Hugging Face's logo

danielcfho
/
qwen2-0.5b-instruct-mlx

Text Generation
MLX
Safetensors
English
qwen2
chat
conversational
Model card Files Community
danielcfho commited on
Commit
72961c9
·
verified ·
1 Parent(s): a87cccb

Add files using upload-large-folder tool

Browse files
Files changed (3) hide show
  1. config.json +0 -4
  2. model.safetensors +2 -2
  3. model.safetensors.index.json +1 -339
config.json CHANGED
@@ -19,10 +19,6 @@
19
  "group_size": 64,
20
  "bits": 4
21
  },
22
- "quantization_config": {
23
- "group_size": 64,
24
- "bits": 4
25
- },
26
  "rms_norm_eps": 1e-06,
27
  "rope_theta": 1000000.0,
28
  "sliding_window": 32768,
 
19
  "group_size": 64,
20
  "bits": 4
21
  },
 
 
 
 
22
  "rms_norm_eps": 1e-06,
23
  "rope_theta": 1000000.0,
24
  "sliding_window": 32768,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c1364a025ae1b224b595c10ba55e58a4d0b45d381381cfa26bf78f3f46b950c
3
- size 309080542
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:641fc4318c5878c2d5d4a99aae2e2b1d186f91820df27414407dfa0fa63e3434
3
+ size 988097440
model.safetensors.index.json CHANGED
@@ -1,634 +1,296 @@
1
  {
2
  "metadata": {
3
- "total_size": 309011968
4
  },
5
  "weight_map": {
6
- "model.embed_tokens.biases": "model.safetensors",
7
- "model.embed_tokens.scales": "model.safetensors",
8
  "model.embed_tokens.weight": "model.safetensors",
9
  "model.layers.0.input_layernorm.weight": "model.safetensors",
10
- "model.layers.0.mlp.down_proj.biases": "model.safetensors",
11
- "model.layers.0.mlp.down_proj.scales": "model.safetensors",
12
  "model.layers.0.mlp.down_proj.weight": "model.safetensors",
13
- "model.layers.0.mlp.gate_proj.biases": "model.safetensors",
14
- "model.layers.0.mlp.gate_proj.scales": "model.safetensors",
15
  "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
16
- "model.layers.0.mlp.up_proj.biases": "model.safetensors",
17
- "model.layers.0.mlp.up_proj.scales": "model.safetensors",
18
  "model.layers.0.mlp.up_proj.weight": "model.safetensors",
19
  "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
20
  "model.layers.0.self_attn.k_proj.bias": "model.safetensors",
21
- "model.layers.0.self_attn.k_proj.biases": "model.safetensors",
22
- "model.layers.0.self_attn.k_proj.scales": "model.safetensors",
23
  "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
24
- "model.layers.0.self_attn.o_proj.biases": "model.safetensors",
25
- "model.layers.0.self_attn.o_proj.scales": "model.safetensors",
26
  "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
27
  "model.layers.0.self_attn.q_proj.bias": "model.safetensors",
28
- "model.layers.0.self_attn.q_proj.biases": "model.safetensors",
29
- "model.layers.0.self_attn.q_proj.scales": "model.safetensors",
30
  "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
31
  "model.layers.0.self_attn.v_proj.bias": "model.safetensors",
32
- "model.layers.0.self_attn.v_proj.biases": "model.safetensors",
33
- "model.layers.0.self_attn.v_proj.scales": "model.safetensors",
34
  "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
35
  "model.layers.1.input_layernorm.weight": "model.safetensors",
36
- "model.layers.1.mlp.down_proj.biases": "model.safetensors",
37
- "model.layers.1.mlp.down_proj.scales": "model.safetensors",
38
  "model.layers.1.mlp.down_proj.weight": "model.safetensors",
39
- "model.layers.1.mlp.gate_proj.biases": "model.safetensors",
40
- "model.layers.1.mlp.gate_proj.scales": "model.safetensors",
41
  "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
42
- "model.layers.1.mlp.up_proj.biases": "model.safetensors",
43
- "model.layers.1.mlp.up_proj.scales": "model.safetensors",
44
  "model.layers.1.mlp.up_proj.weight": "model.safetensors",
45
  "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
46
  "model.layers.1.self_attn.k_proj.bias": "model.safetensors",
47
- "model.layers.1.self_attn.k_proj.biases": "model.safetensors",
48
- "model.layers.1.self_attn.k_proj.scales": "model.safetensors",
49
  "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
50
- "model.layers.1.self_attn.o_proj.biases": "model.safetensors",
51
- "model.layers.1.self_attn.o_proj.scales": "model.safetensors",
52
  "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
53
  "model.layers.1.self_attn.q_proj.bias": "model.safetensors",
54
- "model.layers.1.self_attn.q_proj.biases": "model.safetensors",
55
- "model.layers.1.self_attn.q_proj.scales": "model.safetensors",
56
  "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
57
  "model.layers.1.self_attn.v_proj.bias": "model.safetensors",
58
- "model.layers.1.self_attn.v_proj.biases": "model.safetensors",
59
- "model.layers.1.self_attn.v_proj.scales": "model.safetensors",
60
  "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
61
  "model.layers.10.input_layernorm.weight": "model.safetensors",
62
- "model.layers.10.mlp.down_proj.biases": "model.safetensors",
63
- "model.layers.10.mlp.down_proj.scales": "model.safetensors",
64
  "model.layers.10.mlp.down_proj.weight": "model.safetensors",
65
- "model.layers.10.mlp.gate_proj.biases": "model.safetensors",
66
- "model.layers.10.mlp.gate_proj.scales": "model.safetensors",
67
  "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
68
- "model.layers.10.mlp.up_proj.biases": "model.safetensors",
69
- "model.layers.10.mlp.up_proj.scales": "model.safetensors",
70
  "model.layers.10.mlp.up_proj.weight": "model.safetensors",
71
  "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
72
  "model.layers.10.self_attn.k_proj.bias": "model.safetensors",
73
- "model.layers.10.self_attn.k_proj.biases": "model.safetensors",
74
- "model.layers.10.self_attn.k_proj.scales": "model.safetensors",
75
  "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
76
- "model.layers.10.self_attn.o_proj.biases": "model.safetensors",
77
- "model.layers.10.self_attn.o_proj.scales": "model.safetensors",
78
  "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
79
  "model.layers.10.self_attn.q_proj.bias": "model.safetensors",
80
- "model.layers.10.self_attn.q_proj.biases": "model.safetensors",
81
- "model.layers.10.self_attn.q_proj.scales": "model.safetensors",
82
  "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
83
  "model.layers.10.self_attn.v_proj.bias": "model.safetensors",
84
- "model.layers.10.self_attn.v_proj.biases": "model.safetensors",
85
- "model.layers.10.self_attn.v_proj.scales": "model.safetensors",
86
  "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
87
  "model.layers.11.input_layernorm.weight": "model.safetensors",
88
- "model.layers.11.mlp.down_proj.biases": "model.safetensors",
89
- "model.layers.11.mlp.down_proj.scales": "model.safetensors",
90
  "model.layers.11.mlp.down_proj.weight": "model.safetensors",
91
- "model.layers.11.mlp.gate_proj.biases": "model.safetensors",
92
- "model.layers.11.mlp.gate_proj.scales": "model.safetensors",
93
  "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
94
- "model.layers.11.mlp.up_proj.biases": "model.safetensors",
95
- "model.layers.11.mlp.up_proj.scales": "model.safetensors",
96
  "model.layers.11.mlp.up_proj.weight": "model.safetensors",
97
  "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
98
  "model.layers.11.self_attn.k_proj.bias": "model.safetensors",
99
- "model.layers.11.self_attn.k_proj.biases": "model.safetensors",
100
- "model.layers.11.self_attn.k_proj.scales": "model.safetensors",
101
  "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
102
- "model.layers.11.self_attn.o_proj.biases": "model.safetensors",
103
- "model.layers.11.self_attn.o_proj.scales": "model.safetensors",
104
  "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
105
  "model.layers.11.self_attn.q_proj.bias": "model.safetensors",
106
- "model.layers.11.self_attn.q_proj.biases": "model.safetensors",
107
- "model.layers.11.self_attn.q_proj.scales": "model.safetensors",
108
  "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
109
  "model.layers.11.self_attn.v_proj.bias": "model.safetensors",
110
- "model.layers.11.self_attn.v_proj.biases": "model.safetensors",
111
- "model.layers.11.self_attn.v_proj.scales": "model.safetensors",
112
  "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
113
  "model.layers.12.input_layernorm.weight": "model.safetensors",
114
- "model.layers.12.mlp.down_proj.biases": "model.safetensors",
115
- "model.layers.12.mlp.down_proj.scales": "model.safetensors",
116
  "model.layers.12.mlp.down_proj.weight": "model.safetensors",
117
- "model.layers.12.mlp.gate_proj.biases": "model.safetensors",
118
- "model.layers.12.mlp.gate_proj.scales": "model.safetensors",
119
  "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
120
- "model.layers.12.mlp.up_proj.biases": "model.safetensors",
121
- "model.layers.12.mlp.up_proj.scales": "model.safetensors",
122
  "model.layers.12.mlp.up_proj.weight": "model.safetensors",
123
  "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
124
  "model.layers.12.self_attn.k_proj.bias": "model.safetensors",
125
- "model.layers.12.self_attn.k_proj.biases": "model.safetensors",
126
- "model.layers.12.self_attn.k_proj.scales": "model.safetensors",
127
  "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
128
- "model.layers.12.self_attn.o_proj.biases": "model.safetensors",
129
- "model.layers.12.self_attn.o_proj.scales": "model.safetensors",
130
  "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
131
  "model.layers.12.self_attn.q_proj.bias": "model.safetensors",
132
- "model.layers.12.self_attn.q_proj.biases": "model.safetensors",
133
- "model.layers.12.self_attn.q_proj.scales": "model.safetensors",
134
  "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
135
  "model.layers.12.self_attn.v_proj.bias": "model.safetensors",
136
- "model.layers.12.self_attn.v_proj.biases": "model.safetensors",
137
- "model.layers.12.self_attn.v_proj.scales": "model.safetensors",
138
  "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
139
  "model.layers.13.input_layernorm.weight": "model.safetensors",
140
- "model.layers.13.mlp.down_proj.biases": "model.safetensors",
141
- "model.layers.13.mlp.down_proj.scales": "model.safetensors",
142
  "model.layers.13.mlp.down_proj.weight": "model.safetensors",
143
- "model.layers.13.mlp.gate_proj.biases": "model.safetensors",
144
- "model.layers.13.mlp.gate_proj.scales": "model.safetensors",
145
  "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
146
- "model.layers.13.mlp.up_proj.biases": "model.safetensors",
147
- "model.layers.13.mlp.up_proj.scales": "model.safetensors",
148
  "model.layers.13.mlp.up_proj.weight": "model.safetensors",
149
  "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
150
  "model.layers.13.self_attn.k_proj.bias": "model.safetensors",
151
- "model.layers.13.self_attn.k_proj.biases": "model.safetensors",
152
- "model.layers.13.self_attn.k_proj.scales": "model.safetensors",
153
  "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
154
- "model.layers.13.self_attn.o_proj.biases": "model.safetensors",
155
- "model.layers.13.self_attn.o_proj.scales": "model.safetensors",
156
  "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
157
  "model.layers.13.self_attn.q_proj.bias": "model.safetensors",
158
- "model.layers.13.self_attn.q_proj.biases": "model.safetensors",
159
- "model.layers.13.self_attn.q_proj.scales": "model.safetensors",
160
  "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
161
  "model.layers.13.self_attn.v_proj.bias": "model.safetensors",
162
- "model.layers.13.self_attn.v_proj.biases": "model.safetensors",
163
- "model.layers.13.self_attn.v_proj.scales": "model.safetensors",
164
  "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
165
  "model.layers.14.input_layernorm.weight": "model.safetensors",
166
- "model.layers.14.mlp.down_proj.biases": "model.safetensors",
167
- "model.layers.14.mlp.down_proj.scales": "model.safetensors",
168
  "model.layers.14.mlp.down_proj.weight": "model.safetensors",
169
- "model.layers.14.mlp.gate_proj.biases": "model.safetensors",
170
- "model.layers.14.mlp.gate_proj.scales": "model.safetensors",
171
  "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
172
- "model.layers.14.mlp.up_proj.biases": "model.safetensors",
173
- "model.layers.14.mlp.up_proj.scales": "model.safetensors",
174
  "model.layers.14.mlp.up_proj.weight": "model.safetensors",
175
  "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
176
  "model.layers.14.self_attn.k_proj.bias": "model.safetensors",
177
- "model.layers.14.self_attn.k_proj.biases": "model.safetensors",
178
- "model.layers.14.self_attn.k_proj.scales": "model.safetensors",
179
  "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
180
- "model.layers.14.self_attn.o_proj.biases": "model.safetensors",
181
- "model.layers.14.self_attn.o_proj.scales": "model.safetensors",
182
  "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
183
  "model.layers.14.self_attn.q_proj.bias": "model.safetensors",
184
- "model.layers.14.self_attn.q_proj.biases": "model.safetensors",
185
- "model.layers.14.self_attn.q_proj.scales": "model.safetensors",
186
  "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
187
  "model.layers.14.self_attn.v_proj.bias": "model.safetensors",
188
- "model.layers.14.self_attn.v_proj.biases": "model.safetensors",
189
- "model.layers.14.self_attn.v_proj.scales": "model.safetensors",
190
  "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
191
  "model.layers.15.input_layernorm.weight": "model.safetensors",
192
- "model.layers.15.mlp.down_proj.biases": "model.safetensors",
193
- "model.layers.15.mlp.down_proj.scales": "model.safetensors",
194
  "model.layers.15.mlp.down_proj.weight": "model.safetensors",
195
- "model.layers.15.mlp.gate_proj.biases": "model.safetensors",
196
- "model.layers.15.mlp.gate_proj.scales": "model.safetensors",
197
  "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
198
- "model.layers.15.mlp.up_proj.biases": "model.safetensors",
199
- "model.layers.15.mlp.up_proj.scales": "model.safetensors",
200
  "model.layers.15.mlp.up_proj.weight": "model.safetensors",
201
  "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
202
  "model.layers.15.self_attn.k_proj.bias": "model.safetensors",
203
- "model.layers.15.self_attn.k_proj.biases": "model.safetensors",
204
- "model.layers.15.self_attn.k_proj.scales": "model.safetensors",
205
  "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
206
- "model.layers.15.self_attn.o_proj.biases": "model.safetensors",
207
- "model.layers.15.self_attn.o_proj.scales": "model.safetensors",
208
  "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
209
  "model.layers.15.self_attn.q_proj.bias": "model.safetensors",
210
- "model.layers.15.self_attn.q_proj.biases": "model.safetensors",
211
- "model.layers.15.self_attn.q_proj.scales": "model.safetensors",
212
  "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
213
  "model.layers.15.self_attn.v_proj.bias": "model.safetensors",
214
- "model.layers.15.self_attn.v_proj.biases": "model.safetensors",
215
- "model.layers.15.self_attn.v_proj.scales": "model.safetensors",
216
  "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
217
  "model.layers.16.input_layernorm.weight": "model.safetensors",
218
- "model.layers.16.mlp.down_proj.biases": "model.safetensors",
219
- "model.layers.16.mlp.down_proj.scales": "model.safetensors",
220
  "model.layers.16.mlp.down_proj.weight": "model.safetensors",
221
- "model.layers.16.mlp.gate_proj.biases": "model.safetensors",
222
- "model.layers.16.mlp.gate_proj.scales": "model.safetensors",
223
  "model.layers.16.mlp.gate_proj.weight": "model.safetensors",
224
- "model.layers.16.mlp.up_proj.biases": "model.safetensors",
225
- "model.layers.16.mlp.up_proj.scales": "model.safetensors",
226
  "model.layers.16.mlp.up_proj.weight": "model.safetensors",
227
  "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
228
  "model.layers.16.self_attn.k_proj.bias": "model.safetensors",
229
- "model.layers.16.self_attn.k_proj.biases": "model.safetensors",
230
- "model.layers.16.self_attn.k_proj.scales": "model.safetensors",
231
  "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
232
- "model.layers.16.self_attn.o_proj.biases": "model.safetensors",
233
- "model.layers.16.self_attn.o_proj.scales": "model.safetensors",
234
  "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
235
  "model.layers.16.self_attn.q_proj.bias": "model.safetensors",
236
- "model.layers.16.self_attn.q_proj.biases": "model.safetensors",
237
- "model.layers.16.self_attn.q_proj.scales": "model.safetensors",
238
  "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
239
  "model.layers.16.self_attn.v_proj.bias": "model.safetensors",
240
- "model.layers.16.self_attn.v_proj.biases": "model.safetensors",
241
- "model.layers.16.self_attn.v_proj.scales": "model.safetensors",
242
  "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
243
  "model.layers.17.input_layernorm.weight": "model.safetensors",
244
- "model.layers.17.mlp.down_proj.biases": "model.safetensors",
245
- "model.layers.17.mlp.down_proj.scales": "model.safetensors",
246
  "model.layers.17.mlp.down_proj.weight": "model.safetensors",
247
- "model.layers.17.mlp.gate_proj.biases": "model.safetensors",
248
- "model.layers.17.mlp.gate_proj.scales": "model.safetensors",
249
  "model.layers.17.mlp.gate_proj.weight": "model.safetensors",
250
- "model.layers.17.mlp.up_proj.biases": "model.safetensors",
251
- "model.layers.17.mlp.up_proj.scales": "model.safetensors",
252
  "model.layers.17.mlp.up_proj.weight": "model.safetensors",
253
  "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
254
  "model.layers.17.self_attn.k_proj.bias": "model.safetensors",
255
- "model.layers.17.self_attn.k_proj.biases": "model.safetensors",
256
- "model.layers.17.self_attn.k_proj.scales": "model.safetensors",
257
  "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
258
- "model.layers.17.self_attn.o_proj.biases": "model.safetensors",
259
- "model.layers.17.self_attn.o_proj.scales": "model.safetensors",
260
  "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
261
  "model.layers.17.self_attn.q_proj.bias": "model.safetensors",
262
- "model.layers.17.self_attn.q_proj.biases": "model.safetensors",
263
- "model.layers.17.self_attn.q_proj.scales": "model.safetensors",
264
  "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
265
  "model.layers.17.self_attn.v_proj.bias": "model.safetensors",
266
- "model.layers.17.self_attn.v_proj.biases": "model.safetensors",
267
- "model.layers.17.self_attn.v_proj.scales": "model.safetensors",
268
  "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
269
  "model.layers.18.input_layernorm.weight": "model.safetensors",
270
- "model.layers.18.mlp.down_proj.biases": "model.safetensors",
271
- "model.layers.18.mlp.down_proj.scales": "model.safetensors",
272
  "model.layers.18.mlp.down_proj.weight": "model.safetensors",
273
- "model.layers.18.mlp.gate_proj.biases": "model.safetensors",
274
- "model.layers.18.mlp.gate_proj.scales": "model.safetensors",
275
  "model.layers.18.mlp.gate_proj.weight": "model.safetensors",
276
- "model.layers.18.mlp.up_proj.biases": "model.safetensors",
277
- "model.layers.18.mlp.up_proj.scales": "model.safetensors",
278
  "model.layers.18.mlp.up_proj.weight": "model.safetensors",
279
  "model.layers.18.post_attention_layernorm.weight": "model.safetensors",
280
  "model.layers.18.self_attn.k_proj.bias": "model.safetensors",
281
- "model.layers.18.self_attn.k_proj.biases": "model.safetensors",
282
- "model.layers.18.self_attn.k_proj.scales": "model.safetensors",
283
  "model.layers.18.self_attn.k_proj.weight": "model.safetensors",
284
- "model.layers.18.self_attn.o_proj.biases": "model.safetensors",
285
- "model.layers.18.self_attn.o_proj.scales": "model.safetensors",
286
  "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
287
  "model.layers.18.self_attn.q_proj.bias": "model.safetensors",
288
- "model.layers.18.self_attn.q_proj.biases": "model.safetensors",
289
- "model.layers.18.self_attn.q_proj.scales": "model.safetensors",
290
  "model.layers.18.self_attn.q_proj.weight": "model.safetensors",
291
  "model.layers.18.self_attn.v_proj.bias": "model.safetensors",
292
- "model.layers.18.self_attn.v_proj.biases": "model.safetensors",
293
- "model.layers.18.self_attn.v_proj.scales": "model.safetensors",
294
  "model.layers.18.self_attn.v_proj.weight": "model.safetensors",
295
  "model.layers.19.input_layernorm.weight": "model.safetensors",
296
- "model.layers.19.mlp.down_proj.biases": "model.safetensors",
297
- "model.layers.19.mlp.down_proj.scales": "model.safetensors",
298
  "model.layers.19.mlp.down_proj.weight": "model.safetensors",
299
- "model.layers.19.mlp.gate_proj.biases": "model.safetensors",
300
- "model.layers.19.mlp.gate_proj.scales": "model.safetensors",
301
  "model.layers.19.mlp.gate_proj.weight": "model.safetensors",
302
- "model.layers.19.mlp.up_proj.biases": "model.safetensors",
303
- "model.layers.19.mlp.up_proj.scales": "model.safetensors",
304
  "model.layers.19.mlp.up_proj.weight": "model.safetensors",
305
  "model.layers.19.post_attention_layernorm.weight": "model.safetensors",
306
  "model.layers.19.self_attn.k_proj.bias": "model.safetensors",
307
- "model.layers.19.self_attn.k_proj.biases": "model.safetensors",
308
- "model.layers.19.self_attn.k_proj.scales": "model.safetensors",
309
  "model.layers.19.self_attn.k_proj.weight": "model.safetensors",
310
- "model.layers.19.self_attn.o_proj.biases": "model.safetensors",
311
- "model.layers.19.self_attn.o_proj.scales": "model.safetensors",
312
  "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
313
  "model.layers.19.self_attn.q_proj.bias": "model.safetensors",
314
- "model.layers.19.self_attn.q_proj.biases": "model.safetensors",
315
- "model.layers.19.self_attn.q_proj.scales": "model.safetensors",
316
  "model.layers.19.self_attn.q_proj.weight": "model.safetensors",
317
  "model.layers.19.self_attn.v_proj.bias": "model.safetensors",
318
- "model.layers.19.self_attn.v_proj.biases": "model.safetensors",
319
- "model.layers.19.self_attn.v_proj.scales": "model.safetensors",
320
  "model.layers.19.self_attn.v_proj.weight": "model.safetensors",
321
  "model.layers.2.input_layernorm.weight": "model.safetensors",
322
- "model.layers.2.mlp.down_proj.biases": "model.safetensors",
323
- "model.layers.2.mlp.down_proj.scales": "model.safetensors",
324
  "model.layers.2.mlp.down_proj.weight": "model.safetensors",
325
- "model.layers.2.mlp.gate_proj.biases": "model.safetensors",
326
- "model.layers.2.mlp.gate_proj.scales": "model.safetensors",
327
  "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
328
- "model.layers.2.mlp.up_proj.biases": "model.safetensors",
329
- "model.layers.2.mlp.up_proj.scales": "model.safetensors",
330
  "model.layers.2.mlp.up_proj.weight": "model.safetensors",
331
  "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
332
  "model.layers.2.self_attn.k_proj.bias": "model.safetensors",
333
- "model.layers.2.self_attn.k_proj.biases": "model.safetensors",
334
- "model.layers.2.self_attn.k_proj.scales": "model.safetensors",
335
  "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
336
- "model.layers.2.self_attn.o_proj.biases": "model.safetensors",
337
- "model.layers.2.self_attn.o_proj.scales": "model.safetensors",
338
  "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
339
  "model.layers.2.self_attn.q_proj.bias": "model.safetensors",
340
- "model.layers.2.self_attn.q_proj.biases": "model.safetensors",
341
- "model.layers.2.self_attn.q_proj.scales": "model.safetensors",
342
  "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
343
  "model.layers.2.self_attn.v_proj.bias": "model.safetensors",
344
- "model.layers.2.self_attn.v_proj.biases": "model.safetensors",
345
- "model.layers.2.self_attn.v_proj.scales": "model.safetensors",
346
  "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
347
  "model.layers.20.input_layernorm.weight": "model.safetensors",
348
- "model.layers.20.mlp.down_proj.biases": "model.safetensors",
349
- "model.layers.20.mlp.down_proj.scales": "model.safetensors",
350
  "model.layers.20.mlp.down_proj.weight": "model.safetensors",
351
- "model.layers.20.mlp.gate_proj.biases": "model.safetensors",
352
- "model.layers.20.mlp.gate_proj.scales": "model.safetensors",
353
  "model.layers.20.mlp.gate_proj.weight": "model.safetensors",
354
- "model.layers.20.mlp.up_proj.biases": "model.safetensors",
355
- "model.layers.20.mlp.up_proj.scales": "model.safetensors",
356
  "model.layers.20.mlp.up_proj.weight": "model.safetensors",
357
  "model.layers.20.post_attention_layernorm.weight": "model.safetensors",
358
  "model.layers.20.self_attn.k_proj.bias": "model.safetensors",
359
- "model.layers.20.self_attn.k_proj.biases": "model.safetensors",
360
- "model.layers.20.self_attn.k_proj.scales": "model.safetensors",
361
  "model.layers.20.self_attn.k_proj.weight": "model.safetensors",
362
- "model.layers.20.self_attn.o_proj.biases": "model.safetensors",
363
- "model.layers.20.self_attn.o_proj.scales": "model.safetensors",
364
  "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
365
  "model.layers.20.self_attn.q_proj.bias": "model.safetensors",
366
- "model.layers.20.self_attn.q_proj.biases": "model.safetensors",
367
- "model.layers.20.self_attn.q_proj.scales": "model.safetensors",
368
  "model.layers.20.self_attn.q_proj.weight": "model.safetensors",
369
  "model.layers.20.self_attn.v_proj.bias": "model.safetensors",
370
- "model.layers.20.self_attn.v_proj.biases": "model.safetensors",
371
- "model.layers.20.self_attn.v_proj.scales": "model.safetensors",
372
  "model.layers.20.self_attn.v_proj.weight": "model.safetensors",
373
  "model.layers.21.input_layernorm.weight": "model.safetensors",
374
- "model.layers.21.mlp.down_proj.biases": "model.safetensors",
375
- "model.layers.21.mlp.down_proj.scales": "model.safetensors",
376
  "model.layers.21.mlp.down_proj.weight": "model.safetensors",
377
- "model.layers.21.mlp.gate_proj.biases": "model.safetensors",
378
- "model.layers.21.mlp.gate_proj.scales": "model.safetensors",
379
  "model.layers.21.mlp.gate_proj.weight": "model.safetensors",
380
- "model.layers.21.mlp.up_proj.biases": "model.safetensors",
381
- "model.layers.21.mlp.up_proj.scales": "model.safetensors",
382
  "model.layers.21.mlp.up_proj.weight": "model.safetensors",
383
  "model.layers.21.post_attention_layernorm.weight": "model.safetensors",
384
  "model.layers.21.self_attn.k_proj.bias": "model.safetensors",
385
- "model.layers.21.self_attn.k_proj.biases": "model.safetensors",
386
- "model.layers.21.self_attn.k_proj.scales": "model.safetensors",
387
  "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
388
- "model.layers.21.self_attn.o_proj.biases": "model.safetensors",
389
- "model.layers.21.self_attn.o_proj.scales": "model.safetensors",
390
  "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
391
  "model.layers.21.self_attn.q_proj.bias": "model.safetensors",
392
- "model.layers.21.self_attn.q_proj.biases": "model.safetensors",
393
- "model.layers.21.self_attn.q_proj.scales": "model.safetensors",
394
  "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
395
  "model.layers.21.self_attn.v_proj.bias": "model.safetensors",
396
- "model.layers.21.self_attn.v_proj.biases": "model.safetensors",
397
- "model.layers.21.self_attn.v_proj.scales": "model.safetensors",
398
  "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
399
  "model.layers.22.input_layernorm.weight": "model.safetensors",
400
- "model.layers.22.mlp.down_proj.biases": "model.safetensors",
401
- "model.layers.22.mlp.down_proj.scales": "model.safetensors",
402
  "model.layers.22.mlp.down_proj.weight": "model.safetensors",
403
- "model.layers.22.mlp.gate_proj.biases": "model.safetensors",
404
- "model.layers.22.mlp.gate_proj.scales": "model.safetensors",
405
  "model.layers.22.mlp.gate_proj.weight": "model.safetensors",
406
- "model.layers.22.mlp.up_proj.biases": "model.safetensors",
407
- "model.layers.22.mlp.up_proj.scales": "model.safetensors",
408
  "model.layers.22.mlp.up_proj.weight": "model.safetensors",
409
  "model.layers.22.post_attention_layernorm.weight": "model.safetensors",
410
  "model.layers.22.self_attn.k_proj.bias": "model.safetensors",
411
- "model.layers.22.self_attn.k_proj.biases": "model.safetensors",
412
- "model.layers.22.self_attn.k_proj.scales": "model.safetensors",
413
  "model.layers.22.self_attn.k_proj.weight": "model.safetensors",
414
- "model.layers.22.self_attn.o_proj.biases": "model.safetensors",
415
- "model.layers.22.self_attn.o_proj.scales": "model.safetensors",
416
  "model.layers.22.self_attn.o_proj.weight": "model.safetensors",
417
  "model.layers.22.self_attn.q_proj.bias": "model.safetensors",
418
- "model.layers.22.self_attn.q_proj.biases": "model.safetensors",
419
- "model.layers.22.self_attn.q_proj.scales": "model.safetensors",
420
  "model.layers.22.self_attn.q_proj.weight": "model.safetensors",
421
  "model.layers.22.self_attn.v_proj.bias": "model.safetensors",
422
- "model.layers.22.self_attn.v_proj.biases": "model.safetensors",
423
- "model.layers.22.self_attn.v_proj.scales": "model.safetensors",
424
  "model.layers.22.self_attn.v_proj.weight": "model.safetensors",
425
  "model.layers.23.input_layernorm.weight": "model.safetensors",
426
- "model.layers.23.mlp.down_proj.biases": "model.safetensors",
427
- "model.layers.23.mlp.down_proj.scales": "model.safetensors",
428
  "model.layers.23.mlp.down_proj.weight": "model.safetensors",
429
- "model.layers.23.mlp.gate_proj.biases": "model.safetensors",
430
- "model.layers.23.mlp.gate_proj.scales": "model.safetensors",
431
  "model.layers.23.mlp.gate_proj.weight": "model.safetensors",
432
- "model.layers.23.mlp.up_proj.biases": "model.safetensors",
433
- "model.layers.23.mlp.up_proj.scales": "model.safetensors",
434
  "model.layers.23.mlp.up_proj.weight": "model.safetensors",
435
  "model.layers.23.post_attention_layernorm.weight": "model.safetensors",
436
  "model.layers.23.self_attn.k_proj.bias": "model.safetensors",
437
- "model.layers.23.self_attn.k_proj.biases": "model.safetensors",
438
- "model.layers.23.self_attn.k_proj.scales": "model.safetensors",
439
  "model.layers.23.self_attn.k_proj.weight": "model.safetensors",
440
- "model.layers.23.self_attn.o_proj.biases": "model.safetensors",
441
- "model.layers.23.self_attn.o_proj.scales": "model.safetensors",
442
  "model.layers.23.self_attn.o_proj.weight": "model.safetensors",
443
  "model.layers.23.self_attn.q_proj.bias": "model.safetensors",
444
- "model.layers.23.self_attn.q_proj.biases": "model.safetensors",
445
- "model.layers.23.self_attn.q_proj.scales": "model.safetensors",
446
  "model.layers.23.self_attn.q_proj.weight": "model.safetensors",
447
  "model.layers.23.self_attn.v_proj.bias": "model.safetensors",
448
- "model.layers.23.self_attn.v_proj.biases": "model.safetensors",
449
- "model.layers.23.self_attn.v_proj.scales": "model.safetensors",
450
  "model.layers.23.self_attn.v_proj.weight": "model.safetensors",
451
  "model.layers.3.input_layernorm.weight": "model.safetensors",
452
- "model.layers.3.mlp.down_proj.biases": "model.safetensors",
453
- "model.layers.3.mlp.down_proj.scales": "model.safetensors",
454
  "model.layers.3.mlp.down_proj.weight": "model.safetensors",
455
- "model.layers.3.mlp.gate_proj.biases": "model.safetensors",
456
- "model.layers.3.mlp.gate_proj.scales": "model.safetensors",
457
  "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
458
- "model.layers.3.mlp.up_proj.biases": "model.safetensors",
459
- "model.layers.3.mlp.up_proj.scales": "model.safetensors",
460
  "model.layers.3.mlp.up_proj.weight": "model.safetensors",
461
  "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
462
  "model.layers.3.self_attn.k_proj.bias": "model.safetensors",
463
- "model.layers.3.self_attn.k_proj.biases": "model.safetensors",
464
- "model.layers.3.self_attn.k_proj.scales": "model.safetensors",
465
  "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
466
- "model.layers.3.self_attn.o_proj.biases": "model.safetensors",
467
- "model.layers.3.self_attn.o_proj.scales": "model.safetensors",
468
  "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
469
  "model.layers.3.self_attn.q_proj.bias": "model.safetensors",
470
- "model.layers.3.self_attn.q_proj.biases": "model.safetensors",
471
- "model.layers.3.self_attn.q_proj.scales": "model.safetensors",
472
  "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
473
  "model.layers.3.self_attn.v_proj.bias": "model.safetensors",
474
- "model.layers.3.self_attn.v_proj.biases": "model.safetensors",
475
- "model.layers.3.self_attn.v_proj.scales": "model.safetensors",
476
  "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
477
  "model.layers.4.input_layernorm.weight": "model.safetensors",
478
- "model.layers.4.mlp.down_proj.biases": "model.safetensors",
479
- "model.layers.4.mlp.down_proj.scales": "model.safetensors",
480
  "model.layers.4.mlp.down_proj.weight": "model.safetensors",
481
- "model.layers.4.mlp.gate_proj.biases": "model.safetensors",
482
- "model.layers.4.mlp.gate_proj.scales": "model.safetensors",
483
  "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
484
- "model.layers.4.mlp.up_proj.biases": "model.safetensors",
485
- "model.layers.4.mlp.up_proj.scales": "model.safetensors",
486
  "model.layers.4.mlp.up_proj.weight": "model.safetensors",
487
  "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
488
  "model.layers.4.self_attn.k_proj.bias": "model.safetensors",
489
- "model.layers.4.self_attn.k_proj.biases": "model.safetensors",
490
- "model.layers.4.self_attn.k_proj.scales": "model.safetensors",
491
  "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
492
- "model.layers.4.self_attn.o_proj.biases": "model.safetensors",
493
- "model.layers.4.self_attn.o_proj.scales": "model.safetensors",
494
  "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
495
  "model.layers.4.self_attn.q_proj.bias": "model.safetensors",
496
- "model.layers.4.self_attn.q_proj.biases": "model.safetensors",
497
- "model.layers.4.self_attn.q_proj.scales": "model.safetensors",
498
  "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
499
  "model.layers.4.self_attn.v_proj.bias": "model.safetensors",
500
- "model.layers.4.self_attn.v_proj.biases": "model.safetensors",
501
- "model.layers.4.self_attn.v_proj.scales": "model.safetensors",
502
  "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
503
  "model.layers.5.input_layernorm.weight": "model.safetensors",
504
- "model.layers.5.mlp.down_proj.biases": "model.safetensors",
505
- "model.layers.5.mlp.down_proj.scales": "model.safetensors",
506
  "model.layers.5.mlp.down_proj.weight": "model.safetensors",
507
- "model.layers.5.mlp.gate_proj.biases": "model.safetensors",
508
- "model.layers.5.mlp.gate_proj.scales": "model.safetensors",
509
  "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
510
- "model.layers.5.mlp.up_proj.biases": "model.safetensors",
511
- "model.layers.5.mlp.up_proj.scales": "model.safetensors",
512
  "model.layers.5.mlp.up_proj.weight": "model.safetensors",
513
  "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
514
  "model.layers.5.self_attn.k_proj.bias": "model.safetensors",
515
- "model.layers.5.self_attn.k_proj.biases": "model.safetensors",
516
- "model.layers.5.self_attn.k_proj.scales": "model.safetensors",
517
  "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
518
- "model.layers.5.self_attn.o_proj.biases": "model.safetensors",
519
- "model.layers.5.self_attn.o_proj.scales": "model.safetensors",
520
  "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
521
  "model.layers.5.self_attn.q_proj.bias": "model.safetensors",
522
- "model.layers.5.self_attn.q_proj.biases": "model.safetensors",
523
- "model.layers.5.self_attn.q_proj.scales": "model.safetensors",
524
  "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
525
  "model.layers.5.self_attn.v_proj.bias": "model.safetensors",
526
- "model.layers.5.self_attn.v_proj.biases": "model.safetensors",
527
- "model.layers.5.self_attn.v_proj.scales": "model.safetensors",
528
  "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
529
  "model.layers.6.input_layernorm.weight": "model.safetensors",
530
- "model.layers.6.mlp.down_proj.biases": "model.safetensors",
531
- "model.layers.6.mlp.down_proj.scales": "model.safetensors",
532
  "model.layers.6.mlp.down_proj.weight": "model.safetensors",
533
- "model.layers.6.mlp.gate_proj.biases": "model.safetensors",
534
- "model.layers.6.mlp.gate_proj.scales": "model.safetensors",
535
  "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
536
- "model.layers.6.mlp.up_proj.biases": "model.safetensors",
537
- "model.layers.6.mlp.up_proj.scales": "model.safetensors",
538
  "model.layers.6.mlp.up_proj.weight": "model.safetensors",
539
  "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
540
  "model.layers.6.self_attn.k_proj.bias": "model.safetensors",
541
- "model.layers.6.self_attn.k_proj.biases": "model.safetensors",
542
- "model.layers.6.self_attn.k_proj.scales": "model.safetensors",
543
  "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
544
- "model.layers.6.self_attn.o_proj.biases": "model.safetensors",
545
- "model.layers.6.self_attn.o_proj.scales": "model.safetensors",
546
  "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
547
  "model.layers.6.self_attn.q_proj.bias": "model.safetensors",
548
- "model.layers.6.self_attn.q_proj.biases": "model.safetensors",
549
- "model.layers.6.self_attn.q_proj.scales": "model.safetensors",
550
  "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
551
  "model.layers.6.self_attn.v_proj.bias": "model.safetensors",
552
- "model.layers.6.self_attn.v_proj.biases": "model.safetensors",
553
- "model.layers.6.self_attn.v_proj.scales": "model.safetensors",
554
  "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
555
  "model.layers.7.input_layernorm.weight": "model.safetensors",
556
- "model.layers.7.mlp.down_proj.biases": "model.safetensors",
557
- "model.layers.7.mlp.down_proj.scales": "model.safetensors",
558
  "model.layers.7.mlp.down_proj.weight": "model.safetensors",
559
- "model.layers.7.mlp.gate_proj.biases": "model.safetensors",
560
- "model.layers.7.mlp.gate_proj.scales": "model.safetensors",
561
  "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
562
- "model.layers.7.mlp.up_proj.biases": "model.safetensors",
563
- "model.layers.7.mlp.up_proj.scales": "model.safetensors",
564
  "model.layers.7.mlp.up_proj.weight": "model.safetensors",
565
  "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
566
  "model.layers.7.self_attn.k_proj.bias": "model.safetensors",
567
- "model.layers.7.self_attn.k_proj.biases": "model.safetensors",
568
- "model.layers.7.self_attn.k_proj.scales": "model.safetensors",
569
  "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
570
- "model.layers.7.self_attn.o_proj.biases": "model.safetensors",
571
- "model.layers.7.self_attn.o_proj.scales": "model.safetensors",
572
  "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
573
  "model.layers.7.self_attn.q_proj.bias": "model.safetensors",
574
- "model.layers.7.self_attn.q_proj.biases": "model.safetensors",
575
- "model.layers.7.self_attn.q_proj.scales": "model.safetensors",
576
  "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
577
  "model.layers.7.self_attn.v_proj.bias": "model.safetensors",
578
- "model.layers.7.self_attn.v_proj.biases": "model.safetensors",
579
- "model.layers.7.self_attn.v_proj.scales": "model.safetensors",
580
  "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
581
  "model.layers.8.input_layernorm.weight": "model.safetensors",
582
- "model.layers.8.mlp.down_proj.biases": "model.safetensors",
583
- "model.layers.8.mlp.down_proj.scales": "model.safetensors",
584
  "model.layers.8.mlp.down_proj.weight": "model.safetensors",
585
- "model.layers.8.mlp.gate_proj.biases": "model.safetensors",
586
- "model.layers.8.mlp.gate_proj.scales": "model.safetensors",
587
  "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
588
- "model.layers.8.mlp.up_proj.biases": "model.safetensors",
589
- "model.layers.8.mlp.up_proj.scales": "model.safetensors",
590
  "model.layers.8.mlp.up_proj.weight": "model.safetensors",
591
  "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
592
  "model.layers.8.self_attn.k_proj.bias": "model.safetensors",
593
- "model.layers.8.self_attn.k_proj.biases": "model.safetensors",
594
- "model.layers.8.self_attn.k_proj.scales": "model.safetensors",
595
  "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
596
- "model.layers.8.self_attn.o_proj.biases": "model.safetensors",
597
- "model.layers.8.self_attn.o_proj.scales": "model.safetensors",
598
  "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
599
  "model.layers.8.self_attn.q_proj.bias": "model.safetensors",
600
- "model.layers.8.self_attn.q_proj.biases": "model.safetensors",
601
- "model.layers.8.self_attn.q_proj.scales": "model.safetensors",
602
  "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
603
  "model.layers.8.self_attn.v_proj.bias": "model.safetensors",
604
- "model.layers.8.self_attn.v_proj.biases": "model.safetensors",
605
- "model.layers.8.self_attn.v_proj.scales": "model.safetensors",
606
  "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
607
  "model.layers.9.input_layernorm.weight": "model.safetensors",
608
- "model.layers.9.mlp.down_proj.biases": "model.safetensors",
609
- "model.layers.9.mlp.down_proj.scales": "model.safetensors",
610
  "model.layers.9.mlp.down_proj.weight": "model.safetensors",
611
- "model.layers.9.mlp.gate_proj.biases": "model.safetensors",
612
- "model.layers.9.mlp.gate_proj.scales": "model.safetensors",
613
  "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
614
- "model.layers.9.mlp.up_proj.biases": "model.safetensors",
615
- "model.layers.9.mlp.up_proj.scales": "model.safetensors",
616
  "model.layers.9.mlp.up_proj.weight": "model.safetensors",
617
  "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
618
  "model.layers.9.self_attn.k_proj.bias": "model.safetensors",
619
- "model.layers.9.self_attn.k_proj.biases": "model.safetensors",
620
- "model.layers.9.self_attn.k_proj.scales": "model.safetensors",
621
  "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
622
- "model.layers.9.self_attn.o_proj.biases": "model.safetensors",
623
- "model.layers.9.self_attn.o_proj.scales": "model.safetensors",
624
  "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
625
  "model.layers.9.self_attn.q_proj.bias": "model.safetensors",
626
- "model.layers.9.self_attn.q_proj.biases": "model.safetensors",
627
- "model.layers.9.self_attn.q_proj.scales": "model.safetensors",
628
  "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
629
  "model.layers.9.self_attn.v_proj.bias": "model.safetensors",
630
- "model.layers.9.self_attn.v_proj.biases": "model.safetensors",
631
- "model.layers.9.self_attn.v_proj.scales": "model.safetensors",
632
  "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
633
  "model.norm.weight": "model.safetensors"
634
  }
 
1
  {
2
  "metadata": {
3
+ "total_size": 988065536
4
  },
5
  "weight_map": {
 
 
6
  "model.embed_tokens.weight": "model.safetensors",
7
  "model.layers.0.input_layernorm.weight": "model.safetensors",
 
 
8
  "model.layers.0.mlp.down_proj.weight": "model.safetensors",
 
 
9
  "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
 
 
10
  "model.layers.0.mlp.up_proj.weight": "model.safetensors",
11
  "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
12
  "model.layers.0.self_attn.k_proj.bias": "model.safetensors",
 
 
13
  "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
 
 
14
  "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
15
  "model.layers.0.self_attn.q_proj.bias": "model.safetensors",
 
 
16
  "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
17
  "model.layers.0.self_attn.v_proj.bias": "model.safetensors",
 
 
18
  "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
19
  "model.layers.1.input_layernorm.weight": "model.safetensors",
 
 
20
  "model.layers.1.mlp.down_proj.weight": "model.safetensors",
 
 
21
  "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
 
 
22
  "model.layers.1.mlp.up_proj.weight": "model.safetensors",
23
  "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
24
  "model.layers.1.self_attn.k_proj.bias": "model.safetensors",
 
 
25
  "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
 
 
26
  "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
27
  "model.layers.1.self_attn.q_proj.bias": "model.safetensors",
 
 
28
  "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
29
  "model.layers.1.self_attn.v_proj.bias": "model.safetensors",
 
 
30
  "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
31
  "model.layers.10.input_layernorm.weight": "model.safetensors",
 
 
32
  "model.layers.10.mlp.down_proj.weight": "model.safetensors",
 
 
33
  "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
 
 
34
  "model.layers.10.mlp.up_proj.weight": "model.safetensors",
35
  "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
36
  "model.layers.10.self_attn.k_proj.bias": "model.safetensors",
 
 
37
  "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
 
 
38
  "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
39
  "model.layers.10.self_attn.q_proj.bias": "model.safetensors",
 
 
40
  "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
41
  "model.layers.10.self_attn.v_proj.bias": "model.safetensors",
 
 
42
  "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
43
  "model.layers.11.input_layernorm.weight": "model.safetensors",
 
 
44
  "model.layers.11.mlp.down_proj.weight": "model.safetensors",
 
 
45
  "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
 
 
46
  "model.layers.11.mlp.up_proj.weight": "model.safetensors",
47
  "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
48
  "model.layers.11.self_attn.k_proj.bias": "model.safetensors",
 
 
49
  "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
 
 
50
  "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
51
  "model.layers.11.self_attn.q_proj.bias": "model.safetensors",
 
 
52
  "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
53
  "model.layers.11.self_attn.v_proj.bias": "model.safetensors",
 
 
54
  "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
55
  "model.layers.12.input_layernorm.weight": "model.safetensors",
 
 
56
  "model.layers.12.mlp.down_proj.weight": "model.safetensors",
 
 
57
  "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
 
 
58
  "model.layers.12.mlp.up_proj.weight": "model.safetensors",
59
  "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
60
  "model.layers.12.self_attn.k_proj.bias": "model.safetensors",
 
 
61
  "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
 
 
62
  "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
63
  "model.layers.12.self_attn.q_proj.bias": "model.safetensors",
 
 
64
  "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
65
  "model.layers.12.self_attn.v_proj.bias": "model.safetensors",
 
 
66
  "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
67
  "model.layers.13.input_layernorm.weight": "model.safetensors",
 
 
68
  "model.layers.13.mlp.down_proj.weight": "model.safetensors",
 
 
69
  "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
 
 
70
  "model.layers.13.mlp.up_proj.weight": "model.safetensors",
71
  "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
72
  "model.layers.13.self_attn.k_proj.bias": "model.safetensors",
 
 
73
  "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
 
 
74
  "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
75
  "model.layers.13.self_attn.q_proj.bias": "model.safetensors",
 
 
76
  "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
77
  "model.layers.13.self_attn.v_proj.bias": "model.safetensors",
 
 
78
  "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
79
  "model.layers.14.input_layernorm.weight": "model.safetensors",
 
 
80
  "model.layers.14.mlp.down_proj.weight": "model.safetensors",
 
 
81
  "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
 
 
82
  "model.layers.14.mlp.up_proj.weight": "model.safetensors",
83
  "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
84
  "model.layers.14.self_attn.k_proj.bias": "model.safetensors",
 
 
85
  "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
 
 
86
  "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
87
  "model.layers.14.self_attn.q_proj.bias": "model.safetensors",
 
 
88
  "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
89
  "model.layers.14.self_attn.v_proj.bias": "model.safetensors",
 
 
90
  "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
91
  "model.layers.15.input_layernorm.weight": "model.safetensors",
 
 
92
  "model.layers.15.mlp.down_proj.weight": "model.safetensors",
 
 
93
  "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
 
 
94
  "model.layers.15.mlp.up_proj.weight": "model.safetensors",
95
  "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
96
  "model.layers.15.self_attn.k_proj.bias": "model.safetensors",
 
 
97
  "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
 
 
98
  "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
99
  "model.layers.15.self_attn.q_proj.bias": "model.safetensors",
 
 
100
  "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
101
  "model.layers.15.self_attn.v_proj.bias": "model.safetensors",
 
 
102
  "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
103
  "model.layers.16.input_layernorm.weight": "model.safetensors",
 
 
104
  "model.layers.16.mlp.down_proj.weight": "model.safetensors",
 
 
105
  "model.layers.16.mlp.gate_proj.weight": "model.safetensors",
 
 
106
  "model.layers.16.mlp.up_proj.weight": "model.safetensors",
107
  "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
108
  "model.layers.16.self_attn.k_proj.bias": "model.safetensors",
 
 
109
  "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
 
 
110
  "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
111
  "model.layers.16.self_attn.q_proj.bias": "model.safetensors",
 
 
112
  "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
113
  "model.layers.16.self_attn.v_proj.bias": "model.safetensors",
 
 
114
  "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
115
  "model.layers.17.input_layernorm.weight": "model.safetensors",
 
 
116
  "model.layers.17.mlp.down_proj.weight": "model.safetensors",
 
 
117
  "model.layers.17.mlp.gate_proj.weight": "model.safetensors",
 
 
118
  "model.layers.17.mlp.up_proj.weight": "model.safetensors",
119
  "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
120
  "model.layers.17.self_attn.k_proj.bias": "model.safetensors",
 
 
121
  "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
 
 
122
  "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
123
  "model.layers.17.self_attn.q_proj.bias": "model.safetensors",
 
 
124
  "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
125
  "model.layers.17.self_attn.v_proj.bias": "model.safetensors",
 
 
126
  "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
127
  "model.layers.18.input_layernorm.weight": "model.safetensors",
 
 
128
  "model.layers.18.mlp.down_proj.weight": "model.safetensors",
 
 
129
  "model.layers.18.mlp.gate_proj.weight": "model.safetensors",
 
 
130
  "model.layers.18.mlp.up_proj.weight": "model.safetensors",
131
  "model.layers.18.post_attention_layernorm.weight": "model.safetensors",
132
  "model.layers.18.self_attn.k_proj.bias": "model.safetensors",
 
 
133
  "model.layers.18.self_attn.k_proj.weight": "model.safetensors",
 
 
134
  "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
135
  "model.layers.18.self_attn.q_proj.bias": "model.safetensors",
 
 
136
  "model.layers.18.self_attn.q_proj.weight": "model.safetensors",
137
  "model.layers.18.self_attn.v_proj.bias": "model.safetensors",
 
 
138
  "model.layers.18.self_attn.v_proj.weight": "model.safetensors",
139
  "model.layers.19.input_layernorm.weight": "model.safetensors",
 
 
140
  "model.layers.19.mlp.down_proj.weight": "model.safetensors",
 
 
141
  "model.layers.19.mlp.gate_proj.weight": "model.safetensors",
 
 
142
  "model.layers.19.mlp.up_proj.weight": "model.safetensors",
143
  "model.layers.19.post_attention_layernorm.weight": "model.safetensors",
144
  "model.layers.19.self_attn.k_proj.bias": "model.safetensors",
 
 
145
  "model.layers.19.self_attn.k_proj.weight": "model.safetensors",
 
 
146
  "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
147
  "model.layers.19.self_attn.q_proj.bias": "model.safetensors",
 
 
148
  "model.layers.19.self_attn.q_proj.weight": "model.safetensors",
149
  "model.layers.19.self_attn.v_proj.bias": "model.safetensors",
 
 
150
  "model.layers.19.self_attn.v_proj.weight": "model.safetensors",
151
  "model.layers.2.input_layernorm.weight": "model.safetensors",
 
 
152
  "model.layers.2.mlp.down_proj.weight": "model.safetensors",
 
 
153
  "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
 
 
154
  "model.layers.2.mlp.up_proj.weight": "model.safetensors",
155
  "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
156
  "model.layers.2.self_attn.k_proj.bias": "model.safetensors",
 
 
157
  "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
 
 
158
  "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
159
  "model.layers.2.self_attn.q_proj.bias": "model.safetensors",
 
 
160
  "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
161
  "model.layers.2.self_attn.v_proj.bias": "model.safetensors",
 
 
162
  "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
163
  "model.layers.20.input_layernorm.weight": "model.safetensors",
 
 
164
  "model.layers.20.mlp.down_proj.weight": "model.safetensors",
 
 
165
  "model.layers.20.mlp.gate_proj.weight": "model.safetensors",
 
 
166
  "model.layers.20.mlp.up_proj.weight": "model.safetensors",
167
  "model.layers.20.post_attention_layernorm.weight": "model.safetensors",
168
  "model.layers.20.self_attn.k_proj.bias": "model.safetensors",
 
 
169
  "model.layers.20.self_attn.k_proj.weight": "model.safetensors",
 
 
170
  "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
171
  "model.layers.20.self_attn.q_proj.bias": "model.safetensors",
 
 
172
  "model.layers.20.self_attn.q_proj.weight": "model.safetensors",
173
  "model.layers.20.self_attn.v_proj.bias": "model.safetensors",
 
 
174
  "model.layers.20.self_attn.v_proj.weight": "model.safetensors",
175
  "model.layers.21.input_layernorm.weight": "model.safetensors",
 
 
176
  "model.layers.21.mlp.down_proj.weight": "model.safetensors",
 
 
177
  "model.layers.21.mlp.gate_proj.weight": "model.safetensors",
 
 
178
  "model.layers.21.mlp.up_proj.weight": "model.safetensors",
179
  "model.layers.21.post_attention_layernorm.weight": "model.safetensors",
180
  "model.layers.21.self_attn.k_proj.bias": "model.safetensors",
 
 
181
  "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
 
 
182
  "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
183
  "model.layers.21.self_attn.q_proj.bias": "model.safetensors",
 
 
184
  "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
185
  "model.layers.21.self_attn.v_proj.bias": "model.safetensors",
 
 
186
  "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
187
  "model.layers.22.input_layernorm.weight": "model.safetensors",
 
 
188
  "model.layers.22.mlp.down_proj.weight": "model.safetensors",
 
 
189
  "model.layers.22.mlp.gate_proj.weight": "model.safetensors",
 
 
190
  "model.layers.22.mlp.up_proj.weight": "model.safetensors",
191
  "model.layers.22.post_attention_layernorm.weight": "model.safetensors",
192
  "model.layers.22.self_attn.k_proj.bias": "model.safetensors",
 
 
193
  "model.layers.22.self_attn.k_proj.weight": "model.safetensors",
 
 
194
  "model.layers.22.self_attn.o_proj.weight": "model.safetensors",
195
  "model.layers.22.self_attn.q_proj.bias": "model.safetensors",
 
 
196
  "model.layers.22.self_attn.q_proj.weight": "model.safetensors",
197
  "model.layers.22.self_attn.v_proj.bias": "model.safetensors",
 
 
198
  "model.layers.22.self_attn.v_proj.weight": "model.safetensors",
199
  "model.layers.23.input_layernorm.weight": "model.safetensors",
 
 
200
  "model.layers.23.mlp.down_proj.weight": "model.safetensors",
 
 
201
  "model.layers.23.mlp.gate_proj.weight": "model.safetensors",
 
 
202
  "model.layers.23.mlp.up_proj.weight": "model.safetensors",
203
  "model.layers.23.post_attention_layernorm.weight": "model.safetensors",
204
  "model.layers.23.self_attn.k_proj.bias": "model.safetensors",
 
 
205
  "model.layers.23.self_attn.k_proj.weight": "model.safetensors",
 
 
206
  "model.layers.23.self_attn.o_proj.weight": "model.safetensors",
207
  "model.layers.23.self_attn.q_proj.bias": "model.safetensors",
 
 
208
  "model.layers.23.self_attn.q_proj.weight": "model.safetensors",
209
  "model.layers.23.self_attn.v_proj.bias": "model.safetensors",
 
 
210
  "model.layers.23.self_attn.v_proj.weight": "model.safetensors",
211
  "model.layers.3.input_layernorm.weight": "model.safetensors",
 
 
212
  "model.layers.3.mlp.down_proj.weight": "model.safetensors",
 
 
213
  "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
 
 
214
  "model.layers.3.mlp.up_proj.weight": "model.safetensors",
215
  "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
216
  "model.layers.3.self_attn.k_proj.bias": "model.safetensors",
 
 
217
  "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
 
 
218
  "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
219
  "model.layers.3.self_attn.q_proj.bias": "model.safetensors",
 
 
220
  "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
221
  "model.layers.3.self_attn.v_proj.bias": "model.safetensors",
 
 
222
  "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
223
  "model.layers.4.input_layernorm.weight": "model.safetensors",
 
 
224
  "model.layers.4.mlp.down_proj.weight": "model.safetensors",
 
 
225
  "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
 
 
226
  "model.layers.4.mlp.up_proj.weight": "model.safetensors",
227
  "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
228
  "model.layers.4.self_attn.k_proj.bias": "model.safetensors",
 
 
229
  "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
 
 
230
  "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
231
  "model.layers.4.self_attn.q_proj.bias": "model.safetensors",
 
 
232
  "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
233
  "model.layers.4.self_attn.v_proj.bias": "model.safetensors",
 
 
234
  "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
235
  "model.layers.5.input_layernorm.weight": "model.safetensors",
 
 
236
  "model.layers.5.mlp.down_proj.weight": "model.safetensors",
 
 
237
  "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
 
 
238
  "model.layers.5.mlp.up_proj.weight": "model.safetensors",
239
  "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
240
  "model.layers.5.self_attn.k_proj.bias": "model.safetensors",
 
 
241
  "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
 
 
242
  "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
243
  "model.layers.5.self_attn.q_proj.bias": "model.safetensors",
 
 
244
  "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
245
  "model.layers.5.self_attn.v_proj.bias": "model.safetensors",
 
 
246
  "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
247
  "model.layers.6.input_layernorm.weight": "model.safetensors",
 
 
248
  "model.layers.6.mlp.down_proj.weight": "model.safetensors",
 
 
249
  "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
 
 
250
  "model.layers.6.mlp.up_proj.weight": "model.safetensors",
251
  "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
252
  "model.layers.6.self_attn.k_proj.bias": "model.safetensors",
 
 
253
  "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
 
 
254
  "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
255
  "model.layers.6.self_attn.q_proj.bias": "model.safetensors",
 
 
256
  "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
257
  "model.layers.6.self_attn.v_proj.bias": "model.safetensors",
 
 
258
  "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
259
  "model.layers.7.input_layernorm.weight": "model.safetensors",
 
 
260
  "model.layers.7.mlp.down_proj.weight": "model.safetensors",
 
 
261
  "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
 
 
262
  "model.layers.7.mlp.up_proj.weight": "model.safetensors",
263
  "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
264
  "model.layers.7.self_attn.k_proj.bias": "model.safetensors",
 
 
265
  "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
 
 
266
  "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
267
  "model.layers.7.self_attn.q_proj.bias": "model.safetensors",
 
 
268
  "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
269
  "model.layers.7.self_attn.v_proj.bias": "model.safetensors",
 
 
270
  "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
271
  "model.layers.8.input_layernorm.weight": "model.safetensors",
 
 
272
  "model.layers.8.mlp.down_proj.weight": "model.safetensors",
 
 
273
  "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
 
 
274
  "model.layers.8.mlp.up_proj.weight": "model.safetensors",
275
  "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
276
  "model.layers.8.self_attn.k_proj.bias": "model.safetensors",
 
 
277
  "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
 
 
278
  "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
279
  "model.layers.8.self_attn.q_proj.bias": "model.safetensors",
 
 
280
  "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
281
  "model.layers.8.self_attn.v_proj.bias": "model.safetensors",
 
 
282
  "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
283
  "model.layers.9.input_layernorm.weight": "model.safetensors",
 
 
284
  "model.layers.9.mlp.down_proj.weight": "model.safetensors",
 
 
285
  "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
 
 
286
  "model.layers.9.mlp.up_proj.weight": "model.safetensors",
287
  "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
288
  "model.layers.9.self_attn.k_proj.bias": "model.safetensors",
 
 
289
  "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
 
 
290
  "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
291
  "model.layers.9.self_attn.q_proj.bias": "model.safetensors",
 
 
292
  "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
293
  "model.layers.9.self_attn.v_proj.bias": "model.safetensors",
 
 
294
  "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
295
  "model.norm.weight": "model.safetensors"
296
  }