hllj commited on
Commit
6f91f35
1 Parent(s): 3554a65

Upload BloomForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bigscience/bloomz-7b1",
3
+ "apply_residual_connection_post_layernorm": false,
4
+ "architectures": [
5
+ "BloomForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "attention_softmax_in_fp32": true,
9
+ "bias_dropout_fusion": true,
10
+ "bos_token_id": 1,
11
+ "eos_token_id": 2,
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 4096,
14
+ "initializer_range": 0.02,
15
+ "layer_norm_epsilon": 1e-05,
16
+ "masked_softmax_fusion": true,
17
+ "model_type": "bloom",
18
+ "n_head": 32,
19
+ "n_inner": null,
20
+ "n_layer": 30,
21
+ "offset_alibi": 100,
22
+ "pad_token_id": 3,
23
+ "pretraining_tp": 1,
24
+ "seq_length": 2048,
25
+ "skip_bias_add": true,
26
+ "skip_bias_add_qkv": false,
27
+ "slow_but_exact": false,
28
+ "torch_dtype": "float16",
29
+ "transformers_version": "4.36.2",
30
+ "unk_token_id": 0,
31
+ "use_cache": true,
32
+ "vocab_size": 250880
33
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 3,
6
+ "transformers_version": "4.36.2"
7
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c54dbf40954ab509b0b7def8b086dd364e1ed29774205e36b8aebc5ea40f5cd6
3
+ size 4975258008
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d01817368c8d363a3ce93129fa4982d561db31986f3ae152eafe23d62da9048
3
+ size 4866712640
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a68eef13caa855e901d2c9174bee74df7692675fe969dd42c34db1f7507e0d7f
3
+ size 4296104456
model.safetensors.index.json ADDED
@@ -0,0 +1,372 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14138032128
4
+ },
5
+ "weight_map": {
6
+ "transformer.h.0.input_layernorm.bias": "model-00001-of-00003.safetensors",
7
+ "transformer.h.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
8
+ "transformer.h.0.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
9
+ "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
10
+ "transformer.h.0.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
11
+ "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
12
+ "transformer.h.0.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
13
+ "transformer.h.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
14
+ "transformer.h.0.self_attention.dense.bias": "model-00001-of-00003.safetensors",
15
+ "transformer.h.0.self_attention.dense.weight": "model-00001-of-00003.safetensors",
16
+ "transformer.h.0.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
17
+ "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
18
+ "transformer.h.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
19
+ "transformer.h.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
20
+ "transformer.h.1.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
21
+ "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
22
+ "transformer.h.1.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
23
+ "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
24
+ "transformer.h.1.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
25
+ "transformer.h.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
26
+ "transformer.h.1.self_attention.dense.bias": "model-00001-of-00003.safetensors",
27
+ "transformer.h.1.self_attention.dense.weight": "model-00001-of-00003.safetensors",
28
+ "transformer.h.1.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
29
+ "transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
30
+ "transformer.h.10.input_layernorm.bias": "model-00002-of-00003.safetensors",
31
+ "transformer.h.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
32
+ "transformer.h.10.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
33
+ "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
34
+ "transformer.h.10.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
35
+ "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
36
+ "transformer.h.10.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
37
+ "transformer.h.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
38
+ "transformer.h.10.self_attention.dense.bias": "model-00002-of-00003.safetensors",
39
+ "transformer.h.10.self_attention.dense.weight": "model-00002-of-00003.safetensors",
40
+ "transformer.h.10.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
41
+ "transformer.h.10.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
42
+ "transformer.h.11.input_layernorm.bias": "model-00002-of-00003.safetensors",
43
+ "transformer.h.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
44
+ "transformer.h.11.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
45
+ "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
46
+ "transformer.h.11.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
47
+ "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
48
+ "transformer.h.11.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
49
+ "transformer.h.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
50
+ "transformer.h.11.self_attention.dense.bias": "model-00002-of-00003.safetensors",
51
+ "transformer.h.11.self_attention.dense.weight": "model-00002-of-00003.safetensors",
52
+ "transformer.h.11.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
53
+ "transformer.h.11.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
54
+ "transformer.h.12.input_layernorm.bias": "model-00002-of-00003.safetensors",
55
+ "transformer.h.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
56
+ "transformer.h.12.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
57
+ "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
58
+ "transformer.h.12.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
59
+ "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
60
+ "transformer.h.12.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
61
+ "transformer.h.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
62
+ "transformer.h.12.self_attention.dense.bias": "model-00002-of-00003.safetensors",
63
+ "transformer.h.12.self_attention.dense.weight": "model-00002-of-00003.safetensors",
64
+ "transformer.h.12.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
65
+ "transformer.h.12.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
66
+ "transformer.h.13.input_layernorm.bias": "model-00002-of-00003.safetensors",
67
+ "transformer.h.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
68
+ "transformer.h.13.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
69
+ "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
70
+ "transformer.h.13.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
71
+ "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
72
+ "transformer.h.13.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
73
+ "transformer.h.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
74
+ "transformer.h.13.self_attention.dense.bias": "model-00002-of-00003.safetensors",
75
+ "transformer.h.13.self_attention.dense.weight": "model-00002-of-00003.safetensors",
76
+ "transformer.h.13.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
77
+ "transformer.h.13.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
78
+ "transformer.h.14.input_layernorm.bias": "model-00002-of-00003.safetensors",
79
+ "transformer.h.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
80
+ "transformer.h.14.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
81
+ "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
82
+ "transformer.h.14.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
83
+ "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
84
+ "transformer.h.14.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
85
+ "transformer.h.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
86
+ "transformer.h.14.self_attention.dense.bias": "model-00002-of-00003.safetensors",
87
+ "transformer.h.14.self_attention.dense.weight": "model-00002-of-00003.safetensors",
88
+ "transformer.h.14.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
89
+ "transformer.h.14.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
90
+ "transformer.h.15.input_layernorm.bias": "model-00002-of-00003.safetensors",
91
+ "transformer.h.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
92
+ "transformer.h.15.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
93
+ "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
94
+ "transformer.h.15.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
95
+ "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
96
+ "transformer.h.15.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
97
+ "transformer.h.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
98
+ "transformer.h.15.self_attention.dense.bias": "model-00002-of-00003.safetensors",
99
+ "transformer.h.15.self_attention.dense.weight": "model-00002-of-00003.safetensors",
100
+ "transformer.h.15.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
101
+ "transformer.h.15.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
102
+ "transformer.h.16.input_layernorm.bias": "model-00002-of-00003.safetensors",
103
+ "transformer.h.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
104
+ "transformer.h.16.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
105
+ "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
106
+ "transformer.h.16.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
107
+ "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
108
+ "transformer.h.16.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
109
+ "transformer.h.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
110
+ "transformer.h.16.self_attention.dense.bias": "model-00002-of-00003.safetensors",
111
+ "transformer.h.16.self_attention.dense.weight": "model-00002-of-00003.safetensors",
112
+ "transformer.h.16.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
113
+ "transformer.h.16.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
114
+ "transformer.h.17.input_layernorm.bias": "model-00002-of-00003.safetensors",
115
+ "transformer.h.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
116
+ "transformer.h.17.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
117
+ "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
118
+ "transformer.h.17.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
119
+ "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
120
+ "transformer.h.17.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
121
+ "transformer.h.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
122
+ "transformer.h.17.self_attention.dense.bias": "model-00002-of-00003.safetensors",
123
+ "transformer.h.17.self_attention.dense.weight": "model-00002-of-00003.safetensors",
124
+ "transformer.h.17.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
125
+ "transformer.h.17.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
126
+ "transformer.h.18.input_layernorm.bias": "model-00002-of-00003.safetensors",
127
+ "transformer.h.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
128
+ "transformer.h.18.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
129
+ "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
130
+ "transformer.h.18.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
131
+ "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
132
+ "transformer.h.18.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
133
+ "transformer.h.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
134
+ "transformer.h.18.self_attention.dense.bias": "model-00002-of-00003.safetensors",
135
+ "transformer.h.18.self_attention.dense.weight": "model-00002-of-00003.safetensors",
136
+ "transformer.h.18.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
137
+ "transformer.h.18.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
138
+ "transformer.h.19.input_layernorm.bias": "model-00002-of-00003.safetensors",
139
+ "transformer.h.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
140
+ "transformer.h.19.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
141
+ "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
142
+ "transformer.h.19.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
143
+ "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
144
+ "transformer.h.19.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
145
+ "transformer.h.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
146
+ "transformer.h.19.self_attention.dense.bias": "model-00002-of-00003.safetensors",
147
+ "transformer.h.19.self_attention.dense.weight": "model-00002-of-00003.safetensors",
148
+ "transformer.h.19.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
149
+ "transformer.h.19.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
150
+ "transformer.h.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
151
+ "transformer.h.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
152
+ "transformer.h.2.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
153
+ "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
154
+ "transformer.h.2.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
155
+ "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
156
+ "transformer.h.2.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
157
+ "transformer.h.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
158
+ "transformer.h.2.self_attention.dense.bias": "model-00001-of-00003.safetensors",
159
+ "transformer.h.2.self_attention.dense.weight": "model-00001-of-00003.safetensors",
160
+ "transformer.h.2.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
161
+ "transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
162
+ "transformer.h.20.input_layernorm.bias": "model-00003-of-00003.safetensors",
163
+ "transformer.h.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
164
+ "transformer.h.20.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
165
+ "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
166
+ "transformer.h.20.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
167
+ "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
168
+ "transformer.h.20.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
169
+ "transformer.h.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
170
+ "transformer.h.20.self_attention.dense.bias": "model-00003-of-00003.safetensors",
171
+ "transformer.h.20.self_attention.dense.weight": "model-00003-of-00003.safetensors",
172
+ "transformer.h.20.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
173
+ "transformer.h.20.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
174
+ "transformer.h.21.input_layernorm.bias": "model-00003-of-00003.safetensors",
175
+ "transformer.h.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
176
+ "transformer.h.21.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
177
+ "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
178
+ "transformer.h.21.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
179
+ "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
180
+ "transformer.h.21.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
181
+ "transformer.h.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
182
+ "transformer.h.21.self_attention.dense.bias": "model-00003-of-00003.safetensors",
183
+ "transformer.h.21.self_attention.dense.weight": "model-00003-of-00003.safetensors",
184
+ "transformer.h.21.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
185
+ "transformer.h.21.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
186
+ "transformer.h.22.input_layernorm.bias": "model-00003-of-00003.safetensors",
187
+ "transformer.h.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
188
+ "transformer.h.22.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
189
+ "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
190
+ "transformer.h.22.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
191
+ "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
192
+ "transformer.h.22.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
193
+ "transformer.h.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
194
+ "transformer.h.22.self_attention.dense.bias": "model-00003-of-00003.safetensors",
195
+ "transformer.h.22.self_attention.dense.weight": "model-00003-of-00003.safetensors",
196
+ "transformer.h.22.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
197
+ "transformer.h.22.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
198
+ "transformer.h.23.input_layernorm.bias": "model-00003-of-00003.safetensors",
199
+ "transformer.h.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
200
+ "transformer.h.23.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
201
+ "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
202
+ "transformer.h.23.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
203
+ "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
204
+ "transformer.h.23.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
205
+ "transformer.h.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
206
+ "transformer.h.23.self_attention.dense.bias": "model-00003-of-00003.safetensors",
207
+ "transformer.h.23.self_attention.dense.weight": "model-00003-of-00003.safetensors",
208
+ "transformer.h.23.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
209
+ "transformer.h.23.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
210
+ "transformer.h.24.input_layernorm.bias": "model-00003-of-00003.safetensors",
211
+ "transformer.h.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
212
+ "transformer.h.24.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
213
+ "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
214
+ "transformer.h.24.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
215
+ "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
216
+ "transformer.h.24.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
217
+ "transformer.h.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
218
+ "transformer.h.24.self_attention.dense.bias": "model-00003-of-00003.safetensors",
219
+ "transformer.h.24.self_attention.dense.weight": "model-00003-of-00003.safetensors",
220
+ "transformer.h.24.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
221
+ "transformer.h.24.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
222
+ "transformer.h.25.input_layernorm.bias": "model-00003-of-00003.safetensors",
223
+ "transformer.h.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
224
+ "transformer.h.25.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
225
+ "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
226
+ "transformer.h.25.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
227
+ "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
228
+ "transformer.h.25.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
229
+ "transformer.h.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
230
+ "transformer.h.25.self_attention.dense.bias": "model-00003-of-00003.safetensors",
231
+ "transformer.h.25.self_attention.dense.weight": "model-00003-of-00003.safetensors",
232
+ "transformer.h.25.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
233
+ "transformer.h.25.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
234
+ "transformer.h.26.input_layernorm.bias": "model-00003-of-00003.safetensors",
235
+ "transformer.h.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
236
+ "transformer.h.26.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
237
+ "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
238
+ "transformer.h.26.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
239
+ "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
240
+ "transformer.h.26.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
241
+ "transformer.h.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
242
+ "transformer.h.26.self_attention.dense.bias": "model-00003-of-00003.safetensors",
243
+ "transformer.h.26.self_attention.dense.weight": "model-00003-of-00003.safetensors",
244
+ "transformer.h.26.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
245
+ "transformer.h.26.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
246
+ "transformer.h.27.input_layernorm.bias": "model-00003-of-00003.safetensors",
247
+ "transformer.h.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
248
+ "transformer.h.27.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
249
+ "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
250
+ "transformer.h.27.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
251
+ "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
252
+ "transformer.h.27.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
253
+ "transformer.h.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
254
+ "transformer.h.27.self_attention.dense.bias": "model-00003-of-00003.safetensors",
255
+ "transformer.h.27.self_attention.dense.weight": "model-00003-of-00003.safetensors",
256
+ "transformer.h.27.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
257
+ "transformer.h.27.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
258
+ "transformer.h.28.input_layernorm.bias": "model-00003-of-00003.safetensors",
259
+ "transformer.h.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
260
+ "transformer.h.28.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
261
+ "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
262
+ "transformer.h.28.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
263
+ "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
264
+ "transformer.h.28.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
265
+ "transformer.h.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
266
+ "transformer.h.28.self_attention.dense.bias": "model-00003-of-00003.safetensors",
267
+ "transformer.h.28.self_attention.dense.weight": "model-00003-of-00003.safetensors",
268
+ "transformer.h.28.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
269
+ "transformer.h.28.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
270
+ "transformer.h.29.input_layernorm.bias": "model-00003-of-00003.safetensors",
271
+ "transformer.h.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
272
+ "transformer.h.29.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
273
+ "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
274
+ "transformer.h.29.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
275
+ "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
276
+ "transformer.h.29.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
277
+ "transformer.h.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
278
+ "transformer.h.29.self_attention.dense.bias": "model-00003-of-00003.safetensors",
279
+ "transformer.h.29.self_attention.dense.weight": "model-00003-of-00003.safetensors",
280
+ "transformer.h.29.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
281
+ "transformer.h.29.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
282
+ "transformer.h.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
283
+ "transformer.h.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
284
+ "transformer.h.3.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
285
+ "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
286
+ "transformer.h.3.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
287
+ "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
288
+ "transformer.h.3.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
289
+ "transformer.h.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
290
+ "transformer.h.3.self_attention.dense.bias": "model-00001-of-00003.safetensors",
291
+ "transformer.h.3.self_attention.dense.weight": "model-00001-of-00003.safetensors",
292
+ "transformer.h.3.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
293
+ "transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
294
+ "transformer.h.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
295
+ "transformer.h.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
296
+ "transformer.h.4.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
297
+ "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
298
+ "transformer.h.4.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
299
+ "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
300
+ "transformer.h.4.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
301
+ "transformer.h.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
302
+ "transformer.h.4.self_attention.dense.bias": "model-00001-of-00003.safetensors",
303
+ "transformer.h.4.self_attention.dense.weight": "model-00001-of-00003.safetensors",
304
+ "transformer.h.4.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
305
+ "transformer.h.4.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
306
+ "transformer.h.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
307
+ "transformer.h.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
308
+ "transformer.h.5.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
309
+ "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
310
+ "transformer.h.5.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
311
+ "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
312
+ "transformer.h.5.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
313
+ "transformer.h.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
314
+ "transformer.h.5.self_attention.dense.bias": "model-00001-of-00003.safetensors",
315
+ "transformer.h.5.self_attention.dense.weight": "model-00001-of-00003.safetensors",
316
+ "transformer.h.5.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
317
+ "transformer.h.5.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
318
+ "transformer.h.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
319
+ "transformer.h.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
320
+ "transformer.h.6.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
321
+ "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
322
+ "transformer.h.6.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
323
+ "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
324
+ "transformer.h.6.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
325
+ "transformer.h.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
326
+ "transformer.h.6.self_attention.dense.bias": "model-00001-of-00003.safetensors",
327
+ "transformer.h.6.self_attention.dense.weight": "model-00001-of-00003.safetensors",
328
+ "transformer.h.6.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
329
+ "transformer.h.6.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
330
+ "transformer.h.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
331
+ "transformer.h.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
332
+ "transformer.h.7.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
333
+ "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
334
+ "transformer.h.7.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
335
+ "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
336
+ "transformer.h.7.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
337
+ "transformer.h.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
338
+ "transformer.h.7.self_attention.dense.bias": "model-00002-of-00003.safetensors",
339
+ "transformer.h.7.self_attention.dense.weight": "model-00002-of-00003.safetensors",
340
+ "transformer.h.7.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
341
+ "transformer.h.7.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
342
+ "transformer.h.8.input_layernorm.bias": "model-00002-of-00003.safetensors",
343
+ "transformer.h.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
344
+ "transformer.h.8.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
345
+ "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
346
+ "transformer.h.8.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
347
+ "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
348
+ "transformer.h.8.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
349
+ "transformer.h.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
350
+ "transformer.h.8.self_attention.dense.bias": "model-00002-of-00003.safetensors",
351
+ "transformer.h.8.self_attention.dense.weight": "model-00002-of-00003.safetensors",
352
+ "transformer.h.8.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
353
+ "transformer.h.8.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
354
+ "transformer.h.9.input_layernorm.bias": "model-00002-of-00003.safetensors",
355
+ "transformer.h.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
356
+ "transformer.h.9.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
357
+ "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
358
+ "transformer.h.9.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
359
+ "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
360
+ "transformer.h.9.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
361
+ "transformer.h.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
362
+ "transformer.h.9.self_attention.dense.bias": "model-00002-of-00003.safetensors",
363
+ "transformer.h.9.self_attention.dense.weight": "model-00002-of-00003.safetensors",
364
+ "transformer.h.9.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
365
+ "transformer.h.9.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
366
+ "transformer.ln_f.bias": "model-00003-of-00003.safetensors",
367
+ "transformer.ln_f.weight": "model-00003-of-00003.safetensors",
368
+ "transformer.word_embeddings.weight": "model-00001-of-00003.safetensors",
369
+ "transformer.word_embeddings_layernorm.bias": "model-00001-of-00003.safetensors",
370
+ "transformer.word_embeddings_layernorm.weight": "model-00001-of-00003.safetensors"
371
+ }
372
+ }