm.bias": "pytorch_model-00001-of-00003.bin",
577
+ "decoder.block.5.post_inter_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
578
+ "decoder.block.5.self_attn.o.bias": "pytorch_model-00001-of-00003.bin",
579
+ "decoder.block.5.self_attn.o.weight": "pytorch_model-00001-of-00003.bin",
580
+ "decoder.block.5.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
581
+ "decoder.block.5.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
582
+ "decoder.block.6.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
583
+ "decoder.block.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
584
+ "decoder.block.6.inter_attn.kv.bias": "pytorch_model-00002-of-00003.bin",
585
+ "decoder.block.6.inter_attn.kv.weight": "pytorch_model-00002-of-00003.bin",
586
+ "decoder.block.6.inter_attn.o.bias": "pytorch_model-00002-of-00003.bin",
587
+ "decoder.block.6.inter_attn.o.weight": "pytorch_model-00002-of-00003.bin",
588
+ "decoder.block.6.inter_attn.q.bias": "pytorch_model-00002-of-00003.bin",
589
+ "decoder.block.6.inter_attn.q.weight": "pytorch_model-00002-of-00003.bin",
590
+ "decoder.block.6.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
591
+ "decoder.block.6.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
592
+ "decoder.block.6.post_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
593
+ "decoder.block.6.post_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
594
+ "decoder.block.6.post_inter_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
595
+ "decoder.block.6.post_inter_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
596
+ "decoder.block.6.self_attn.o.bias": "pytorch_model-00002-of-00003.bin",
597
+ "decoder.block.6.self_attn.o.weight": "pytorch_model-00002-of-00003.bin",
598
+ "decoder.block.6.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
599
+ "decoder.block.6.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
600
+ "decoder.block.7.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
601
+ "decoder.block.7.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
602
+ "decoder.block.7.inter_attn.kv.bias": "pytorch_model-00002-of-00003.bin",
603
+ "decoder.block.7.inter_attn.kv.weight": "pytorch_model-00002-of-00003.bin",
604
+ "decoder.block.7.inter_attn.o.bias": "pytorch_model-00002-of-00003.bin",
605
+ "decoder.block.7.inter_attn.o.weight": "pytorch_model-00002-of-00003.bin",
606
+ "decoder.block.7.inter_attn.q.bias": "pytorch_model-00002-of-00003.bin",
607
+ "decoder.block.7.inter_attn.q.weight": "pytorch_model-00002-of-00003.bin",
608
+ "decoder.block.7.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
609
+ "decoder.block.7.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
610
+ "decoder.block.7.post_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
611
+ "decoder.block.7.post_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
612
+ "decoder.block.7.post_inter_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
613
+ "decoder.block.7.post_inter_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
614
+ "decoder.block.7.self_attn.o.bias": "pytorch_model-00002-of-00003.bin",
615
+ "decoder.block.7.self_attn.o.weight": "pytorch_model-00002-of-00003.bin",
616
+ "decoder.block.7.self_attn.qkv.bias": "pytorch_model-00002-of-00003.bin",
617
+ "decoder.block.7.self_attn.qkv.weight": "pytorch_model-00002-of-00003.bin",
618
+ "decoder.block.8.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
619
+ "decoder.block.8.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
620
+ "decoder.block.8.inter_attn.kv.bias": "pytorch_model-00002-of-00003.bin",
621
+ "decoder.block.8.inter_attn.kv.weight": "pytorch_model-00002-of-00003.bin",
622
+ "decoder.block.8.inter_attn.o.bias": "pytorch_model-00002-of-00003.bin",
623
+ "decoder.block.8.inter_attn.o.weight": "pytorch_model-00002-of-00003.bin",
624
+ "decoder.block.8.inter_attn.q.bias": "pytorch_model-00002-of-00003.bin",
625
+ "decoder.block.8.inter_attn.q.weight": "pytorch_model-00002-of-00003.bin",
626
+ "decoder.block.8.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
627
+ "decoder.block.8.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
628
+ "decoder.block.8.post_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
629
+ "decoder.block.8.post_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
630
+ "decoder.block.8.post_inter_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
631
+ "decoder.block.8.post_inter_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
632
+ "decoder.block.8.self_attn.o.bias": "pytorch_model-00002-of-00003.bin",
633
+ "decoder.block.8.self_attn.o.weight": "pytorch_model-00002-of-00003.bin",
634
+ "decoder.block.8.self_attn.qkv.bias": "pytorch_model-00002-of-00003.bin",
635
+ "decoder.block.8.self_attn.qkv.weight": "pytorch_model-00002-of-00003.bin",
636
+ "decoder.block.9.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
637
+ "decoder.block.9.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
638
+ "decoder.block.9.inter_attn.kv.bias": "pytorch_model-00002-of-00003.bin",
639
+ "decoder.block.9.inter_attn.kv.weight": "pytorch_model-00002-of-00003.bin",
640
+ "decoder.block.9.inter_attn.o.bias": "pytorch_model-00002-of-00003.bin",
641
+ "decoder.block.9.inter_attn.o.weight": "pytorch_model-00002-of-00003.bin",
642
+ "decoder.block.9.inter_attn.q.bias": "pytorch_model-00002-of-00003.bin",
643
+ "decoder.block.9.inter_attn.q.weight": "pytorch_model-00002-of-00003.bin",
644
+ "decoder.block.9.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
645
+ "decoder.block.9.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
646
+ "decoder.block.9.post_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
647
+ "decoder.block.9.post_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
648
+ "decoder.block.9.post_inter_attn_layernorm.bias": "pytorch_model-00002-of-00003.bin",
649
+ "decoder.block.9.post_inter_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
650
+ "decoder.block.9.self_attn.o.bias": "pytorch_model-00002-of-00003.bin",
651
+ "decoder.block.9.self_attn.o.weight": "pytorch_model-00002-of-00003.bin",
652
+ "decoder.block.9.self_attn.qkv.bias": "pytorch_model-00002-of-00003.bin",
653
+ "decoder.block.9.self_attn.qkv.weight": "pytorch_model-00002-of-00003.bin",
654
+ "decoder.final_layernorm.bias": "pytorch_model-00003-of-00003.bin",
655
+ "decoder.final_layernorm.weight": "pytorch_model-00003-of-00003.bin",
656
+ "encoder.block.0.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
657
+ "encoder.block.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
658
+ "encoder.block.0.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
659
+ "encoder.block.0.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
660
+ "encoder.block.0.post_attn_layernorm.bias": "pytorch_model-00001-of-00003.bin",
661
+ "encoder.block.0.post_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
662
+ "encoder.block.0.self_attn.o.bias": "pytorch_model-00001-of-00003.bin",
663
+ "encoder.block.0.self_attn.o.weight": "pytorch_model-00001-of-00003.bin",
664
+ "encoder.block.0.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
665
+ "encoder.block.0.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
666
+ "encoder.block.1.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
667
+ "encoder.block.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
668
+ "encoder.block.1.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
669
+ "encoder.block.1.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
670
+ "encoder.block.1.post_attn_layernorm.bias": "pytorch_model-00001-of-00003.bin",
671
+ "encoder.block.1.post_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
672
+ "encoder.block.1.self_attn.o.bias": "pytorch_model-00001-of-00003.bin",
673
+ "encoder.block.1.self_attn.o.weight": "pytorch_model-00001-of-00003.bin",
674
+ "encoder.block.1.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
675
+ "encoder.block.1.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
676
+ "encoder.block.10.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
677
+ "encoder.block.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
678
+ "encoder.block.10.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
679
+ "encoder.block.10.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
680
+ "encoder.block.10.post_attn_layernorm.bias": "pytorch_model-00001-of-00003.bin",
681
+ "encoder.block.10.post_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
682
+ "encoder.block.10.self_attn.o.bias": "pytorch_model-00001-of-00003.bin",
683
+ "encoder.block.10.self_attn.o.weight": "pytorch_model-00001-of-00003.bin",
684
+ "encoder.block.10.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
685
+ "encoder.block.10.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
686
+ "encoder.block.11.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
687
+ "encoder.block.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
688
+ "encoder.block.11.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
689
+ "encoder.block.11.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
690
+ "encoder.block.11.post_attn_layernorm.bias": "pytorch_model-00001-of-00003.bin",
691
+ "encoder.block.11.post_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
692
+ "encoder.block.11.self_attn.o.bias": "pytorch_model-00001-of-00003.bin",
693
+ "encoder.block.11.self_attn.o.weight": "pytorch_model-00001-of-00003.bin",
694
+ "encoder.block.11.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
695
+ "encoder.block.11.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
696
+ "encoder.block.2.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
697
+ "encoder.block.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
698
+ "encoder.block.2.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
699
+ "encoder.block.2.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
700
+ "encoder.block.2.post_attn_layernorm.bias": "pytorch_model-00001-of-00003.bin",
701
+ "encoder.block.2.post_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
702
+ "encoder.block.2.self_attn.o.bias": "pytorch_model-00001-of-00003.bin",
703
+ "encoder.block.2.self_attn.o.weight": "pytorch_model-00001-of-00003.bin",
704
+ "encoder.block.2.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
705
+ "encoder.block.2.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
706
+ "encoder.block.3.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
707
+ "encoder.block.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
708
+ "encoder.block.3.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
709
+ "encoder.block.3.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
710
+ "encoder.block.3.post_attn_layernorm.bias": "pytorch_model-00001-of-00003.bin",
711
+ "encoder.block.3.post_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
712
+ "encoder.block.3.self_attn.o.bias": "pytorch_model-00001-of-00003.bin",
713
+ "encoder.block.3.self_attn.o.weight": "pytorch_model-00001-of-00003.bin",
714
+ "encoder.block.3.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
715
+ "encoder.block.3.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
716
+ "encoder.block.4.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
717
+ "encoder.block.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
718
+ "encoder.block.4.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
719
+ "encoder.block.4.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
720
+ "encoder.block.4.post_attn_layernorm.bias": "pytorch_model-00001-of-00003.bin",
721
+ "encoder.block.4.post_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
722
+ "encoder.block.4.self_attn.o.bias": "pytorch_model-00001-of-00003.bin",
723
+ "encoder.block.4.self_attn.o.weight": "pytorch_model-00001-of-00003.bin",
724
+ "encoder.block.4.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
725
+ "encoder.block.4.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
726
+ "encoder.block.5.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
727
+ "encoder.block.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
728
+ "encoder.block.5.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
729
+ "encoder.block.5.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
730
+ "encoder.block.5.post_attn_layernorm.bias": "pytorch_model-00001-of-00003.bin",
731
+ "encoder.block.5.post_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
732
+ "encoder.block.5.self_attn.o.bias": "pytorch_model-00001-of-00003.bin",
733
+ "encoder.block.5.self_attn.o.weight": "pytorch_model-00001-of-00003.bin",
734
+ "encoder.block.5.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
735
+ "encoder.block.5.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
736
+ "encoder.block.6.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
737
+ "encoder.block.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
738
+ "encoder.block.6.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
739
+ "encoder.block.6.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
740
+ "encoder.block.6.post_attn_layernorm.bias": "pytorch_model-00001-of-00003.bin",
741
+ "encoder.block.6.post_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
742
+ "encoder.block.6.self_attn.o.bias": "pytorch_model-00001-of-00003.bin",
743
+ "encoder.block.6.self_attn.o.weight": "pytorch_model-00001-of-00003.bin",
744
+ "encoder.block.6.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
745
+ "encoder.block.6.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
746
+ "encoder.block.7.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
747
+ "encoder.block.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
748
+ "encoder.block.7.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
749
+ "encoder.block.7.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
750
+ "encoder.block.7.post_attn_layernorm.bias": "pytorch_model-00001-of-00003.bin",
751
+ "encoder.block.7.post_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
752
+ "encoder.block.7.self_attn.o.bias": "pytorch_model-00001-of-00003.bin",
753
+ "encoder.block.7.self_attn.o.weight": "pytorch_model-00001-of-00003.bin",
754
+ "encoder.block.7.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
755
+ "encoder.block.7.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
756
+ "encoder.block.8.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
757
+ "encoder.block.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
758
+ "encoder.block.8.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
759
+ "encoder.block.8.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
760
+ "encoder.block.8.post_attn_layernorm.bias": "pytorch_model-00001-of-00003.bin",
761
+ "encoder.block.8.post_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
762
+ "encoder.block.8.self_attn.o.bias": "pytorch_model-00001-of-00003.bin",
763
+ "encoder.block.8.self_attn.o.weight": "pytorch_model-00001-of-00003.bin",
764
+ "encoder.block.8.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
765
+ "encoder.block.8.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
766
+ "encoder.block.9.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
767
+ "encoder.block.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
768
+ "encoder.block.9.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
769
+ "encoder.block.9.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
770
+ "encoder.block.9.post_attn_layernorm.bias": "pytorch_model-00001-of-00003.bin",
771
+ "encoder.block.9.post_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
772
+ "encoder.block.9.self_attn.o.bias": "pytorch_model-00001-of-00003.bin",
773
+ "encoder.block.9.self_attn.o.weight": "pytorch_model-00001-of-00003.bin",
774
+ "encoder.block.9.self_attn.qkv.bias": "pytorch_model-00001-of-00003.bin",
775
+ "encoder.block.9.self_attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
776
+ "encoder.final_layernorm.bias": "pytorch_model-00001-of-00003.bin",
777
+ "encoder.final_layernorm.weight": "pytorch_model-00001-of-00003.bin",
778
+ "lm_head.bias": "pytorch_model-00003-of-00003.bin",
779
+ "lm_head.weight": "pytorch_model-00001-of-00003.bin",
780
+ "shared_embedding.weight": "pytorch_model-00001-of-00003.bin"
781
+ }
782
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": "</s>",
105
+ "pad_token": "<pad>",
106
+ "unk_token": "<unk>"
107
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
tokenizer_config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "clean_up_tokenization_spaces": true,
105
+ "eos_token": "</s>",
106
+ "extra_ids": 100,
107
+ "model_max_length": 1000000000000000019884624838656,
108
+ "pad_token": "<pad>",
109
+ "sp_model_kwargs": {},
110
+ "tokenizer_class": "OpenBATokenizer",
111
+ "tokenizer_file": null,
112
+ "unk_token": "<unk>"
113
+ }