nayohan commited on
Commit
7473ab3
1 Parent(s): b78ff91

Upload LlamaForCausalLM

Browse files
config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_name_or_path": "./meta-llama/Llama-2-13b-chat-hf_DocQA7_MS",
3
  "architectures": [
4
- "LlamaModel"
5
  ],
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
 
1
  {
2
  "_name_or_path": "./meta-llama/Llama-2-13b-chat-hf_DocQA7_MS",
3
  "architectures": [
4
+ "LlamaForCausalLM"
5
  ],
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "do_sample": true,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.6,
8
+ "top_p": 0.9,
9
+ "transformers_version": "4.34.1"
10
+ }
pytorch_model-00001-of-00006.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a01eb15838c1953ec3070e680683bf81d8bdf34c602910311339fd36a7d2c0a
3
- size 9956539186
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2280f2d04da9befb40c6e8b72e40df6334d8803e6c165ae2f31c85682f97c6f9
3
+ size 9956539570
pytorch_model-00002-of-00006.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:880558d9cbe59d34308093a102212ad48fe55895f1d3da2a7f19c702b8d4417a
3
- size 9940852182
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c36af7976808b2370a5c9b248ed89943cd51a6cf446246435ce4690a0e5b25e
3
+ size 9940852630
pytorch_model-00003-of-00006.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f00ff2118d3d895ee569df139499bc808d87c5e2bde2519e2763f7505333fac
3
- size 9940852258
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37e8cfeccfb2b5ca904c4fda24287ff580cb1f9ae300a789b70b3b691e47d002
3
+ size 9940852642
pytorch_model-00004-of-00006.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36fece651595af0b39e16f9ff24f300e7983aeaf9bf1a1ad78d4bcbc5caaef89
3
- size 9867410592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1acb9897f023fa7e23e7151faf9e2585ca66915be4ce0b68f73985f38771ad37
3
+ size 9867410976
pytorch_model-00005-of-00006.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d97589321a51289c831a893d7ffa8e553a3ba8361830c73a49e1194fa224727
3
- size 9867452228
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6469488ec20930beb18efcc0dc951cffc0de9a2d2b18c3471a7fe8438b31067
3
+ size 9867452612
pytorch_model-00006-of-00006.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80dbd89a916289df2848e6cbd500fbf680e9581f80b6da86e83654e649a6460c
3
- size 1835115750
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d1313bd1f81a4d6bf208963ec8535c80f2a86575ea363193890ab4951b3d6c8
3
+ size 2490476152
pytorch_model.bin.index.json CHANGED
@@ -1,369 +1,370 @@
1
  {
2
  "metadata": {
3
- "total_size": 51408097280
4
  },
5
  "weight_map": {
6
- "embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
7
- "layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
8
- "layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
9
- "layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
10
- "layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
11
- "layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
12
- "layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
13
- "layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
14
- "layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
15
- "layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
16
- "layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
17
- "layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
18
- "layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
19
- "layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
20
- "layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
21
- "layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
22
- "layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
23
- "layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
24
- "layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
25
- "layers.10.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
26
- "layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
27
- "layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
28
- "layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
29
- "layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
30
- "layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
31
- "layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
32
- "layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
33
- "layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
34
- "layers.11.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
35
- "layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
36
- "layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
37
- "layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
38
- "layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
39
- "layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
40
- "layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
41
- "layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
42
- "layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
43
- "layers.12.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
44
- "layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
45
- "layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
46
- "layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
47
- "layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
48
- "layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
49
- "layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
50
- "layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
51
- "layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
52
- "layers.13.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
53
- "layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
54
- "layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
55
- "layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
56
- "layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
57
- "layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
58
- "layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
59
- "layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
60
- "layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
61
- "layers.14.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
62
- "layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
63
- "layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
64
- "layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
65
- "layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
66
- "layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
67
- "layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
68
- "layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
69
- "layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
70
- "layers.15.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
71
- "layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
72
- "layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
73
- "layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
74
- "layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
75
- "layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
76
- "layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
77
- "layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
78
- "layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
79
- "layers.16.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
80
- "layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
81
- "layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
82
- "layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
83
- "layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
84
- "layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
85
- "layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
86
- "layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
87
- "layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
88
- "layers.17.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
89
- "layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
90
- "layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
91
- "layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
92
- "layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
93
- "layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
94
- "layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
95
- "layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
96
- "layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
97
- "layers.18.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
98
- "layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
99
- "layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
100
- "layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
101
- "layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
102
- "layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
103
- "layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
104
- "layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
105
- "layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
106
- "layers.19.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
107
- "layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
108
- "layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
109
- "layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
110
- "layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
111
- "layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
112
- "layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
113
- "layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
114
- "layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
115
- "layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
116
- "layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
117
- "layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
118
- "layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
119
- "layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
120
- "layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
121
- "layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
122
- "layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
123
- "layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
124
- "layers.20.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
125
- "layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
126
- "layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
127
- "layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
128
- "layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
129
- "layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
130
- "layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
131
- "layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
132
- "layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
133
- "layers.21.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
134
- "layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
135
- "layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
136
- "layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
137
- "layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
138
- "layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
139
- "layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
140
- "layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
141
- "layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
142
- "layers.22.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
143
- "layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
144
- "layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
145
- "layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
146
- "layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
147
- "layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
148
- "layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
149
- "layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
150
- "layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
151
- "layers.23.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
152
- "layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
153
- "layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
154
- "layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
155
- "layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
156
- "layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
157
- "layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
158
- "layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
159
- "layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
160
- "layers.24.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
161
- "layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
162
- "layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
163
- "layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
164
- "layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
165
- "layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
166
- "layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
167
- "layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
168
- "layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
169
- "layers.25.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
170
- "layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
171
- "layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
172
- "layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
173
- "layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
174
- "layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
175
- "layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
176
- "layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
177
- "layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
178
- "layers.26.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
179
- "layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
180
- "layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
181
- "layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
182
- "layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
183
- "layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
184
- "layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
185
- "layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
186
- "layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
187
- "layers.27.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
188
- "layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
189
- "layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
190
- "layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
191
- "layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
192
- "layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
193
- "layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
194
- "layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
195
- "layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
196
- "layers.28.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
197
- "layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
198
- "layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
199
- "layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
200
- "layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
201
- "layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
202
- "layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
203
- "layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
204
- "layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
205
- "layers.29.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
206
- "layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
207
- "layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
208
- "layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
209
- "layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
210
- "layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
211
- "layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
212
- "layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
213
- "layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
214
- "layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
215
- "layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
216
- "layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
217
- "layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
218
- "layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
219
- "layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
220
- "layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
221
- "layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
222
- "layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
223
- "layers.30.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
224
- "layers.30.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
225
- "layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
226
- "layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
227
- "layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
228
- "layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
229
- "layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
230
- "layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
231
- "layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
232
- "layers.31.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
233
- "layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
234
- "layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
235
- "layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
236
- "layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
237
- "layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
238
- "layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
239
- "layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
240
- "layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
241
- "layers.32.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
242
- "layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
243
- "layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
244
- "layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
245
- "layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
246
- "layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
247
- "layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
248
- "layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
249
- "layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
250
- "layers.33.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
251
- "layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
252
- "layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
253
- "layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
254
- "layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
255
- "layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
256
- "layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
257
- "layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
258
- "layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
259
- "layers.34.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
260
- "layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
261
- "layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
262
- "layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
263
- "layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
264
- "layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
265
- "layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
266
- "layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
267
- "layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
268
- "layers.35.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
269
- "layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
270
- "layers.35.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
271
- "layers.35.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
272
- "layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
273
- "layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
274
- "layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
275
- "layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
276
- "layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
277
- "layers.36.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
278
- "layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
279
- "layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
280
- "layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
281
- "layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
282
- "layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
283
- "layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
284
- "layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
285
- "layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
286
- "layers.37.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
287
- "layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
288
- "layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
289
- "layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
290
- "layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
291
- "layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
292
- "layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
293
- "layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
294
- "layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
295
- "layers.38.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
296
- "layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
297
- "layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
298
- "layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
299
- "layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
300
- "layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
301
- "layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
302
- "layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
303
- "layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
304
- "layers.39.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
305
- "layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
306
- "layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
307
- "layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
308
- "layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
309
- "layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
310
- "layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
311
- "layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
312
- "layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
313
- "layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
314
- "layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
315
- "layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
316
- "layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
317
- "layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
318
- "layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
319
- "layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
320
- "layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
321
- "layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
322
- "layers.5.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
323
- "layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
324
- "layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
325
- "layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
326
- "layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
327
- "layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
328
- "layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
329
- "layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
330
- "layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
331
- "layers.6.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
332
- "layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
333
- "layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
334
- "layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
335
- "layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
336
- "layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
337
- "layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
338
- "layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
339
- "layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
340
- "layers.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
341
- "layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
342
- "layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
343
- "layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
344
- "layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
345
- "layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
346
- "layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
347
- "layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
348
- "layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
349
- "layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
350
- "layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
351
- "layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
352
- "layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
353
- "layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
354
- "layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
355
- "layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
356
- "layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
357
- "layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
358
- "layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
359
- "layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
360
- "layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
361
- "layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
362
- "layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
363
- "layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
364
- "layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
365
- "layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
366
- "layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
367
- "norm.weight": "pytorch_model-00006-of-00006.bin"
 
368
  }
369
  }
 
1
  {
2
  "metadata": {
3
+ "total_size": 52063457280
4
  },
5
  "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00006-of-00006.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
16
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
17
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
18
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
19
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
20
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
22
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
23
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
24
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
25
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
26
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
27
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
28
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
29
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
30
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
31
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
32
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
33
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
34
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
35
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
36
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
37
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
38
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
39
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
40
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
41
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
42
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
43
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
44
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
45
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
46
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
47
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
48
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
49
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
50
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
51
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
52
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
53
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
54
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
55
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
56
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
57
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
58
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
59
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
60
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
61
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
62
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
63
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
64
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
65
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
66
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
67
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
68
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
69
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
70
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
71
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
72
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
73
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
74
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
75
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
76
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
77
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
78
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
79
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
80
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
81
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
82
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
83
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
84
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
85
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
86
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
87
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
88
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
89
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
90
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
91
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
92
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
93
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
94
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
95
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
96
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
97
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
98
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
99
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
100
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
101
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
102
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
103
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
104
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
105
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
106
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
107
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
108
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
109
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
110
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
111
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
112
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
113
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
114
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
115
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
116
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
117
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
118
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
119
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
120
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
121
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
122
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
123
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
124
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
125
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
126
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
127
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
128
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
129
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
130
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
131
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
132
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
133
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
134
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
135
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
136
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
137
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
138
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
139
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
140
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
141
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
142
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
143
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
144
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
145
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
146
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
147
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
148
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
149
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
150
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
151
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
152
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
153
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
154
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
155
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
156
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
157
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
158
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
159
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
160
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
161
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
162
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
163
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
164
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
165
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
166
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
167
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
168
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
169
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
170
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
171
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
172
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
173
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
174
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
175
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
176
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
177
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
178
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
179
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
180
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
181
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
182
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
183
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
184
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
185
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
186
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
187
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
188
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
189
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
190
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
191
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
192
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
193
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
194
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
195
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
196
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
197
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
198
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
199
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
200
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
201
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
202
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
203
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
204
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
205
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
206
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
207
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
208
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
209
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
210
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
211
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
212
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
213
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
214
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
215
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
216
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
217
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
218
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
219
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
220
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
221
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
222
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
223
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
224
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
225
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
226
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
227
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
228
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
229
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
230
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
231
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
232
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
233
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
234
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
235
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
236
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
237
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
238
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
239
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
240
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
241
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
242
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
243
+ "model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
244
+ "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
245
+ "model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
246
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
247
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
248
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
249
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
250
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
251
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
252
+ "model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
253
+ "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
254
+ "model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
255
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
256
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
257
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
258
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
259
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
260
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
261
+ "model.layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
262
+ "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
263
+ "model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
264
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
265
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
266
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
267
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
268
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
269
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
270
+ "model.layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
271
+ "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
272
+ "model.layers.35.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
273
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
274
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
275
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
276
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
277
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
278
+ "model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
279
+ "model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
280
+ "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
281
+ "model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
282
+ "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
283
+ "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
284
+ "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
285
+ "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
286
+ "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
287
+ "model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
288
+ "model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
289
+ "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
290
+ "model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
291
+ "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
292
+ "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
293
+ "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
294
+ "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
295
+ "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
296
+ "model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
297
+ "model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
298
+ "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
299
+ "model.layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
300
+ "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
301
+ "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
302
+ "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
303
+ "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
304
+ "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
305
+ "model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
306
+ "model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
307
+ "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
308
+ "model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
309
+ "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
310
+ "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
311
+ "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
312
+ "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
313
+ "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
314
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
315
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
316
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
317
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
318
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
319
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
320
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
321
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
322
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
323
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
324
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
325
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
326
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
327
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
328
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
329
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
330
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
331
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
332
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
333
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
334
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
335
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
336
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
337
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
338
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
339
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
340
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
341
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
342
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
343
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
344
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
345
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
346
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
347
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
348
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
349
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
350
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
351
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
352
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
353
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
354
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
355
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
356
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
357
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
358
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
359
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
360
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
361
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
362
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
363
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
364
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
365
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
366
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
367
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
368
+ "model.norm.weight": "pytorch_model-00006-of-00006.bin"
369
  }
370
  }