Hugging Face's logo

metterian
/
kullm-polyglot-12.8b-v1

Text Generation
Transformers
PyTorch
Korean
gpt_neox
feature-extraction
kullm-13.b
polyglot-ko
gpt-neox
Inference Endpoints
text-generation-inference
Model card Files Community
1
metterian commited on
Commit
edec0ed
•
1 Parent(s): 1eeb209

Upload model

Browse files
Files changed (8) hide show
  1. config.json +27 -0
  2. pytorch_model-00001-of-00006.bin +3 -0
  3. pytorch_model-00002-of-00006.bin +3 -0
  4. pytorch_model-00003-of-00006.bin +3 -0
  5. pytorch_model-00004-of-00006.bin +3 -0
  6. pytorch_model-00005-of-00006.bin +3 -0
  7. pytorch_model-00006-of-00006.bin +3 -0
  8. pytorch_model.bin.index.json +610 -0
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/persuade/01_KuAlpaca/models/lora-alpaca/",
3
+ "architectures": [
4
+ "GPTNeoXModel"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": 0.1,
8
+ "eos_token_id": 0,
9
+ "hidden_act": "gelu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 20480,
13
+ "layer_norm_eps": 1e-05,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "gpt_neox",
16
+ "num_attention_heads": 40,
17
+ "num_hidden_layers": 40,
18
+ "num_steps": "global_step301000",
19
+ "rotary_emb_base": 10000,
20
+ "rotary_pct": 0.5,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.30.0.dev0",
24
+ "use_cache": true,
25
+ "use_parallel_residual": true,
26
+ "vocab_size": 30080
27
+ }
pytorch_model-00001-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f9787f3bb0c4e0cc364946a8a7331481fd91809e657deeb6ca45517198afb6d
3
+ size 9879129362
pytorch_model-00002-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e76fa9465afd593d36a46c5324f191fbb09921a041a679f46373afe2eac41562
3
+ size 9997176581
pytorch_model-00003-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:395f3d43dca3e65c00aa9c18b3614094500e9119a6cd6c371c8e2179109b51e0
3
+ size 9787420437
pytorch_model-00004-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c66a4dcbabc4236c0e83744b7295841fef1aae84ca5d9bc632c41f03e8ef6248
3
+ size 9678324992
pytorch_model-00005-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f947686d318f1fb87428bd0c5d03acf306bc66dd915887785682d6632775833
3
+ size 9682542297
pytorch_model-00006-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:770a89d1ab815947de78d75e44f51f722460dee7ee094e07793cda6332fca34f
3
+ size 2101763081
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,610 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 50979353760.0
4
+ },
5
+ "weight_map": {
6
+ "embed_in.weight": "pytorch_model-00001-of-00006.bin",
7
+ "final_layer_norm.bias": "pytorch_model-00006-of-00006.bin",
8
+ "final_layer_norm.weight": "pytorch_model-00006-of-00006.bin",
9
+ "layers.0.attention.bias": "pytorch_model-00001-of-00006.bin",
10
+ "layers.0.attention.dense.bias": "pytorch_model-00001-of-00006.bin",
11
+ "layers.0.attention.dense.weight": "pytorch_model-00001-of-00006.bin",
12
+ "layers.0.attention.masked_bias": "pytorch_model-00001-of-00006.bin",
13
+ "layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00006.bin",
14
+ "layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00006.bin",
15
+ "layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
16
+ "layers.0.input_layernorm.bias": "pytorch_model-00001-of-00006.bin",
17
+ "layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
18
+ "layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00006.bin",
19
+ "layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00006.bin",
20
+ "layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00006.bin",
21
+ "layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00006.bin",
22
+ "layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00006.bin",
23
+ "layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
24
+ "layers.1.attention.bias": "pytorch_model-00001-of-00006.bin",
25
+ "layers.1.attention.dense.bias": "pytorch_model-00001-of-00006.bin",
26
+ "layers.1.attention.dense.weight": "pytorch_model-00001-of-00006.bin",
27
+ "layers.1.attention.masked_bias": "pytorch_model-00001-of-00006.bin",
28
+ "layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00006.bin",
29
+ "layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00006.bin",
30
+ "layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
31
+ "layers.1.input_layernorm.bias": "pytorch_model-00001-of-00006.bin",
32
+ "layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
33
+ "layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00006.bin",
34
+ "layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00006.bin",
35
+ "layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00006.bin",
36
+ "layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00006.bin",
37
+ "layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00006.bin",
38
+ "layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
39
+ "layers.10.attention.bias": "pytorch_model-00002-of-00006.bin",
40
+ "layers.10.attention.dense.bias": "pytorch_model-00002-of-00006.bin",
41
+ "layers.10.attention.dense.weight": "pytorch_model-00002-of-00006.bin",
42
+ "layers.10.attention.masked_bias": "pytorch_model-00002-of-00006.bin",
43
+ "layers.10.attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
44
+ "layers.10.attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
45
+ "layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
46
+ "layers.10.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
47
+ "layers.10.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
48
+ "layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
49
+ "layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
50
+ "layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00006.bin",
51
+ "layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00006.bin",
52
+ "layers.10.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
53
+ "layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
54
+ "layers.11.attention.bias": "pytorch_model-00002-of-00006.bin",
55
+ "layers.11.attention.dense.bias": "pytorch_model-00002-of-00006.bin",
56
+ "layers.11.attention.dense.weight": "pytorch_model-00002-of-00006.bin",
57
+ "layers.11.attention.masked_bias": "pytorch_model-00002-of-00006.bin",
58
+ "layers.11.attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
59
+ "layers.11.attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
60
+ "layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
61
+ "layers.11.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
62
+ "layers.11.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
63
+ "layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
64
+ "layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
65
+ "layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00006.bin",
66
+ "layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00006.bin",
67
+ "layers.11.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
68
+ "layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
69
+ "layers.12.attention.bias": "pytorch_model-00002-of-00006.bin",
70
+ "layers.12.attention.dense.bias": "pytorch_model-00002-of-00006.bin",
71
+ "layers.12.attention.dense.weight": "pytorch_model-00002-of-00006.bin",
72
+ "layers.12.attention.masked_bias": "pytorch_model-00002-of-00006.bin",
73
+ "layers.12.attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
74
+ "layers.12.attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
75
+ "layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
76
+ "layers.12.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
77
+ "layers.12.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
78
+ "layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
79
+ "layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
80
+ "layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00006.bin",
81
+ "layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00006.bin",
82
+ "layers.12.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
83
+ "layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
84
+ "layers.13.attention.bias": "pytorch_model-00002-of-00006.bin",
85
+ "layers.13.attention.dense.bias": "pytorch_model-00002-of-00006.bin",
86
+ "layers.13.attention.dense.weight": "pytorch_model-00002-of-00006.bin",
87
+ "layers.13.attention.masked_bias": "pytorch_model-00002-of-00006.bin",
88
+ "layers.13.attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
89
+ "layers.13.attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
90
+ "layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
91
+ "layers.13.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
92
+ "layers.13.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
93
+ "layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
94
+ "layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
95
+ "layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00006.bin",
96
+ "layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00006.bin",
97
+ "layers.13.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
98
+ "layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
99
+ "layers.14.attention.bias": "pytorch_model-00002-of-00006.bin",
100
+ "layers.14.attention.dense.bias": "pytorch_model-00002-of-00006.bin",
101
+ "layers.14.attention.dense.weight": "pytorch_model-00002-of-00006.bin",
102
+ "layers.14.attention.masked_bias": "pytorch_model-00002-of-00006.bin",
103
+ "layers.14.attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
104
+ "layers.14.attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
105
+ "layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
106
+ "layers.14.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
107
+ "layers.14.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
108
+ "layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
109
+ "layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
110
+ "layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00006.bin",
111
+ "layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00006.bin",
112
+ "layers.14.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
113
+ "layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
114
+ "layers.15.attention.bias": "pytorch_model-00002-of-00006.bin",
115
+ "layers.15.attention.dense.bias": "pytorch_model-00003-of-00006.bin",
116
+ "layers.15.attention.dense.weight": "pytorch_model-00003-of-00006.bin",
117
+ "layers.15.attention.masked_bias": "pytorch_model-00002-of-00006.bin",
118
+ "layers.15.attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
119
+ "layers.15.attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
120
+ "layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
121
+ "layers.15.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
122
+ "layers.15.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
123
+ "layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
124
+ "layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
125
+ "layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
126
+ "layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
127
+ "layers.15.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
128
+ "layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
129
+ "layers.16.attention.bias": "pytorch_model-00003-of-00006.bin",
130
+ "layers.16.attention.dense.bias": "pytorch_model-00003-of-00006.bin",
131
+ "layers.16.attention.dense.weight": "pytorch_model-00003-of-00006.bin",
132
+ "layers.16.attention.masked_bias": "pytorch_model-00003-of-00006.bin",
133
+ "layers.16.attention.query_key_value.bias": "pytorch_model-00003-of-00006.bin",
134
+ "layers.16.attention.query_key_value.weight": "pytorch_model-00003-of-00006.bin",
135
+ "layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
136
+ "layers.16.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
137
+ "layers.16.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
138
+ "layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
139
+ "layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
140
+ "layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
141
+ "layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
142
+ "layers.16.post_attention_layernorm.bias": "pytorch_model-00003-of-00006.bin",
143
+ "layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
144
+ "layers.17.attention.bias": "pytorch_model-00003-of-00006.bin",
145
+ "layers.17.attention.dense.bias": "pytorch_model-00003-of-00006.bin",
146
+ "layers.17.attention.dense.weight": "pytorch_model-00003-of-00006.bin",
147
+ "layers.17.attention.masked_bias": "pytorch_model-00003-of-00006.bin",
148
+ "layers.17.attention.query_key_value.bias": "pytorch_model-00003-of-00006.bin",
149
+ "layers.17.attention.query_key_value.weight": "pytorch_model-00003-of-00006.bin",
150
+ "layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
151
+ "layers.17.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
152
+ "layers.17.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
153
+ "layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
154
+ "layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
155
+ "layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
156
+ "layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
157
+ "layers.17.post_attention_layernorm.bias": "pytorch_model-00003-of-00006.bin",
158
+ "layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
159
+ "layers.18.attention.bias": "pytorch_model-00003-of-00006.bin",
160
+ "layers.18.attention.dense.bias": "pytorch_model-00003-of-00006.bin",
161
+ "layers.18.attention.dense.weight": "pytorch_model-00003-of-00006.bin",
162
+ "layers.18.attention.masked_bias": "pytorch_model-00003-of-00006.bin",
163
+ "layers.18.attention.query_key_value.bias": "pytorch_model-00003-of-00006.bin",
164
+ "layers.18.attention.query_key_value.weight": "pytorch_model-00003-of-00006.bin",
165
+ "layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
166
+ "layers.18.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
167
+ "layers.18.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
168
+ "layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
169
+ "layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
170
+ "layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
171
+ "layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
172
+ "layers.18.post_attention_layernorm.bias": "pytorch_model-00003-of-00006.bin",
173
+ "layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
174
+ "layers.19.attention.bias": "pytorch_model-00003-of-00006.bin",
175
+ "layers.19.attention.dense.bias": "pytorch_model-00003-of-00006.bin",
176
+ "layers.19.attention.dense.weight": "pytorch_model-00003-of-00006.bin",
177
+ "layers.19.attention.masked_bias": "pytorch_model-00003-of-00006.bin",
178
+ "layers.19.attention.query_key_value.bias": "pytorch_model-00003-of-00006.bin",
179
+ "layers.19.attention.query_key_value.weight": "pytorch_model-00003-of-00006.bin",
180
+ "layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
181
+ "layers.19.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
182
+ "layers.19.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
183
+ "layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
184
+ "layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
185
+ "layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
186
+ "layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
187
+ "layers.19.post_attention_layernorm.bias": "pytorch_model-00003-of-00006.bin",
188
+ "layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
189
+ "layers.2.attention.bias": "pytorch_model-00001-of-00006.bin",
190
+ "layers.2.attention.dense.bias": "pytorch_model-00001-of-00006.bin",
191
+ "layers.2.attention.dense.weight": "pytorch_model-00001-of-00006.bin",
192
+ "layers.2.attention.masked_bias": "pytorch_model-00001-of-00006.bin",
193
+ "layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00006.bin",
194
+ "layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00006.bin",
195
+ "layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
196
+ "layers.2.input_layernorm.bias": "pytorch_model-00001-of-00006.bin",
197
+ "layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
198
+ "layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00006.bin",
199
+ "layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00006.bin",
200
+ "layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00006.bin",
201
+ "layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00006.bin",
202
+ "layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00006.bin",
203
+ "layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
204
+ "layers.20.attention.bias": "pytorch_model-00003-of-00006.bin",
205
+ "layers.20.attention.dense.bias": "pytorch_model-00003-of-00006.bin",
206
+ "layers.20.attention.dense.weight": "pytorch_model-00003-of-00006.bin",
207
+ "layers.20.attention.masked_bias": "pytorch_model-00003-of-00006.bin",
208
+ "layers.20.attention.query_key_value.bias": "pytorch_model-00003-of-00006.bin",
209
+ "layers.20.attention.query_key_value.weight": "pytorch_model-00003-of-00006.bin",
210
+ "layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
211
+ "layers.20.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
212
+ "layers.20.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
213
+ "layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
214
+ "layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
215
+ "layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
216
+ "layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
217
+ "layers.20.post_attention_layernorm.bias": "pytorch_model-00003-of-00006.bin",
218
+ "layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
219
+ "layers.21.attention.bias": "pytorch_model-00003-of-00006.bin",
220
+ "layers.21.attention.dense.bias": "pytorch_model-00003-of-00006.bin",
221
+ "layers.21.attention.dense.weight": "pytorch_model-00003-of-00006.bin",
222
+ "layers.21.attention.masked_bias": "pytorch_model-00003-of-00006.bin",
223
+ "layers.21.attention.query_key_value.bias": "pytorch_model-00003-of-00006.bin",
224
+ "layers.21.attention.query_key_value.weight": "pytorch_model-00003-of-00006.bin",
225
+ "layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
226
+ "layers.21.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
227
+ "layers.21.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
228
+ "layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
229
+ "layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
230
+ "layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
231
+ "layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
232
+ "layers.21.post_attention_layernorm.bias": "pytorch_model-00003-of-00006.bin",
233
+ "layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
234
+ "layers.22.attention.bias": "pytorch_model-00003-of-00006.bin",
235
+ "layers.22.attention.dense.bias": "pytorch_model-00003-of-00006.bin",
236
+ "layers.22.attention.dense.weight": "pytorch_model-00003-of-00006.bin",
237
+ "layers.22.attention.masked_bias": "pytorch_model-00003-of-00006.bin",
238
+ "layers.22.attention.query_key_value.bias": "pytorch_model-00003-of-00006.bin",
239
+ "layers.22.attention.query_key_value.weight": "pytorch_model-00003-of-00006.bin",
240
+ "layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
241
+ "layers.22.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
242
+ "layers.22.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
243
+ "layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
244
+ "layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
245
+ "layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
246
+ "layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
247
+ "layers.22.post_attention_layernorm.bias": "pytorch_model-00003-of-00006.bin",
248
+ "layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
249
+ "layers.23.attention.bias": "pytorch_model-00003-of-00006.bin",
250
+ "layers.23.attention.dense.bias": "pytorch_model-00004-of-00006.bin",
251
+ "layers.23.attention.dense.weight": "pytorch_model-00004-of-00006.bin",
252
+ "layers.23.attention.masked_bias": "pytorch_model-00003-of-00006.bin",
253
+ "layers.23.attention.query_key_value.bias": "pytorch_model-00004-of-00006.bin",
254
+ "layers.23.attention.query_key_value.weight": "pytorch_model-00004-of-00006.bin",
255
+ "layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
256
+ "layers.23.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
257
+ "layers.23.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
258
+ "layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00006.bin",
259
+ "layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00006.bin",
260
+ "layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
261
+ "layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
262
+ "layers.23.post_attention_layernorm.bias": "pytorch_model-00003-of-00006.bin",
263
+ "layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
264
+ "layers.24.attention.bias": "pytorch_model-00004-of-00006.bin",
265
+ "layers.24.attention.dense.bias": "pytorch_model-00004-of-00006.bin",
266
+ "layers.24.attention.dense.weight": "pytorch_model-00004-of-00006.bin",
267
+ "layers.24.attention.masked_bias": "pytorch_model-00004-of-00006.bin",
268
+ "layers.24.attention.query_key_value.bias": "pytorch_model-00004-of-00006.bin",
269
+ "layers.24.attention.query_key_value.weight": "pytorch_model-00004-of-00006.bin",
270
+ "layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
271
+ "layers.24.input_layernorm.bias": "pytorch_model-00004-of-00006.bin",
272
+ "layers.24.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
273
+ "layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00006.bin",
274
+ "layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00006.bin",
275
+ "layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
276
+ "layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
277
+ "layers.24.post_attention_layernorm.bias": "pytorch_model-00004-of-00006.bin",
278
+ "layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
279
+ "layers.25.attention.bias": "pytorch_model-00004-of-00006.bin",
280
+ "layers.25.attention.dense.bias": "pytorch_model-00004-of-00006.bin",
281
+ "layers.25.attention.dense.weight": "pytorch_model-00004-of-00006.bin",
282
+ "layers.25.attention.masked_bias": "pytorch_model-00004-of-00006.bin",
283
+ "layers.25.attention.query_key_value.bias": "pytorch_model-00004-of-00006.bin",
284
+ "layers.25.attention.query_key_value.weight": "pytorch_model-00004-of-00006.bin",
285
+ "layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
286
+ "layers.25.input_layernorm.bias": "pytorch_model-00004-of-00006.bin",
287
+ "layers.25.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
288
+ "layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00006.bin",
289
+ "layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00006.bin",
290
+ "layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
291
+ "layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
292
+ "layers.25.post_attention_layernorm.bias": "pytorch_model-00004-of-00006.bin",
293
+ "layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
294
+ "layers.26.attention.bias": "pytorch_model-00004-of-00006.bin",
295
+ "layers.26.attention.dense.bias": "pytorch_model-00004-of-00006.bin",
296
+ "layers.26.attention.dense.weight": "pytorch_model-00004-of-00006.bin",
297
+ "layers.26.attention.masked_bias": "pytorch_model-00004-of-00006.bin",
298
+ "layers.26.attention.query_key_value.bias": "pytorch_model-00004-of-00006.bin",
299
+ "layers.26.attention.query_key_value.weight": "pytorch_model-00004-of-00006.bin",
300
+ "layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
301
+ "layers.26.input_layernorm.bias": "pytorch_model-00004-of-00006.bin",
302
+ "layers.26.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
303
+ "layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00006.bin",
304
+ "layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00006.bin",
305
+ "layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
306
+ "layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
307
+ "layers.26.post_attention_layernorm.bias": "pytorch_model-00004-of-00006.bin",
308
+ "layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
309
+ "layers.27.attention.bias": "pytorch_model-00004-of-00006.bin",
310
+ "layers.27.attention.dense.bias": "pytorch_model-00004-of-00006.bin",
311
+ "layers.27.attention.dense.weight": "pytorch_model-00004-of-00006.bin",
312
+ "layers.27.attention.masked_bias": "pytorch_model-00004-of-00006.bin",
313
+ "layers.27.attention.query_key_value.bias": "pytorch_model-00004-of-00006.bin",
314
+ "layers.27.attention.query_key_value.weight": "pytorch_model-00004-of-00006.bin",
315
+ "layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
316
+ "layers.27.input_layernorm.bias": "pytorch_model-00004-of-00006.bin",
317
+ "layers.27.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
318
+ "layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00006.bin",
319
+ "layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00006.bin",
320
+ "layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
321
+ "layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
322
+ "layers.27.post_attention_layernorm.bias": "pytorch_model-00004-of-00006.bin",
323
+ "layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
324
+ "layers.28.attention.bias": "pytorch_model-00004-of-00006.bin",
325
+ "layers.28.attention.dense.bias": "pytorch_model-00004-of-00006.bin",
326
+ "layers.28.attention.dense.weight": "pytorch_model-00004-of-00006.bin",
327
+ "layers.28.attention.masked_bias": "pytorch_model-00004-of-00006.bin",
328
+ "layers.28.attention.query_key_value.bias": "pytorch_model-00004-of-00006.bin",
329
+ "layers.28.attention.query_key_value.weight": "pytorch_model-00004-of-00006.bin",
330
+ "layers.28.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
331
+ "layers.28.input_layernorm.bias": "pytorch_model-00004-of-00006.bin",
332
+ "layers.28.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
333
+ "layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00006.bin",
334
+ "layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00006.bin",
335
+ "layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
336
+ "layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
337
+ "layers.28.post_attention_layernorm.bias": "pytorch_model-00004-of-00006.bin",
338
+ "layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
339
+ "layers.29.attention.bias": "pytorch_model-00004-of-00006.bin",
340
+ "layers.29.attention.dense.bias": "pytorch_model-00004-of-00006.bin",
341
+ "layers.29.attention.dense.weight": "pytorch_model-00004-of-00006.bin",
342
+ "layers.29.attention.masked_bias": "pytorch_model-00004-of-00006.bin",
343
+ "layers.29.attention.query_key_value.bias": "pytorch_model-00004-of-00006.bin",
344
+ "layers.29.attention.query_key_value.weight": "pytorch_model-00004-of-00006.bin",
345
+ "layers.29.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
346
+ "layers.29.input_layernorm.bias": "pytorch_model-00004-of-00006.bin",
347
+ "layers.29.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
348
+ "layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00006.bin",
349
+ "layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00006.bin",
350
+ "layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
351
+ "layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
352
+ "layers.29.post_attention_layernorm.bias": "pytorch_model-00004-of-00006.bin",
353
+ "layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
354
+ "layers.3.attention.bias": "pytorch_model-00001-of-00006.bin",
355
+ "layers.3.attention.dense.bias": "pytorch_model-00001-of-00006.bin",
356
+ "layers.3.attention.dense.weight": "pytorch_model-00001-of-00006.bin",
357
+ "layers.3.attention.masked_bias": "pytorch_model-00001-of-00006.bin",
358
+ "layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00006.bin",
359
+ "layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00006.bin",
360
+ "layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
361
+ "layers.3.input_layernorm.bias": "pytorch_model-00001-of-00006.bin",
362
+ "layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
363
+ "layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00006.bin",
364
+ "layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00006.bin",
365
+ "layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00006.bin",
366
+ "layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00006.bin",
367
+ "layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00006.bin",
368
+ "layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
369
+ "layers.30.attention.bias": "pytorch_model-00004-of-00006.bin",
370
+ "layers.30.attention.dense.bias": "pytorch_model-00004-of-00006.bin",
371
+ "layers.30.attention.dense.weight": "pytorch_model-00004-of-00006.bin",
372
+ "layers.30.attention.masked_bias": "pytorch_model-00004-of-00006.bin",
373
+ "layers.30.attention.query_key_value.bias": "pytorch_model-00004-of-00006.bin",
374
+ "layers.30.attention.query_key_value.weight": "pytorch_model-00004-of-00006.bin",
375
+ "layers.30.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
376
+ "layers.30.input_layernorm.bias": "pytorch_model-00004-of-00006.bin",
377
+ "layers.30.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
378
+ "layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00006.bin",
379
+ "layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00006.bin",
380
+ "layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
381
+ "layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
382
+ "layers.30.post_attention_layernorm.bias": "pytorch_model-00004-of-00006.bin",
383
+ "layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
384
+ "layers.31.attention.bias": "pytorch_model-00005-of-00006.bin",
385
+ "layers.31.attention.dense.bias": "pytorch_model-00005-of-00006.bin",
386
+ "layers.31.attention.dense.weight": "pytorch_model-00005-of-00006.bin",
387
+ "layers.31.attention.masked_bias": "pytorch_model-00005-of-00006.bin",
388
+ "layers.31.attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
389
+ "layers.31.attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
390
+ "layers.31.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
391
+ "layers.31.input_layernorm.bias": "pytorch_model-00005-of-00006.bin",
392
+ "layers.31.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
393
+ "layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00006.bin",
394
+ "layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00006.bin",
395
+ "layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00006.bin",
396
+ "layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00006.bin",
397
+ "layers.31.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
398
+ "layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
399
+ "layers.32.attention.bias": "pytorch_model-00005-of-00006.bin",
400
+ "layers.32.attention.dense.bias": "pytorch_model-00005-of-00006.bin",
401
+ "layers.32.attention.dense.weight": "pytorch_model-00005-of-00006.bin",
402
+ "layers.32.attention.masked_bias": "pytorch_model-00005-of-00006.bin",
403
+ "layers.32.attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
404
+ "layers.32.attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
405
+ "layers.32.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
406
+ "layers.32.input_layernorm.bias": "pytorch_model-00005-of-00006.bin",
407
+ "layers.32.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
408
+ "layers.32.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00006.bin",
409
+ "layers.32.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00006.bin",
410
+ "layers.32.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00006.bin",
411
+ "layers.32.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00006.bin",
412
+ "layers.32.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
413
+ "layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
414
+ "layers.33.attention.bias": "pytorch_model-00005-of-00006.bin",
415
+ "layers.33.attention.dense.bias": "pytorch_model-00005-of-00006.bin",
416
+ "layers.33.attention.dense.weight": "pytorch_model-00005-of-00006.bin",
417
+ "layers.33.attention.masked_bias": "pytorch_model-00005-of-00006.bin",
418
+ "layers.33.attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
419
+ "layers.33.attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
420
+ "layers.33.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
421
+ "layers.33.input_layernorm.bias": "pytorch_model-00005-of-00006.bin",
422
+ "layers.33.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
423
+ "layers.33.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00006.bin",
424
+ "layers.33.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00006.bin",
425
+ "layers.33.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00006.bin",
426
+ "layers.33.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00006.bin",
427
+ "layers.33.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
428
+ "layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
429
+ "layers.34.attention.bias": "pytorch_model-00005-of-00006.bin",
430
+ "layers.34.attention.dense.bias": "pytorch_model-00005-of-00006.bin",
431
+ "layers.34.attention.dense.weight": "pytorch_model-00005-of-00006.bin",
432
+ "layers.34.attention.masked_bias": "pytorch_model-00005-of-00006.bin",
433
+ "layers.34.attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
434
+ "layers.34.attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
435
+ "layers.34.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
436
+ "layers.34.input_layernorm.bias": "pytorch_model-00005-of-00006.bin",
437
+ "layers.34.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
438
+ "layers.34.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00006.bin",
439
+ "layers.34.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00006.bin",
440
+ "layers.34.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00006.bin",
441
+ "layers.34.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00006.bin",
442
+ "layers.34.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
443
+ "layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
444
+ "layers.35.attention.bias": "pytorch_model-00005-of-00006.bin",
445
+ "layers.35.attention.dense.bias": "pytorch_model-00005-of-00006.bin",
446
+ "layers.35.attention.dense.weight": "pytorch_model-00005-of-00006.bin",
447
+ "layers.35.attention.masked_bias": "pytorch_model-00005-of-00006.bin",
448
+ "layers.35.attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
449
+ "layers.35.attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
450
+ "layers.35.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
451
+ "layers.35.input_layernorm.bias": "pytorch_model-00005-of-00006.bin",
452
+ "layers.35.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
453
+ "layers.35.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00006.bin",
454
+ "layers.35.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00006.bin",
455
+ "layers.35.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00006.bin",
456
+ "layers.35.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00006.bin",
457
+ "layers.35.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
458
+ "layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
459
+ "layers.36.attention.bias": "pytorch_model-00005-of-00006.bin",
460
+ "layers.36.attention.dense.bias": "pytorch_model-00005-of-00006.bin",
461
+ "layers.36.attention.dense.weight": "pytorch_model-00005-of-00006.bin",
462
+ "layers.36.attention.masked_bias": "pytorch_model-00005-of-00006.bin",
463
+ "layers.36.attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
464
+ "layers.36.attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
465
+ "layers.36.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
466
+ "layers.36.input_layernorm.bias": "pytorch_model-00005-of-00006.bin",
467
+ "layers.36.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
468
+ "layers.36.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00006.bin",
469
+ "layers.36.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00006.bin",
470
+ "layers.36.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00006.bin",
471
+ "layers.36.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00006.bin",
472
+ "layers.36.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
473
+ "layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
474
+ "layers.37.attention.bias": "pytorch_model-00005-of-00006.bin",
475
+ "layers.37.attention.dense.bias": "pytorch_model-00005-of-00006.bin",
476
+ "layers.37.attention.dense.weight": "pytorch_model-00005-of-00006.bin",
477
+ "layers.37.attention.masked_bias": "pytorch_model-00005-of-00006.bin",
478
+ "layers.37.attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
479
+ "layers.37.attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
480
+ "layers.37.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
481
+ "layers.37.input_layernorm.bias": "pytorch_model-00005-of-00006.bin",
482
+ "layers.37.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
483
+ "layers.37.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00006.bin",
484
+ "layers.37.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00006.bin",
485
+ "layers.37.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00006.bin",
486
+ "layers.37.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00006.bin",
487
+ "layers.37.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
488
+ "layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
489
+ "layers.38.attention.bias": "pytorch_model-00005-of-00006.bin",
490
+ "layers.38.attention.dense.bias": "pytorch_model-00005-of-00006.bin",
491
+ "layers.38.attention.dense.weight": "pytorch_model-00005-of-00006.bin",
492
+ "layers.38.attention.masked_bias": "pytorch_model-00005-of-00006.bin",
493
+ "layers.38.attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
494
+ "layers.38.attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
495
+ "layers.38.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
496
+ "layers.38.input_layernorm.bias": "pytorch_model-00005-of-00006.bin",
497
+ "layers.38.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
498
+ "layers.38.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00006.bin",
499
+ "layers.38.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00006.bin",
500
+ "layers.38.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00006.bin",
501
+ "layers.38.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00006.bin",
502
+ "layers.38.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
503
+ "layers.38.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
504
+ "layers.39.attention.bias": "pytorch_model-00006-of-00006.bin",
505
+ "layers.39.attention.dense.bias": "pytorch_model-00006-of-00006.bin",
506
+ "layers.39.attention.dense.weight": "pytorch_model-00006-of-00006.bin",
507
+ "layers.39.attention.masked_bias": "pytorch_model-00006-of-00006.bin",
508
+ "layers.39.attention.query_key_value.bias": "pytorch_model-00006-of-00006.bin",
509
+ "layers.39.attention.query_key_value.weight": "pytorch_model-00006-of-00006.bin",
510
+ "layers.39.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00006.bin",
511
+ "layers.39.input_layernorm.bias": "pytorch_model-00006-of-00006.bin",
512
+ "layers.39.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
513
+ "layers.39.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00006.bin",
514
+ "layers.39.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00006.bin",
515
+ "layers.39.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00006.bin",
516
+ "layers.39.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00006.bin",
517
+ "layers.39.post_attention_layernorm.bias": "pytorch_model-00006-of-00006.bin",
518
+ "layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
519
+ "layers.4.attention.bias": "pytorch_model-00001-of-00006.bin",
520
+ "layers.4.attention.dense.bias": "pytorch_model-00001-of-00006.bin",
521
+ "layers.4.attention.dense.weight": "pytorch_model-00001-of-00006.bin",
522
+ "layers.4.attention.masked_bias": "pytorch_model-00001-of-00006.bin",
523
+ "layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00006.bin",
524
+ "layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00006.bin",
525
+ "layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
526
+ "layers.4.input_layernorm.bias": "pytorch_model-00001-of-00006.bin",
527
+ "layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
528
+ "layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00006.bin",
529
+ "layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00006.bin",
530
+ "layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00006.bin",
531
+ "layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00006.bin",
532
+ "layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00006.bin",
533
+ "layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
534
+ "layers.5.attention.bias": "pytorch_model-00001-of-00006.bin",
535
+ "layers.5.attention.dense.bias": "pytorch_model-00001-of-00006.bin",
536
+ "layers.5.attention.dense.weight": "pytorch_model-00001-of-00006.bin",
537
+ "layers.5.attention.masked_bias": "pytorch_model-00001-of-00006.bin",
538
+ "layers.5.attention.query_key_value.bias": "pytorch_model-00001-of-00006.bin",
539
+ "layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00006.bin",
540
+ "layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
541
+ "layers.5.input_layernorm.bias": "pytorch_model-00001-of-00006.bin",
542
+ "layers.5.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
543
+ "layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00006.bin",
544
+ "layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00006.bin",
545
+ "layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00006.bin",
546
+ "layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00006.bin",
547
+ "layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00006.bin",
548
+ "layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
549
+ "layers.6.attention.bias": "pytorch_model-00001-of-00006.bin",
550
+ "layers.6.attention.dense.bias": "pytorch_model-00001-of-00006.bin",
551
+ "layers.6.attention.dense.weight": "pytorch_model-00001-of-00006.bin",
552
+ "layers.6.attention.masked_bias": "pytorch_model-00001-of-00006.bin",
553
+ "layers.6.attention.query_key_value.bias": "pytorch_model-00001-of-00006.bin",
554
+ "layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00006.bin",
555
+ "layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
556
+ "layers.6.input_layernorm.bias": "pytorch_model-00001-of-00006.bin",
557
+ "layers.6.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
558
+ "layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00006.bin",
559
+ "layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00006.bin",
560
+ "layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00006.bin",
561
+ "layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00006.bin",
562
+ "layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00006.bin",
563
+ "layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
564
+ "layers.7.attention.bias": "pytorch_model-00001-of-00006.bin",
565
+ "layers.7.attention.dense.bias": "pytorch_model-00001-of-00006.bin",
566
+ "layers.7.attention.dense.weight": "pytorch_model-00001-of-00006.bin",
567
+ "layers.7.attention.masked_bias": "pytorch_model-00001-of-00006.bin",
568
+ "layers.7.attention.query_key_value.bias": "pytorch_model-00001-of-00006.bin",
569
+ "layers.7.attention.query_key_value.weight": "pytorch_model-00001-of-00006.bin",
570
+ "layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
571
+ "layers.7.input_layernorm.bias": "pytorch_model-00001-of-00006.bin",
572
+ "layers.7.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
573
+ "layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
574
+ "layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
575
+ "layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00006.bin",
576
+ "layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00006.bin",
577
+ "layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00006.bin",
578
+ "layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
579
+ "layers.8.attention.bias": "pytorch_model-00002-of-00006.bin",
580
+ "layers.8.attention.dense.bias": "pytorch_model-00002-of-00006.bin",
581
+ "layers.8.attention.dense.weight": "pytorch_model-00002-of-00006.bin",
582
+ "layers.8.attention.masked_bias": "pytorch_model-00002-of-00006.bin",
583
+ "layers.8.attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
584
+ "layers.8.attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
585
+ "layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
586
+ "layers.8.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
587
+ "layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
588
+ "layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
589
+ "layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
590
+ "layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00006.bin",
591
+ "layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00006.bin",
592
+ "layers.8.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
593
+ "layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
594
+ "layers.9.attention.bias": "pytorch_model-00002-of-00006.bin",
595
+ "layers.9.attention.dense.bias": "pytorch_model-00002-of-00006.bin",
596
+ "layers.9.attention.dense.weight": "pytorch_model-00002-of-00006.bin",
597
+ "layers.9.attention.masked_bias": "pytorch_model-00002-of-00006.bin",
598
+ "layers.9.attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
599
+ "layers.9.attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
600
+ "layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
601
+ "layers.9.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
602
+ "layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
603
+ "layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
604
+ "layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
605
+ "layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00006.bin",
606
+ "layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00006.bin",
607
+ "layers.9.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
608
+ "layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin"
609
+ }
610
+ }