Hugging Face's logo

Aleph-Alpha
/
Pharia-1-LLM-7B-control-hf

Text Generation
Transformers
Safetensors
pharia-v1
conversational
custom_code
Model card Files Community
6
ArturBaranowskiAA commited on
Commit
6f39d18
•
1 Parent(s): 16288b0

Update weights to bfloat16.

Browse files
Files changed (7) hide show
  1. model-00001-of-00006.safetensors → model-00001-of-00003.safetensors +2 -2
  2. model-00002-of-00006.safetensors → model-00002-of-00003.safetensors +2 -2
  3. model-00003-of-00006.safetensors → model-00003-of-00003.safetensors +2 -2
  4. model-00004-of-00006.safetensors +0 -3
  5. model-00005-of-00006.safetensors +0 -3
  6. model-00006-of-00006.safetensors +0 -3
  7. model.safetensors.index.json +437 -437
model-00001-of-00006.safetensors → model-00001-of-00003.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3009a9aa25882572e6ba3f18f6f5563f70190698d38586619698f46c9309c90
3
- size 4964584832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44ef561687e6c3922b27138c219d4949c9e03252d7025388233c19266ad7466e
3
+ size 4917673288
model-00002-of-00006.safetensors → model-00002-of-00003.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f560242d251889eda5a665773b925c1f3367cba42d6f29701ae2d1c0c55059d9
3
- size 4870745896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0431d3e8fdda20289ad6c31bd36230916fe47fcfa25a1e5b49caf1f91f4fa7a
3
+ size 4998205232
model-00003-of-00006.safetensors → model-00003-of-00003.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bcccc898c4b052d47ea1c536c39a5e6a2d714ff67bca9367e464684b083c50f6
3
- size 4870764856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c0f3839cda99222440ed1e2db0ed3b03622cbdf4e2494e89b94169e63eb6d7e
3
+ size 4167260232
model-00004-of-00006.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:16031b5dd1ce7e73159a97119b4d4fe7a70913108e6a40cdf9cefb9037f24767
3
- size 4681960456
 
 
 
 
model-00005-of-00006.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:001ef60478b026109e6f48b9973a682f6ee7c3ce8864eb8a70bac9ee188cb0b2
3
- size 4870764888
 
 
 
 
model-00006-of-00006.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:867fedb5b5780c6d2ec05c34c8b9e6dca337d201b72cc4a9dc0269404c157c86
3
- size 3907406784
 
 
 
 
model.safetensors.index.json CHANGED
@@ -1,443 +1,443 @@
1
  {
2
  "metadata": {
3
- "total_size": 28166178816
4
  },
5
  "weight_map": {
6
- "lm_head.weight": "model-00006-of-00006.safetensors",
7
- "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
8
- "model.layers.0.input_layernorm.bias": "model-00001-of-00006.safetensors",
9
- "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
10
- "model.layers.0.mlp.down_proj.bias": "model-00001-of-00006.safetensors",
11
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
12
- "model.layers.0.mlp.up_proj.bias": "model-00001-of-00006.safetensors",
13
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
14
- "model.layers.0.post_attention_layernorm.bias": "model-00001-of-00006.safetensors",
15
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
16
- "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
17
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
18
- "model.layers.0.self_attn.o_proj.bias": "model-00001-of-00006.safetensors",
19
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
20
- "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
21
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
22
- "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
23
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
24
- "model.layers.1.input_layernorm.bias": "model-00001-of-00006.safetensors",
25
- "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
26
- "model.layers.1.mlp.down_proj.bias": "model-00001-of-00006.safetensors",
27
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
28
- "model.layers.1.mlp.up_proj.bias": "model-00001-of-00006.safetensors",
29
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
30
- "model.layers.1.post_attention_layernorm.bias": "model-00001-of-00006.safetensors",
31
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
32
- "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
33
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
34
- "model.layers.1.self_attn.o_proj.bias": "model-00001-of-00006.safetensors",
35
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
36
- "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
37
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
38
- "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
39
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
40
- "model.layers.10.input_layernorm.bias": "model-00003-of-00006.safetensors",
41
- "model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
42
- "model.layers.10.mlp.down_proj.bias": "model-00003-of-00006.safetensors",
43
- "model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
44
- "model.layers.10.mlp.up_proj.bias": "model-00003-of-00006.safetensors",
45
- "model.layers.10.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
46
- "model.layers.10.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
47
- "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
48
- "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
49
- "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
50
- "model.layers.10.self_attn.o_proj.bias": "model-00003-of-00006.safetensors",
51
- "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
52
- "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
53
- "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
54
- "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
55
- "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
56
- "model.layers.11.input_layernorm.bias": "model-00003-of-00006.safetensors",
57
- "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
58
- "model.layers.11.mlp.down_proj.bias": "model-00003-of-00006.safetensors",
59
- "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
60
- "model.layers.11.mlp.up_proj.bias": "model-00003-of-00006.safetensors",
61
- "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
62
- "model.layers.11.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
63
- "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
64
- "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
65
- "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
66
- "model.layers.11.self_attn.o_proj.bias": "model-00003-of-00006.safetensors",
67
- "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
68
- "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
69
- "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
70
- "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
71
- "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
72
- "model.layers.12.input_layernorm.bias": "model-00003-of-00006.safetensors",
73
- "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
74
- "model.layers.12.mlp.down_proj.bias": "model-00003-of-00006.safetensors",
75
- "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
76
- "model.layers.12.mlp.up_proj.bias": "model-00003-of-00006.safetensors",
77
- "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
78
- "model.layers.12.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
79
- "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
80
- "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
81
- "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
82
- "model.layers.12.self_attn.o_proj.bias": "model-00003-of-00006.safetensors",
83
- "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
84
- "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
85
- "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
86
- "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
87
- "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
88
- "model.layers.13.input_layernorm.bias": "model-00003-of-00006.safetensors",
89
- "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
90
- "model.layers.13.mlp.down_proj.bias": "model-00003-of-00006.safetensors",
91
- "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
92
- "model.layers.13.mlp.up_proj.bias": "model-00003-of-00006.safetensors",
93
- "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
94
- "model.layers.13.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
95
- "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
96
- "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
97
- "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
98
- "model.layers.13.self_attn.o_proj.bias": "model-00003-of-00006.safetensors",
99
- "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
100
- "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
101
- "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
102
- "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
103
- "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
104
- "model.layers.14.input_layernorm.bias": "model-00004-of-00006.safetensors",
105
- "model.layers.14.input_layernorm.weight": "model-00004-of-00006.safetensors",
106
- "model.layers.14.mlp.down_proj.bias": "model-00004-of-00006.safetensors",
107
- "model.layers.14.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
108
- "model.layers.14.mlp.up_proj.bias": "model-00004-of-00006.safetensors",
109
- "model.layers.14.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
110
- "model.layers.14.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
111
- "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
112
- "model.layers.14.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
113
- "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
114
- "model.layers.14.self_attn.o_proj.bias": "model-00003-of-00006.safetensors",
115
- "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
116
- "model.layers.14.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
117
- "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
118
- "model.layers.14.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
119
- "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
120
- "model.layers.15.input_layernorm.bias": "model-00004-of-00006.safetensors",
121
- "model.layers.15.input_layernorm.weight": "model-00004-of-00006.safetensors",
122
- "model.layers.15.mlp.down_proj.bias": "model-00004-of-00006.safetensors",
123
- "model.layers.15.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
124
- "model.layers.15.mlp.up_proj.bias": "model-00004-of-00006.safetensors",
125
- "model.layers.15.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
126
- "model.layers.15.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
127
- "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
128
- "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
129
- "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
130
- "model.layers.15.self_attn.o_proj.bias": "model-00004-of-00006.safetensors",
131
- "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
132
- "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
133
- "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
134
- "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
135
- "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
136
- "model.layers.16.input_layernorm.bias": "model-00004-of-00006.safetensors",
137
- "model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
138
- "model.layers.16.mlp.down_proj.bias": "model-00004-of-00006.safetensors",
139
- "model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
140
- "model.layers.16.mlp.up_proj.bias": "model-00004-of-00006.safetensors",
141
- "model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
142
- "model.layers.16.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
143
- "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
144
- "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
145
- "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
146
- "model.layers.16.self_attn.o_proj.bias": "model-00004-of-00006.safetensors",
147
- "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
148
- "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
149
- "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
150
- "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
151
- "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
152
- "model.layers.17.input_layernorm.bias": "model-00004-of-00006.safetensors",
153
- "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
154
- "model.layers.17.mlp.down_proj.bias": "model-00004-of-00006.safetensors",
155
- "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
156
- "model.layers.17.mlp.up_proj.bias": "model-00004-of-00006.safetensors",
157
- "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
158
- "model.layers.17.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
159
- "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
160
- "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
161
- "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
162
- "model.layers.17.self_attn.o_proj.bias": "model-00004-of-00006.safetensors",
163
- "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
164
- "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
165
- "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
166
- "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
167
- "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
168
- "model.layers.18.input_layernorm.bias": "model-00004-of-00006.safetensors",
169
- "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
170
- "model.layers.18.mlp.down_proj.bias": "model-00004-of-00006.safetensors",
171
- "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
172
- "model.layers.18.mlp.up_proj.bias": "model-00004-of-00006.safetensors",
173
- "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
174
- "model.layers.18.post_attention_layernorm.bias": "model-00004-of-00006.safetensors",
175
- "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
176
- "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
177
- "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
178
- "model.layers.18.self_attn.o_proj.bias": "model-00004-of-00006.safetensors",
179
- "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
180
- "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
181
- "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
182
- "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
183
- "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
184
- "model.layers.19.input_layernorm.bias": "model-00005-of-00006.safetensors",
185
- "model.layers.19.input_layernorm.weight": "model-00005-of-00006.safetensors",
186
- "model.layers.19.mlp.down_proj.bias": "model-00005-of-00006.safetensors",
187
- "model.layers.19.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
188
- "model.layers.19.mlp.up_proj.bias": "model-00004-of-00006.safetensors",
189
- "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
190
- "model.layers.19.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
191
- "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
192
- "model.layers.19.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
193
- "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
194
- "model.layers.19.self_attn.o_proj.bias": "model-00004-of-00006.safetensors",
195
- "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
196
- "model.layers.19.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
197
- "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
198
- "model.layers.19.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
199
- "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
200
- "model.layers.2.input_layernorm.bias": "model-00001-of-00006.safetensors",
201
- "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
202
- "model.layers.2.mlp.down_proj.bias": "model-00001-of-00006.safetensors",
203
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
204
- "model.layers.2.mlp.up_proj.bias": "model-00001-of-00006.safetensors",
205
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
206
- "model.layers.2.post_attention_layernorm.bias": "model-00001-of-00006.safetensors",
207
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
208
- "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
209
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
210
- "model.layers.2.self_attn.o_proj.bias": "model-00001-of-00006.safetensors",
211
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
212
- "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
213
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
214
- "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
215
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
216
- "model.layers.20.input_layernorm.bias": "model-00005-of-00006.safetensors",
217
- "model.layers.20.input_layernorm.weight": "model-00005-of-00006.safetensors",
218
- "model.layers.20.mlp.down_proj.bias": "model-00005-of-00006.safetensors",
219
- "model.layers.20.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
220
- "model.layers.20.mlp.up_proj.bias": "model-00005-of-00006.safetensors",
221
- "model.layers.20.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
222
- "model.layers.20.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
223
- "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
224
- "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
225
- "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
226
- "model.layers.20.self_attn.o_proj.bias": "model-00005-of-00006.safetensors",
227
- "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
228
- "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
229
- "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
230
- "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
231
- "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
232
- "model.layers.21.input_layernorm.bias": "model-00005-of-00006.safetensors",
233
- "model.layers.21.input_layernorm.weight": "model-00005-of-00006.safetensors",
234
- "model.layers.21.mlp.down_proj.bias": "model-00005-of-00006.safetensors",
235
- "model.layers.21.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
236
- "model.layers.21.mlp.up_proj.bias": "model-00005-of-00006.safetensors",
237
- "model.layers.21.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
238
- "model.layers.21.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
239
- "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
240
- "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
241
- "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
242
- "model.layers.21.self_attn.o_proj.bias": "model-00005-of-00006.safetensors",
243
- "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
244
- "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
245
- "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
246
- "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
247
- "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
248
- "model.layers.22.input_layernorm.bias": "model-00005-of-00006.safetensors",
249
- "model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
250
- "model.layers.22.mlp.down_proj.bias": "model-00005-of-00006.safetensors",
251
- "model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
252
- "model.layers.22.mlp.up_proj.bias": "model-00005-of-00006.safetensors",
253
- "model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
254
- "model.layers.22.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
255
- "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
256
- "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
257
- "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
258
- "model.layers.22.self_attn.o_proj.bias": "model-00005-of-00006.safetensors",
259
- "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
260
- "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
261
- "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
262
- "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
263
- "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
264
- "model.layers.23.input_layernorm.bias": "model-00005-of-00006.safetensors",
265
- "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
266
- "model.layers.23.mlp.down_proj.bias": "model-00005-of-00006.safetensors",
267
- "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
268
- "model.layers.23.mlp.up_proj.bias": "model-00005-of-00006.safetensors",
269
- "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
270
- "model.layers.23.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
271
- "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
272
- "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
273
- "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
274
- "model.layers.23.self_attn.o_proj.bias": "model-00005-of-00006.safetensors",
275
- "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
276
- "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
277
- "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
278
- "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
279
- "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
280
- "model.layers.24.input_layernorm.bias": "model-00005-of-00006.safetensors",
281
- "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
282
- "model.layers.24.mlp.down_proj.bias": "model-00005-of-00006.safetensors",
283
- "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
284
- "model.layers.24.mlp.up_proj.bias": "model-00005-of-00006.safetensors",
285
- "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
286
- "model.layers.24.post_attention_layernorm.bias": "model-00005-of-00006.safetensors",
287
- "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
288
- "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
289
- "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
290
- "model.layers.24.self_attn.o_proj.bias": "model-00005-of-00006.safetensors",
291
- "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
292
- "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
293
- "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
294
- "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
295
- "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
296
- "model.layers.25.input_layernorm.bias": "model-00006-of-00006.safetensors",
297
- "model.layers.25.input_layernorm.weight": "model-00006-of-00006.safetensors",
298
- "model.layers.25.mlp.down_proj.bias": "model-00006-of-00006.safetensors",
299
- "model.layers.25.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
300
- "model.layers.25.mlp.up_proj.bias": "model-00006-of-00006.safetensors",
301
- "model.layers.25.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
302
- "model.layers.25.post_attention_layernorm.bias": "model-00006-of-00006.safetensors",
303
- "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
304
- "model.layers.25.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
305
- "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
306
- "model.layers.25.self_attn.o_proj.bias": "model-00005-of-00006.safetensors",
307
- "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
308
- "model.layers.25.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
309
- "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
310
- "model.layers.25.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
311
- "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
312
- "model.layers.26.input_layernorm.bias": "model-00006-of-00006.safetensors",
313
- "model.layers.26.input_layernorm.weight": "model-00006-of-00006.safetensors",
314
- "model.layers.26.mlp.down_proj.bias": "model-00006-of-00006.safetensors",
315
- "model.layers.26.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
316
- "model.layers.26.mlp.up_proj.bias": "model-00006-of-00006.safetensors",
317
- "model.layers.26.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
318
- "model.layers.26.post_attention_layernorm.bias": "model-00006-of-00006.safetensors",
319
- "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
320
- "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
321
- "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
322
- "model.layers.26.self_attn.o_proj.bias": "model-00006-of-00006.safetensors",
323
- "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
324
- "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
325
- "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
326
- "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
327
- "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
328
- "model.layers.3.input_layernorm.bias": "model-00002-of-00006.safetensors",
329
- "model.layers.3.input_layernorm.weight": "model-00002-of-00006.safetensors",
330
- "model.layers.3.mlp.down_proj.bias": "model-00002-of-00006.safetensors",
331
- "model.layers.3.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
332
- "model.layers.3.mlp.up_proj.bias": "model-00002-of-00006.safetensors",
333
- "model.layers.3.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
334
- "model.layers.3.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
335
- "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
336
- "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
337
- "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
338
- "model.layers.3.self_attn.o_proj.bias": "model-00002-of-00006.safetensors",
339
- "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
340
- "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
341
- "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
342
- "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
343
- "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
344
- "model.layers.4.input_layernorm.bias": "model-00002-of-00006.safetensors",
345
- "model.layers.4.input_layernorm.weight": "model-00002-of-00006.safetensors",
346
- "model.layers.4.mlp.down_proj.bias": "model-00002-of-00006.safetensors",
347
- "model.layers.4.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
348
- "model.layers.4.mlp.up_proj.bias": "model-00002-of-00006.safetensors",
349
- "model.layers.4.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
350
- "model.layers.4.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
351
- "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
352
- "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
353
- "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
354
- "model.layers.4.self_attn.o_proj.bias": "model-00002-of-00006.safetensors",
355
- "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
356
- "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
357
- "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
358
- "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
359
- "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
360
- "model.layers.5.input_layernorm.bias": "model-00002-of-00006.safetensors",
361
- "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
362
- "model.layers.5.mlp.down_proj.bias": "model-00002-of-00006.safetensors",
363
- "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
364
- "model.layers.5.mlp.up_proj.bias": "model-00002-of-00006.safetensors",
365
- "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
366
- "model.layers.5.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
367
- "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
368
- "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
369
- "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
370
- "model.layers.5.self_attn.o_proj.bias": "model-00002-of-00006.safetensors",
371
- "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
372
- "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
373
- "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
374
- "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
375
- "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
376
- "model.layers.6.input_layernorm.bias": "model-00002-of-00006.safetensors",
377
- "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
378
- "model.layers.6.mlp.down_proj.bias": "model-00002-of-00006.safetensors",
379
- "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
380
- "model.layers.6.mlp.up_proj.bias": "model-00002-of-00006.safetensors",
381
- "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
382
- "model.layers.6.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
383
- "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
384
- "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
385
- "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
386
- "model.layers.6.self_attn.o_proj.bias": "model-00002-of-00006.safetensors",
387
- "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
388
- "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
389
- "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
390
- "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
391
- "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
392
- "model.layers.7.input_layernorm.bias": "model-00002-of-00006.safetensors",
393
- "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
394
- "model.layers.7.mlp.down_proj.bias": "model-00002-of-00006.safetensors",
395
- "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
396
- "model.layers.7.mlp.up_proj.bias": "model-00002-of-00006.safetensors",
397
- "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
398
- "model.layers.7.post_attention_layernorm.bias": "model-00002-of-00006.safetensors",
399
- "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
400
- "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
401
- "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
402
- "model.layers.7.self_attn.o_proj.bias": "model-00002-of-00006.safetensors",
403
- "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
404
- "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
405
- "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
406
- "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
407
- "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
408
- "model.layers.8.input_layernorm.bias": "model-00003-of-00006.safetensors",
409
- "model.layers.8.input_layernorm.weight": "model-00003-of-00006.safetensors",
410
- "model.layers.8.mlp.down_proj.bias": "model-00003-of-00006.safetensors",
411
- "model.layers.8.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
412
- "model.layers.8.mlp.up_proj.bias": "model-00002-of-00006.safetensors",
413
- "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
414
- "model.layers.8.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
415
- "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
416
- "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
417
- "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
418
- "model.layers.8.self_attn.o_proj.bias": "model-00002-of-00006.safetensors",
419
- "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
420
- "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
421
- "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
422
- "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
423
- "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
424
- "model.layers.9.input_layernorm.bias": "model-00003-of-00006.safetensors",
425
- "model.layers.9.input_layernorm.weight": "model-00003-of-00006.safetensors",
426
- "model.layers.9.mlp.down_proj.bias": "model-00003-of-00006.safetensors",
427
- "model.layers.9.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
428
- "model.layers.9.mlp.up_proj.bias": "model-00003-of-00006.safetensors",
429
- "model.layers.9.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
430
- "model.layers.9.post_attention_layernorm.bias": "model-00003-of-00006.safetensors",
431
- "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
432
- "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
433
- "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
434
- "model.layers.9.self_attn.o_proj.bias": "model-00003-of-00006.safetensors",
435
- "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
436
- "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
437
- "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
438
- "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
439
- "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
440
- "model.norm.bias": "model-00006-of-00006.safetensors",
441
- "model.norm.weight": "model-00006-of-00006.safetensors"
442
  }
443
  }
 
1
  {
2
  "metadata": {
3
+ "total_size": 14083089408
4
  },
5
  "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.bias": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
17
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.0.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
19
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
21
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
23
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.1.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
27
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
28
+ "model.layers.1.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
29
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.1.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
31
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
33
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.1.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
35
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
36
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
37
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
38
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
39
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
40
+ "model.layers.10.input_layernorm.bias": "model-00002-of-00003.safetensors",
41
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
42
+ "model.layers.10.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
43
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.10.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
45
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.10.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
47
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
49
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.10.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
51
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
53
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
55
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.11.input_layernorm.bias": "model-00002-of-00003.safetensors",
57
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.11.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
59
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.11.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
61
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.11.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
63
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
65
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.11.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
67
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
69
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
71
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.12.input_layernorm.bias": "model-00002-of-00003.safetensors",
73
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.12.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
75
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.12.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
77
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.12.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
79
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
81
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.12.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
83
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
85
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
87
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.13.input_layernorm.bias": "model-00002-of-00003.safetensors",
89
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.13.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
91
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.13.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
93
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.13.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
95
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
97
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.13.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
99
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
101
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
103
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.14.input_layernorm.bias": "model-00002-of-00003.safetensors",
105
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.14.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
107
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.14.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
109
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.14.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
111
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
113
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.14.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
115
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
117
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
118
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
119
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
120
+ "model.layers.15.input_layernorm.bias": "model-00002-of-00003.safetensors",
121
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
122
+ "model.layers.15.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
123
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
124
+ "model.layers.15.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
125
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.15.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
127
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
129
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.15.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
131
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
133
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
135
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.16.input_layernorm.bias": "model-00002-of-00003.safetensors",
137
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.16.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
139
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.16.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
141
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.16.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
143
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
144
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
145
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
146
+ "model.layers.16.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
147
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
148
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
149
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
151
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.17.input_layernorm.bias": "model-00002-of-00003.safetensors",
153
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
154
+ "model.layers.17.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
155
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
156
+ "model.layers.17.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
157
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
158
+ "model.layers.17.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
159
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
160
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
161
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
162
+ "model.layers.17.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
163
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
164
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
165
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
166
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
167
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
168
+ "model.layers.18.input_layernorm.bias": "model-00002-of-00003.safetensors",
169
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
170
+ "model.layers.18.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
171
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
172
+ "model.layers.18.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
173
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
174
+ "model.layers.18.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
175
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
176
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
177
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
178
+ "model.layers.18.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
179
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
180
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
181
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
182
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
183
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
184
+ "model.layers.19.input_layernorm.bias": "model-00002-of-00003.safetensors",
185
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
186
+ "model.layers.19.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
187
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
188
+ "model.layers.19.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
189
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
190
+ "model.layers.19.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
191
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
192
+ "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
193
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
194
+ "model.layers.19.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
195
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
196
+ "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
197
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
198
+ "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
199
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
200
+ "model.layers.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
201
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
202
+ "model.layers.2.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
203
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
204
+ "model.layers.2.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
205
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
206
+ "model.layers.2.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
207
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
208
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
209
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
210
+ "model.layers.2.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
211
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
212
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
213
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
214
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
215
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.20.input_layernorm.bias": "model-00003-of-00003.safetensors",
217
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
218
+ "model.layers.20.mlp.down_proj.bias": "model-00003-of-00003.safetensors",
219
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
220
+ "model.layers.20.mlp.up_proj.bias": "model-00003-of-00003.safetensors",
221
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
222
+ "model.layers.20.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
223
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
224
+ "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
225
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
226
+ "model.layers.20.self_attn.o_proj.bias": "model-00003-of-00003.safetensors",
227
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
228
+ "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
229
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
230
+ "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
231
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
232
+ "model.layers.21.input_layernorm.bias": "model-00003-of-00003.safetensors",
233
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
+ "model.layers.21.mlp.down_proj.bias": "model-00003-of-00003.safetensors",
235
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
236
+ "model.layers.21.mlp.up_proj.bias": "model-00003-of-00003.safetensors",
237
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
238
+ "model.layers.21.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
239
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
240
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
241
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
242
+ "model.layers.21.self_attn.o_proj.bias": "model-00003-of-00003.safetensors",
243
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
244
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
245
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
246
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
247
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
248
+ "model.layers.22.input_layernorm.bias": "model-00003-of-00003.safetensors",
249
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
250
+ "model.layers.22.mlp.down_proj.bias": "model-00003-of-00003.safetensors",
251
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
252
+ "model.layers.22.mlp.up_proj.bias": "model-00003-of-00003.safetensors",
253
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
254
+ "model.layers.22.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
255
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
256
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
257
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
258
+ "model.layers.22.self_attn.o_proj.bias": "model-00003-of-00003.safetensors",
259
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
260
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
261
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
262
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
263
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
264
+ "model.layers.23.input_layernorm.bias": "model-00003-of-00003.safetensors",
265
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
266
+ "model.layers.23.mlp.down_proj.bias": "model-00003-of-00003.safetensors",
267
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
268
+ "model.layers.23.mlp.up_proj.bias": "model-00003-of-00003.safetensors",
269
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
270
+ "model.layers.23.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
271
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
272
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
273
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
274
+ "model.layers.23.self_attn.o_proj.bias": "model-00003-of-00003.safetensors",
275
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
276
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
277
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
278
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
279
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
280
+ "model.layers.24.input_layernorm.bias": "model-00003-of-00003.safetensors",
281
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
282
+ "model.layers.24.mlp.down_proj.bias": "model-00003-of-00003.safetensors",
283
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
284
+ "model.layers.24.mlp.up_proj.bias": "model-00003-of-00003.safetensors",
285
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
286
+ "model.layers.24.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
287
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
288
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
289
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
290
+ "model.layers.24.self_attn.o_proj.bias": "model-00003-of-00003.safetensors",
291
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
292
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
293
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
294
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
295
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
296
+ "model.layers.25.input_layernorm.bias": "model-00003-of-00003.safetensors",
297
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
298
+ "model.layers.25.mlp.down_proj.bias": "model-00003-of-00003.safetensors",
299
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
300
+ "model.layers.25.mlp.up_proj.bias": "model-00003-of-00003.safetensors",
301
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
302
+ "model.layers.25.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
303
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
304
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
305
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
306
+ "model.layers.25.self_attn.o_proj.bias": "model-00003-of-00003.safetensors",
307
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
308
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
309
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
310
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
311
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
312
+ "model.layers.26.input_layernorm.bias": "model-00003-of-00003.safetensors",
313
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
314
+ "model.layers.26.mlp.down_proj.bias": "model-00003-of-00003.safetensors",
315
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
316
+ "model.layers.26.mlp.up_proj.bias": "model-00003-of-00003.safetensors",
317
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
318
+ "model.layers.26.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
319
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
320
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
321
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
322
+ "model.layers.26.self_attn.o_proj.bias": "model-00003-of-00003.safetensors",
323
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
324
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
325
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
326
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
327
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
328
+ "model.layers.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
329
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
330
+ "model.layers.3.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
331
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
332
+ "model.layers.3.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
333
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
334
+ "model.layers.3.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
335
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
336
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
337
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
338
+ "model.layers.3.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
339
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
340
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
341
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
342
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
343
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
344
+ "model.layers.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
345
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
346
+ "model.layers.4.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
347
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
348
+ "model.layers.4.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
349
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
350
+ "model.layers.4.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
351
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
352
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
353
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
354
+ "model.layers.4.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
355
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
356
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
357
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
358
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
359
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
360
+ "model.layers.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
361
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
362
+ "model.layers.5.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
363
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
364
+ "model.layers.5.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
365
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
366
+ "model.layers.5.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
367
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
368
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
369
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
370
+ "model.layers.5.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
371
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
372
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
373
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
374
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
375
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
376
+ "model.layers.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
377
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
378
+ "model.layers.6.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
379
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
380
+ "model.layers.6.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
381
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
382
+ "model.layers.6.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
383
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
384
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
385
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
386
+ "model.layers.6.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
387
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
388
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
389
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
390
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
391
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
392
+ "model.layers.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
393
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
394
+ "model.layers.7.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
395
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
396
+ "model.layers.7.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
397
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
398
+ "model.layers.7.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
399
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
400
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
401
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
402
+ "model.layers.7.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
403
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
404
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
405
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
406
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
407
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
408
+ "model.layers.8.input_layernorm.bias": "model-00002-of-00003.safetensors",
409
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
410
+ "model.layers.8.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
411
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
412
+ "model.layers.8.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
413
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
414
+ "model.layers.8.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
415
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
416
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
417
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
418
+ "model.layers.8.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
419
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
420
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
421
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
422
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
423
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
424
+ "model.layers.9.input_layernorm.bias": "model-00002-of-00003.safetensors",
425
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
426
+ "model.layers.9.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
427
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
428
+ "model.layers.9.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
429
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
430
+ "model.layers.9.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
431
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
432
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
433
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
434
+ "model.layers.9.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
435
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
436
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
437
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
438
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
439
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
440
+ "model.norm.bias": "model-00003-of-00003.safetensors",
441
+ "model.norm.weight": "model-00003-of-00003.safetensors"
442
  }
443
  }