wenkai commited on
Commit
8731786
1 Parent(s): 51b5d6b

Upload 7 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<s>": 1,
4
+ "<unk>": 0,
5
+ "<|im_end|>": 32000,
6
+ "<|im_start|>": 32001
7
+ }
config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Blip2ProteinOPT"
4
+ ],
5
+ "model_type": "FAPM",
6
+ "torch_dtype": "float32",
7
+ "transformers_version": "4.34.0"
8
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.34.0"
4
+ }
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,556 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14959216640
4
+ },
5
+ "weight_map": {
6
+ "Qformer.bert.embeddings.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
7
+ "Qformer.bert.embeddings.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
8
+ "Qformer.bert.embeddings.position_ids": "pytorch_model-00001-of-00002.bin",
9
+ "Qformer.bert.encoder.layer.0.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
10
+ "Qformer.bert.encoder.layer.0.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
11
+ "Qformer.bert.encoder.layer.0.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
12
+ "Qformer.bert.encoder.layer.0.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
13
+ "Qformer.bert.encoder.layer.0.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
14
+ "Qformer.bert.encoder.layer.0.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
15
+ "Qformer.bert.encoder.layer.0.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
16
+ "Qformer.bert.encoder.layer.0.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
17
+ "Qformer.bert.encoder.layer.0.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
18
+ "Qformer.bert.encoder.layer.0.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
19
+ "Qformer.bert.encoder.layer.0.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
20
+ "Qformer.bert.encoder.layer.0.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
21
+ "Qformer.bert.encoder.layer.0.crossattention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
22
+ "Qformer.bert.encoder.layer.0.crossattention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
23
+ "Qformer.bert.encoder.layer.0.crossattention.self.key.bias": "pytorch_model-00001-of-00002.bin",
24
+ "Qformer.bert.encoder.layer.0.crossattention.self.key.weight": "pytorch_model-00001-of-00002.bin",
25
+ "Qformer.bert.encoder.layer.0.crossattention.self.query.bias": "pytorch_model-00001-of-00002.bin",
26
+ "Qformer.bert.encoder.layer.0.crossattention.self.query.weight": "pytorch_model-00001-of-00002.bin",
27
+ "Qformer.bert.encoder.layer.0.crossattention.self.value.bias": "pytorch_model-00001-of-00002.bin",
28
+ "Qformer.bert.encoder.layer.0.crossattention.self.value.weight": "pytorch_model-00001-of-00002.bin",
29
+ "Qformer.bert.encoder.layer.0.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin",
30
+ "Qformer.bert.encoder.layer.0.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin",
31
+ "Qformer.bert.encoder.layer.0.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
32
+ "Qformer.bert.encoder.layer.0.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
33
+ "Qformer.bert.encoder.layer.0.output_query.dense.bias": "pytorch_model-00001-of-00002.bin",
34
+ "Qformer.bert.encoder.layer.0.output_query.dense.weight": "pytorch_model-00001-of-00002.bin",
35
+ "Qformer.bert.encoder.layer.1.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
36
+ "Qformer.bert.encoder.layer.1.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
37
+ "Qformer.bert.encoder.layer.1.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
38
+ "Qformer.bert.encoder.layer.1.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
39
+ "Qformer.bert.encoder.layer.1.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
40
+ "Qformer.bert.encoder.layer.1.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
41
+ "Qformer.bert.encoder.layer.1.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
42
+ "Qformer.bert.encoder.layer.1.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
43
+ "Qformer.bert.encoder.layer.1.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
44
+ "Qformer.bert.encoder.layer.1.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
45
+ "Qformer.bert.encoder.layer.1.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin",
46
+ "Qformer.bert.encoder.layer.1.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin",
47
+ "Qformer.bert.encoder.layer.1.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
48
+ "Qformer.bert.encoder.layer.1.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
49
+ "Qformer.bert.encoder.layer.1.output_query.dense.bias": "pytorch_model-00001-of-00002.bin",
50
+ "Qformer.bert.encoder.layer.1.output_query.dense.weight": "pytorch_model-00001-of-00002.bin",
51
+ "Qformer.bert.encoder.layer.10.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
52
+ "Qformer.bert.encoder.layer.10.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
53
+ "Qformer.bert.encoder.layer.10.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
54
+ "Qformer.bert.encoder.layer.10.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
55
+ "Qformer.bert.encoder.layer.10.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
56
+ "Qformer.bert.encoder.layer.10.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
57
+ "Qformer.bert.encoder.layer.10.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
58
+ "Qformer.bert.encoder.layer.10.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
59
+ "Qformer.bert.encoder.layer.10.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
60
+ "Qformer.bert.encoder.layer.10.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
61
+ "Qformer.bert.encoder.layer.10.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
62
+ "Qformer.bert.encoder.layer.10.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
63
+ "Qformer.bert.encoder.layer.10.crossattention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
64
+ "Qformer.bert.encoder.layer.10.crossattention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
65
+ "Qformer.bert.encoder.layer.10.crossattention.self.key.bias": "pytorch_model-00001-of-00002.bin",
66
+ "Qformer.bert.encoder.layer.10.crossattention.self.key.weight": "pytorch_model-00001-of-00002.bin",
67
+ "Qformer.bert.encoder.layer.10.crossattention.self.query.bias": "pytorch_model-00001-of-00002.bin",
68
+ "Qformer.bert.encoder.layer.10.crossattention.self.query.weight": "pytorch_model-00001-of-00002.bin",
69
+ "Qformer.bert.encoder.layer.10.crossattention.self.value.bias": "pytorch_model-00001-of-00002.bin",
70
+ "Qformer.bert.encoder.layer.10.crossattention.self.value.weight": "pytorch_model-00001-of-00002.bin",
71
+ "Qformer.bert.encoder.layer.10.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin",
72
+ "Qformer.bert.encoder.layer.10.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin",
73
+ "Qformer.bert.encoder.layer.10.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
74
+ "Qformer.bert.encoder.layer.10.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
75
+ "Qformer.bert.encoder.layer.10.output_query.dense.bias": "pytorch_model-00001-of-00002.bin",
76
+ "Qformer.bert.encoder.layer.10.output_query.dense.weight": "pytorch_model-00001-of-00002.bin",
77
+ "Qformer.bert.encoder.layer.11.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
78
+ "Qformer.bert.encoder.layer.11.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
79
+ "Qformer.bert.encoder.layer.11.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
80
+ "Qformer.bert.encoder.layer.11.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
81
+ "Qformer.bert.encoder.layer.11.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
82
+ "Qformer.bert.encoder.layer.11.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
83
+ "Qformer.bert.encoder.layer.11.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
84
+ "Qformer.bert.encoder.layer.11.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
85
+ "Qformer.bert.encoder.layer.11.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
86
+ "Qformer.bert.encoder.layer.11.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
87
+ "Qformer.bert.encoder.layer.11.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin",
88
+ "Qformer.bert.encoder.layer.11.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin",
89
+ "Qformer.bert.encoder.layer.11.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
90
+ "Qformer.bert.encoder.layer.11.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
91
+ "Qformer.bert.encoder.layer.11.output_query.dense.bias": "pytorch_model-00001-of-00002.bin",
92
+ "Qformer.bert.encoder.layer.11.output_query.dense.weight": "pytorch_model-00001-of-00002.bin",
93
+ "Qformer.bert.encoder.layer.2.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
94
+ "Qformer.bert.encoder.layer.2.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
95
+ "Qformer.bert.encoder.layer.2.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
96
+ "Qformer.bert.encoder.layer.2.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
97
+ "Qformer.bert.encoder.layer.2.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
98
+ "Qformer.bert.encoder.layer.2.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
99
+ "Qformer.bert.encoder.layer.2.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
100
+ "Qformer.bert.encoder.layer.2.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
101
+ "Qformer.bert.encoder.layer.2.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
102
+ "Qformer.bert.encoder.layer.2.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
103
+ "Qformer.bert.encoder.layer.2.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
104
+ "Qformer.bert.encoder.layer.2.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
105
+ "Qformer.bert.encoder.layer.2.crossattention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
106
+ "Qformer.bert.encoder.layer.2.crossattention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
107
+ "Qformer.bert.encoder.layer.2.crossattention.self.key.bias": "pytorch_model-00001-of-00002.bin",
108
+ "Qformer.bert.encoder.layer.2.crossattention.self.key.weight": "pytorch_model-00001-of-00002.bin",
109
+ "Qformer.bert.encoder.layer.2.crossattention.self.query.bias": "pytorch_model-00001-of-00002.bin",
110
+ "Qformer.bert.encoder.layer.2.crossattention.self.query.weight": "pytorch_model-00001-of-00002.bin",
111
+ "Qformer.bert.encoder.layer.2.crossattention.self.value.bias": "pytorch_model-00001-of-00002.bin",
112
+ "Qformer.bert.encoder.layer.2.crossattention.self.value.weight": "pytorch_model-00001-of-00002.bin",
113
+ "Qformer.bert.encoder.layer.2.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin",
114
+ "Qformer.bert.encoder.layer.2.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin",
115
+ "Qformer.bert.encoder.layer.2.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
116
+ "Qformer.bert.encoder.layer.2.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
117
+ "Qformer.bert.encoder.layer.2.output_query.dense.bias": "pytorch_model-00001-of-00002.bin",
118
+ "Qformer.bert.encoder.layer.2.output_query.dense.weight": "pytorch_model-00001-of-00002.bin",
119
+ "Qformer.bert.encoder.layer.3.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
120
+ "Qformer.bert.encoder.layer.3.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
121
+ "Qformer.bert.encoder.layer.3.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
122
+ "Qformer.bert.encoder.layer.3.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
123
+ "Qformer.bert.encoder.layer.3.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
124
+ "Qformer.bert.encoder.layer.3.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
125
+ "Qformer.bert.encoder.layer.3.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
126
+ "Qformer.bert.encoder.layer.3.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
127
+ "Qformer.bert.encoder.layer.3.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
128
+ "Qformer.bert.encoder.layer.3.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
129
+ "Qformer.bert.encoder.layer.3.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin",
130
+ "Qformer.bert.encoder.layer.3.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin",
131
+ "Qformer.bert.encoder.layer.3.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
132
+ "Qformer.bert.encoder.layer.3.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
133
+ "Qformer.bert.encoder.layer.3.output_query.dense.bias": "pytorch_model-00001-of-00002.bin",
134
+ "Qformer.bert.encoder.layer.3.output_query.dense.weight": "pytorch_model-00001-of-00002.bin",
135
+ "Qformer.bert.encoder.layer.4.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
136
+ "Qformer.bert.encoder.layer.4.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
137
+ "Qformer.bert.encoder.layer.4.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
138
+ "Qformer.bert.encoder.layer.4.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
139
+ "Qformer.bert.encoder.layer.4.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
140
+ "Qformer.bert.encoder.layer.4.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
141
+ "Qformer.bert.encoder.layer.4.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
142
+ "Qformer.bert.encoder.layer.4.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
143
+ "Qformer.bert.encoder.layer.4.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
144
+ "Qformer.bert.encoder.layer.4.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
145
+ "Qformer.bert.encoder.layer.4.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
146
+ "Qformer.bert.encoder.layer.4.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
147
+ "Qformer.bert.encoder.layer.4.crossattention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
148
+ "Qformer.bert.encoder.layer.4.crossattention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
149
+ "Qformer.bert.encoder.layer.4.crossattention.self.key.bias": "pytorch_model-00001-of-00002.bin",
150
+ "Qformer.bert.encoder.layer.4.crossattention.self.key.weight": "pytorch_model-00001-of-00002.bin",
151
+ "Qformer.bert.encoder.layer.4.crossattention.self.query.bias": "pytorch_model-00001-of-00002.bin",
152
+ "Qformer.bert.encoder.layer.4.crossattention.self.query.weight": "pytorch_model-00001-of-00002.bin",
153
+ "Qformer.bert.encoder.layer.4.crossattention.self.value.bias": "pytorch_model-00001-of-00002.bin",
154
+ "Qformer.bert.encoder.layer.4.crossattention.self.value.weight": "pytorch_model-00001-of-00002.bin",
155
+ "Qformer.bert.encoder.layer.4.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin",
156
+ "Qformer.bert.encoder.layer.4.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin",
157
+ "Qformer.bert.encoder.layer.4.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
158
+ "Qformer.bert.encoder.layer.4.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
159
+ "Qformer.bert.encoder.layer.4.output_query.dense.bias": "pytorch_model-00001-of-00002.bin",
160
+ "Qformer.bert.encoder.layer.4.output_query.dense.weight": "pytorch_model-00001-of-00002.bin",
161
+ "Qformer.bert.encoder.layer.5.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
162
+ "Qformer.bert.encoder.layer.5.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
163
+ "Qformer.bert.encoder.layer.5.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
164
+ "Qformer.bert.encoder.layer.5.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
165
+ "Qformer.bert.encoder.layer.5.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
166
+ "Qformer.bert.encoder.layer.5.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
167
+ "Qformer.bert.encoder.layer.5.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
168
+ "Qformer.bert.encoder.layer.5.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
169
+ "Qformer.bert.encoder.layer.5.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
170
+ "Qformer.bert.encoder.layer.5.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
171
+ "Qformer.bert.encoder.layer.5.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin",
172
+ "Qformer.bert.encoder.layer.5.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin",
173
+ "Qformer.bert.encoder.layer.5.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
174
+ "Qformer.bert.encoder.layer.5.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
175
+ "Qformer.bert.encoder.layer.5.output_query.dense.bias": "pytorch_model-00001-of-00002.bin",
176
+ "Qformer.bert.encoder.layer.5.output_query.dense.weight": "pytorch_model-00001-of-00002.bin",
177
+ "Qformer.bert.encoder.layer.6.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
178
+ "Qformer.bert.encoder.layer.6.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
179
+ "Qformer.bert.encoder.layer.6.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
180
+ "Qformer.bert.encoder.layer.6.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
181
+ "Qformer.bert.encoder.layer.6.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
182
+ "Qformer.bert.encoder.layer.6.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
183
+ "Qformer.bert.encoder.layer.6.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
184
+ "Qformer.bert.encoder.layer.6.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
185
+ "Qformer.bert.encoder.layer.6.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
186
+ "Qformer.bert.encoder.layer.6.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
187
+ "Qformer.bert.encoder.layer.6.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
188
+ "Qformer.bert.encoder.layer.6.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
189
+ "Qformer.bert.encoder.layer.6.crossattention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
190
+ "Qformer.bert.encoder.layer.6.crossattention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
191
+ "Qformer.bert.encoder.layer.6.crossattention.self.key.bias": "pytorch_model-00001-of-00002.bin",
192
+ "Qformer.bert.encoder.layer.6.crossattention.self.key.weight": "pytorch_model-00001-of-00002.bin",
193
+ "Qformer.bert.encoder.layer.6.crossattention.self.query.bias": "pytorch_model-00001-of-00002.bin",
194
+ "Qformer.bert.encoder.layer.6.crossattention.self.query.weight": "pytorch_model-00001-of-00002.bin",
195
+ "Qformer.bert.encoder.layer.6.crossattention.self.value.bias": "pytorch_model-00001-of-00002.bin",
196
+ "Qformer.bert.encoder.layer.6.crossattention.self.value.weight": "pytorch_model-00001-of-00002.bin",
197
+ "Qformer.bert.encoder.layer.6.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin",
198
+ "Qformer.bert.encoder.layer.6.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin",
199
+ "Qformer.bert.encoder.layer.6.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
200
+ "Qformer.bert.encoder.layer.6.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
201
+ "Qformer.bert.encoder.layer.6.output_query.dense.bias": "pytorch_model-00001-of-00002.bin",
202
+ "Qformer.bert.encoder.layer.6.output_query.dense.weight": "pytorch_model-00001-of-00002.bin",
203
+ "Qformer.bert.encoder.layer.7.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
204
+ "Qformer.bert.encoder.layer.7.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
205
+ "Qformer.bert.encoder.layer.7.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
206
+ "Qformer.bert.encoder.layer.7.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
207
+ "Qformer.bert.encoder.layer.7.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
208
+ "Qformer.bert.encoder.layer.7.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
209
+ "Qformer.bert.encoder.layer.7.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
210
+ "Qformer.bert.encoder.layer.7.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
211
+ "Qformer.bert.encoder.layer.7.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
212
+ "Qformer.bert.encoder.layer.7.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
213
+ "Qformer.bert.encoder.layer.7.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin",
214
+ "Qformer.bert.encoder.layer.7.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin",
215
+ "Qformer.bert.encoder.layer.7.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
216
+ "Qformer.bert.encoder.layer.7.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
217
+ "Qformer.bert.encoder.layer.7.output_query.dense.bias": "pytorch_model-00001-of-00002.bin",
218
+ "Qformer.bert.encoder.layer.7.output_query.dense.weight": "pytorch_model-00001-of-00002.bin",
219
+ "Qformer.bert.encoder.layer.8.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
220
+ "Qformer.bert.encoder.layer.8.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
221
+ "Qformer.bert.encoder.layer.8.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
222
+ "Qformer.bert.encoder.layer.8.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
223
+ "Qformer.bert.encoder.layer.8.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
224
+ "Qformer.bert.encoder.layer.8.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
225
+ "Qformer.bert.encoder.layer.8.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
226
+ "Qformer.bert.encoder.layer.8.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
227
+ "Qformer.bert.encoder.layer.8.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
228
+ "Qformer.bert.encoder.layer.8.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
229
+ "Qformer.bert.encoder.layer.8.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
230
+ "Qformer.bert.encoder.layer.8.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
231
+ "Qformer.bert.encoder.layer.8.crossattention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
232
+ "Qformer.bert.encoder.layer.8.crossattention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
233
+ "Qformer.bert.encoder.layer.8.crossattention.self.key.bias": "pytorch_model-00001-of-00002.bin",
234
+ "Qformer.bert.encoder.layer.8.crossattention.self.key.weight": "pytorch_model-00001-of-00002.bin",
235
+ "Qformer.bert.encoder.layer.8.crossattention.self.query.bias": "pytorch_model-00001-of-00002.bin",
236
+ "Qformer.bert.encoder.layer.8.crossattention.self.query.weight": "pytorch_model-00001-of-00002.bin",
237
+ "Qformer.bert.encoder.layer.8.crossattention.self.value.bias": "pytorch_model-00001-of-00002.bin",
238
+ "Qformer.bert.encoder.layer.8.crossattention.self.value.weight": "pytorch_model-00001-of-00002.bin",
239
+ "Qformer.bert.encoder.layer.8.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin",
240
+ "Qformer.bert.encoder.layer.8.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin",
241
+ "Qformer.bert.encoder.layer.8.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
242
+ "Qformer.bert.encoder.layer.8.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
243
+ "Qformer.bert.encoder.layer.8.output_query.dense.bias": "pytorch_model-00001-of-00002.bin",
244
+ "Qformer.bert.encoder.layer.8.output_query.dense.weight": "pytorch_model-00001-of-00002.bin",
245
+ "Qformer.bert.encoder.layer.9.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
246
+ "Qformer.bert.encoder.layer.9.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
247
+ "Qformer.bert.encoder.layer.9.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
248
+ "Qformer.bert.encoder.layer.9.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
249
+ "Qformer.bert.encoder.layer.9.attention.self.key.bias": "pytorch_model-00001-of-00002.bin",
250
+ "Qformer.bert.encoder.layer.9.attention.self.key.weight": "pytorch_model-00001-of-00002.bin",
251
+ "Qformer.bert.encoder.layer.9.attention.self.query.bias": "pytorch_model-00001-of-00002.bin",
252
+ "Qformer.bert.encoder.layer.9.attention.self.query.weight": "pytorch_model-00001-of-00002.bin",
253
+ "Qformer.bert.encoder.layer.9.attention.self.value.bias": "pytorch_model-00001-of-00002.bin",
254
+ "Qformer.bert.encoder.layer.9.attention.self.value.weight": "pytorch_model-00001-of-00002.bin",
255
+ "Qformer.bert.encoder.layer.9.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin",
256
+ "Qformer.bert.encoder.layer.9.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin",
257
+ "Qformer.bert.encoder.layer.9.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
258
+ "Qformer.bert.encoder.layer.9.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
259
+ "Qformer.bert.encoder.layer.9.output_query.dense.bias": "pytorch_model-00001-of-00002.bin",
260
+ "Qformer.bert.encoder.layer.9.output_query.dense.weight": "pytorch_model-00001-of-00002.bin",
261
+ "opt_model.lm_head.weight": "pytorch_model-00002-of-00002.bin",
262
+ "opt_model.model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
263
+ "opt_model.model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
264
+ "opt_model.model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
265
+ "opt_model.model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
266
+ "opt_model.model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
267
+ "opt_model.model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
268
+ "opt_model.model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
269
+ "opt_model.model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
270
+ "opt_model.model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
271
+ "opt_model.model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
272
+ "opt_model.model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
273
+ "opt_model.model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
274
+ "opt_model.model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
275
+ "opt_model.model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
276
+ "opt_model.model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
277
+ "opt_model.model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
278
+ "opt_model.model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
279
+ "opt_model.model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
280
+ "opt_model.model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
281
+ "opt_model.model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
282
+ "opt_model.model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
283
+ "opt_model.model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
284
+ "opt_model.model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
285
+ "opt_model.model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
286
+ "opt_model.model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
287
+ "opt_model.model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
288
+ "opt_model.model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
289
+ "opt_model.model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
290
+ "opt_model.model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
291
+ "opt_model.model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
292
+ "opt_model.model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
293
+ "opt_model.model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
294
+ "opt_model.model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
295
+ "opt_model.model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
296
+ "opt_model.model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
297
+ "opt_model.model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
298
+ "opt_model.model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
299
+ "opt_model.model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
300
+ "opt_model.model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
301
+ "opt_model.model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
302
+ "opt_model.model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
303
+ "opt_model.model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
304
+ "opt_model.model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
305
+ "opt_model.model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
306
+ "opt_model.model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
307
+ "opt_model.model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
308
+ "opt_model.model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
309
+ "opt_model.model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
310
+ "opt_model.model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
311
+ "opt_model.model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
312
+ "opt_model.model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
313
+ "opt_model.model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
314
+ "opt_model.model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
315
+ "opt_model.model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
316
+ "opt_model.model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
317
+ "opt_model.model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
318
+ "opt_model.model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
319
+ "opt_model.model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
320
+ "opt_model.model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
321
+ "opt_model.model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
322
+ "opt_model.model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
323
+ "opt_model.model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
324
+ "opt_model.model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
325
+ "opt_model.model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
326
+ "opt_model.model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
327
+ "opt_model.model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
328
+ "opt_model.model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
329
+ "opt_model.model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
330
+ "opt_model.model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
331
+ "opt_model.model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
332
+ "opt_model.model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
333
+ "opt_model.model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
334
+ "opt_model.model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
335
+ "opt_model.model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
336
+ "opt_model.model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
337
+ "opt_model.model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
338
+ "opt_model.model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
339
+ "opt_model.model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
340
+ "opt_model.model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
341
+ "opt_model.model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
342
+ "opt_model.model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
343
+ "opt_model.model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
344
+ "opt_model.model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
345
+ "opt_model.model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
346
+ "opt_model.model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
347
+ "opt_model.model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
348
+ "opt_model.model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
349
+ "opt_model.model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
350
+ "opt_model.model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
351
+ "opt_model.model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
352
+ "opt_model.model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
353
+ "opt_model.model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
354
+ "opt_model.model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
355
+ "opt_model.model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
356
+ "opt_model.model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
357
+ "opt_model.model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
358
+ "opt_model.model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
359
+ "opt_model.model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
360
+ "opt_model.model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
361
+ "opt_model.model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
362
+ "opt_model.model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
363
+ "opt_model.model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
364
+ "opt_model.model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
365
+ "opt_model.model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
366
+ "opt_model.model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
367
+ "opt_model.model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
368
+ "opt_model.model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
369
+ "opt_model.model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
370
+ "opt_model.model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
371
+ "opt_model.model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
372
+ "opt_model.model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
373
+ "opt_model.model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
374
+ "opt_model.model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
375
+ "opt_model.model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
376
+ "opt_model.model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
377
+ "opt_model.model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
378
+ "opt_model.model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
379
+ "opt_model.model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
380
+ "opt_model.model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
381
+ "opt_model.model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
382
+ "opt_model.model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
383
+ "opt_model.model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
384
+ "opt_model.model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
385
+ "opt_model.model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
386
+ "opt_model.model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
387
+ "opt_model.model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
388
+ "opt_model.model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
389
+ "opt_model.model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
390
+ "opt_model.model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
391
+ "opt_model.model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
392
+ "opt_model.model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
393
+ "opt_model.model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
394
+ "opt_model.model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
395
+ "opt_model.model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
396
+ "opt_model.model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
397
+ "opt_model.model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
398
+ "opt_model.model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
399
+ "opt_model.model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
400
+ "opt_model.model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
401
+ "opt_model.model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
402
+ "opt_model.model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
403
+ "opt_model.model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
404
+ "opt_model.model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
405
+ "opt_model.model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
406
+ "opt_model.model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
407
+ "opt_model.model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
408
+ "opt_model.model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
409
+ "opt_model.model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
410
+ "opt_model.model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
411
+ "opt_model.model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
412
+ "opt_model.model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
413
+ "opt_model.model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
414
+ "opt_model.model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
415
+ "opt_model.model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
416
+ "opt_model.model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
417
+ "opt_model.model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
418
+ "opt_model.model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
419
+ "opt_model.model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
420
+ "opt_model.model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
421
+ "opt_model.model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
422
+ "opt_model.model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
423
+ "opt_model.model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
424
+ "opt_model.model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
425
+ "opt_model.model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
426
+ "opt_model.model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
427
+ "opt_model.model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
428
+ "opt_model.model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
429
+ "opt_model.model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
430
+ "opt_model.model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
431
+ "opt_model.model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
432
+ "opt_model.model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
433
+ "opt_model.model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
434
+ "opt_model.model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
435
+ "opt_model.model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
436
+ "opt_model.model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
437
+ "opt_model.model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
438
+ "opt_model.model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
439
+ "opt_model.model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
440
+ "opt_model.model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
441
+ "opt_model.model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
442
+ "opt_model.model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
443
+ "opt_model.model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
444
+ "opt_model.model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
445
+ "opt_model.model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
446
+ "opt_model.model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
447
+ "opt_model.model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
448
+ "opt_model.model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
449
+ "opt_model.model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
450
+ "opt_model.model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
451
+ "opt_model.model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
452
+ "opt_model.model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
453
+ "opt_model.model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
454
+ "opt_model.model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
455
+ "opt_model.model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
456
+ "opt_model.model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
457
+ "opt_model.model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
458
+ "opt_model.model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
459
+ "opt_model.model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
460
+ "opt_model.model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
461
+ "opt_model.model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
462
+ "opt_model.model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
463
+ "opt_model.model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
464
+ "opt_model.model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
465
+ "opt_model.model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
466
+ "opt_model.model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
467
+ "opt_model.model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
468
+ "opt_model.model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
469
+ "opt_model.model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
470
+ "opt_model.model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
471
+ "opt_model.model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
472
+ "opt_model.model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
473
+ "opt_model.model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
474
+ "opt_model.model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
475
+ "opt_model.model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
476
+ "opt_model.model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
477
+ "opt_model.model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
478
+ "opt_model.model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
479
+ "opt_model.model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
480
+ "opt_model.model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
481
+ "opt_model.model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
482
+ "opt_model.model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
483
+ "opt_model.model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
484
+ "opt_model.model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
485
+ "opt_model.model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
486
+ "opt_model.model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
487
+ "opt_model.model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
488
+ "opt_model.model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
489
+ "opt_model.model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
490
+ "opt_model.model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
491
+ "opt_model.model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
492
+ "opt_model.model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
493
+ "opt_model.model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
494
+ "opt_model.model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
495
+ "opt_model.model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
496
+ "opt_model.model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
497
+ "opt_model.model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
498
+ "opt_model.model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
499
+ "opt_model.model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
500
+ "opt_model.model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
501
+ "opt_model.model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
502
+ "opt_model.model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
503
+ "opt_model.model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
504
+ "opt_model.model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
505
+ "opt_model.model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
506
+ "opt_model.model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
507
+ "opt_model.model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
508
+ "opt_model.model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
509
+ "opt_model.model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
510
+ "opt_model.model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
511
+ "opt_model.model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
512
+ "opt_model.model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
513
+ "opt_model.model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
514
+ "opt_model.model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
515
+ "opt_model.model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
516
+ "opt_model.model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
517
+ "opt_model.model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
518
+ "opt_model.model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
519
+ "opt_model.model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
520
+ "opt_model.model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
521
+ "opt_model.model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
522
+ "opt_model.model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
523
+ "opt_model.model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
524
+ "opt_model.model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
525
+ "opt_model.model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
526
+ "opt_model.model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
527
+ "opt_model.model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
528
+ "opt_model.model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
529
+ "opt_model.model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
530
+ "opt_model.model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
531
+ "opt_model.model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
532
+ "opt_model.model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
533
+ "opt_model.model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
534
+ "opt_model.model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
535
+ "opt_model.model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
536
+ "opt_model.model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
537
+ "opt_model.model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
538
+ "opt_model.model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
539
+ "opt_model.model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
540
+ "opt_model.model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
541
+ "opt_model.model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
542
+ "opt_model.model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
543
+ "opt_model.model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
544
+ "opt_model.model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
545
+ "opt_model.model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
546
+ "opt_model.model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
547
+ "opt_model.model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
548
+ "opt_model.model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
549
+ "opt_model.model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
550
+ "opt_model.model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
551
+ "opt_model.model.norm.weight": "pytorch_model-00002-of-00002.bin",
552
+ "opt_proj.bias": "pytorch_model-00002-of-00002.bin",
553
+ "opt_proj.weight": "pytorch_model-00002-of-00002.bin",
554
+ "query_tokens": "pytorch_model-00001-of-00002.bin"
555
+ }
556
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>",
6
+ "<|im_end|>",
7
+ "<|im_start|>"
8
+ ],
9
+ "bos_token": "<s>",
10
+ "eos_token": "<|im_end|>",
11
+ "pad_token": "<pad>",
12
+ "unk_token": "<unk>"
13
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<|im_end|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|im_start|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ }
45
+ },
46
+ "additional_special_tokens": [
47
+ "<unk>",
48
+ "<s>",
49
+ "</s>",
50
+ "<|im_end|>",
51
+ "<|im_start|>"
52
+ ],
53
+ "bos_token": "<s>",
54
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
55
+ "clean_up_tokenization_spaces": false,
56
+ "eos_token": "<|im_end|>",
57
+ "legacy": true,
58
+ "model_max_length": 1000000000000000019884624838656,
59
+ "pad_token": "<pad>",
60
+ "sp_model_kwargs": {},
61
+ "spaces_between_special_tokens": false,
62
+ "tokenizer_class": "LlamaTokenizer",
63
+ "tokenizer_file": null,
64
+ "trust_remote_code": false,
65
+ "unk_token": "<unk>",
66
+ "use_default_system_prompt": true,
67
+ "use_fast": false
68
+ }