Hugging Face's logo

mlx-community
/
Qwen3-4B-Instruct-2507-DDWQ

Safetensors
qwen3
4-bit precision
Model card Files
xet
Community
N8Programs commited on
Commit
675822f
·
verified ·
1 Parent(s): fe8bdd2

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +28 -0
  3. config.json +1434 -0
  4. generation_config.json +13 -0
  5. merges.txt +0 -0
  6. model.safetensors +3 -0
  7. model.safetensors.index.json +912 -0
  8. special_tokens_map.json +31 -0
  9. tokenizer.json +3 -0
  10. tokenizer_config.json +240 -0
  11. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
config.json ADDED
@@ -0,0 +1,1434 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2560,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 9728,
14
+ "max_position_embeddings": 262144,
15
+ "max_window_layers": 36,
16
+ "model_type": "qwen3",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 36,
19
+ "num_key_value_heads": 8,
20
+ "quantization": {
21
+ "group_size": 64,
22
+ "bits": 4,
23
+ "model.embed_tokens": {
24
+ "bits": 6,
25
+ "group_size": 64
26
+ },
27
+ "model.layers.0.self_attn.q_proj": true,
28
+ "model.layers.0.self_attn.k_proj": {
29
+ "bits": 6,
30
+ "group_size": 64
31
+ },
32
+ "model.layers.0.self_attn.v_proj": {
33
+ "bits": 6,
34
+ "group_size": 64
35
+ },
36
+ "model.layers.0.self_attn.o_proj": {
37
+ "bits": 6,
38
+ "group_size": 64
39
+ },
40
+ "model.layers.0.self_attn.q_norm": false,
41
+ "model.layers.0.self_attn.k_norm": false,
42
+ "model.layers.0.self_attn.rope": false,
43
+ "model.layers.0.mlp.gate_proj": true,
44
+ "model.layers.0.mlp.down_proj": true,
45
+ "model.layers.0.mlp.up_proj": true,
46
+ "model.layers.0.input_layernorm": false,
47
+ "model.layers.0.post_attention_layernorm": false,
48
+ "model.layers.1.self_attn.q_proj": true,
49
+ "model.layers.1.self_attn.k_proj": true,
50
+ "model.layers.1.self_attn.v_proj": true,
51
+ "model.layers.1.self_attn.o_proj": true,
52
+ "model.layers.1.self_attn.q_norm": false,
53
+ "model.layers.1.self_attn.k_norm": false,
54
+ "model.layers.1.self_attn.rope": false,
55
+ "model.layers.1.mlp.gate_proj": {
56
+ "bits": 6,
57
+ "group_size": 64
58
+ },
59
+ "model.layers.1.mlp.down_proj": true,
60
+ "model.layers.1.mlp.up_proj": {
61
+ "bits": 6,
62
+ "group_size": 64
63
+ },
64
+ "model.layers.1.input_layernorm": false,
65
+ "model.layers.1.post_attention_layernorm": false,
66
+ "model.layers.2.self_attn.q_proj": true,
67
+ "model.layers.2.self_attn.k_proj": {
68
+ "bits": 6,
69
+ "group_size": 64
70
+ },
71
+ "model.layers.2.self_attn.v_proj": {
72
+ "bits": 6,
73
+ "group_size": 64
74
+ },
75
+ "model.layers.2.self_attn.o_proj": true,
76
+ "model.layers.2.self_attn.q_norm": false,
77
+ "model.layers.2.self_attn.k_norm": false,
78
+ "model.layers.2.self_attn.rope": false,
79
+ "model.layers.2.mlp.gate_proj": {
80
+ "bits": 6,
81
+ "group_size": 64
82
+ },
83
+ "model.layers.2.mlp.down_proj": true,
84
+ "model.layers.2.mlp.up_proj": {
85
+ "bits": 6,
86
+ "group_size": 64
87
+ },
88
+ "model.layers.2.input_layernorm": false,
89
+ "model.layers.2.post_attention_layernorm": false,
90
+ "model.layers.3.self_attn.q_proj": true,
91
+ "model.layers.3.self_attn.k_proj": true,
92
+ "model.layers.3.self_attn.v_proj": {
93
+ "bits": 6,
94
+ "group_size": 64
95
+ },
96
+ "model.layers.3.self_attn.o_proj": true,
97
+ "model.layers.3.self_attn.q_norm": false,
98
+ "model.layers.3.self_attn.k_norm": false,
99
+ "model.layers.3.self_attn.rope": false,
100
+ "model.layers.3.mlp.gate_proj": {
101
+ "bits": 6,
102
+ "group_size": 64
103
+ },
104
+ "model.layers.3.mlp.down_proj": true,
105
+ "model.layers.3.mlp.up_proj": true,
106
+ "model.layers.3.input_layernorm": false,
107
+ "model.layers.3.post_attention_layernorm": false,
108
+ "model.layers.4.self_attn.q_proj": true,
109
+ "model.layers.4.self_attn.k_proj": {
110
+ "bits": 6,
111
+ "group_size": 64
112
+ },
113
+ "model.layers.4.self_attn.v_proj": {
114
+ "bits": 6,
115
+ "group_size": 64
116
+ },
117
+ "model.layers.4.self_attn.o_proj": true,
118
+ "model.layers.4.self_attn.q_norm": false,
119
+ "model.layers.4.self_attn.k_norm": false,
120
+ "model.layers.4.self_attn.rope": false,
121
+ "model.layers.4.mlp.gate_proj": {
122
+ "bits": 6,
123
+ "group_size": 64
124
+ },
125
+ "model.layers.4.mlp.down_proj": true,
126
+ "model.layers.4.mlp.up_proj": {
127
+ "bits": 6,
128
+ "group_size": 64
129
+ },
130
+ "model.layers.4.input_layernorm": false,
131
+ "model.layers.4.post_attention_layernorm": false,
132
+ "model.layers.5.self_attn.q_proj": true,
133
+ "model.layers.5.self_attn.k_proj": true,
134
+ "model.layers.5.self_attn.v_proj": {
135
+ "bits": 6,
136
+ "group_size": 64
137
+ },
138
+ "model.layers.5.self_attn.o_proj": true,
139
+ "model.layers.5.self_attn.q_norm": false,
140
+ "model.layers.5.self_attn.k_norm": false,
141
+ "model.layers.5.self_attn.rope": false,
142
+ "model.layers.5.mlp.gate_proj": true,
143
+ "model.layers.5.mlp.down_proj": true,
144
+ "model.layers.5.mlp.up_proj": true,
145
+ "model.layers.5.input_layernorm": false,
146
+ "model.layers.5.post_attention_layernorm": false,
147
+ "model.layers.6.self_attn.q_proj": true,
148
+ "model.layers.6.self_attn.k_proj": true,
149
+ "model.layers.6.self_attn.v_proj": {
150
+ "bits": 6,
151
+ "group_size": 64
152
+ },
153
+ "model.layers.6.self_attn.o_proj": true,
154
+ "model.layers.6.self_attn.q_norm": false,
155
+ "model.layers.6.self_attn.k_norm": false,
156
+ "model.layers.6.self_attn.rope": false,
157
+ "model.layers.6.mlp.gate_proj": true,
158
+ "model.layers.6.mlp.down_proj": {
159
+ "bits": 6,
160
+ "group_size": 64
161
+ },
162
+ "model.layers.6.mlp.up_proj": true,
163
+ "model.layers.6.input_layernorm": false,
164
+ "model.layers.6.post_attention_layernorm": false,
165
+ "model.layers.7.self_attn.q_proj": true,
166
+ "model.layers.7.self_attn.k_proj": {
167
+ "bits": 6,
168
+ "group_size": 64
169
+ },
170
+ "model.layers.7.self_attn.v_proj": {
171
+ "bits": 6,
172
+ "group_size": 64
173
+ },
174
+ "model.layers.7.self_attn.o_proj": true,
175
+ "model.layers.7.self_attn.q_norm": false,
176
+ "model.layers.7.self_attn.k_norm": false,
177
+ "model.layers.7.self_attn.rope": false,
178
+ "model.layers.7.mlp.gate_proj": true,
179
+ "model.layers.7.mlp.down_proj": true,
180
+ "model.layers.7.mlp.up_proj": true,
181
+ "model.layers.7.input_layernorm": false,
182
+ "model.layers.7.post_attention_layernorm": false,
183
+ "model.layers.8.self_attn.q_proj": true,
184
+ "model.layers.8.self_attn.k_proj": {
185
+ "bits": 6,
186
+ "group_size": 64
187
+ },
188
+ "model.layers.8.self_attn.v_proj": {
189
+ "bits": 6,
190
+ "group_size": 64
191
+ },
192
+ "model.layers.8.self_attn.o_proj": true,
193
+ "model.layers.8.self_attn.q_norm": false,
194
+ "model.layers.8.self_attn.k_norm": false,
195
+ "model.layers.8.self_attn.rope": false,
196
+ "model.layers.8.mlp.gate_proj": true,
197
+ "model.layers.8.mlp.down_proj": true,
198
+ "model.layers.8.mlp.up_proj": true,
199
+ "model.layers.8.input_layernorm": false,
200
+ "model.layers.8.post_attention_layernorm": false,
201
+ "model.layers.9.self_attn.q_proj": true,
202
+ "model.layers.9.self_attn.k_proj": {
203
+ "bits": 6,
204
+ "group_size": 64
205
+ },
206
+ "model.layers.9.self_attn.v_proj": {
207
+ "bits": 6,
208
+ "group_size": 64
209
+ },
210
+ "model.layers.9.self_attn.o_proj": true,
211
+ "model.layers.9.self_attn.q_norm": false,
212
+ "model.layers.9.self_attn.k_norm": false,
213
+ "model.layers.9.self_attn.rope": false,
214
+ "model.layers.9.mlp.gate_proj": true,
215
+ "model.layers.9.mlp.down_proj": true,
216
+ "model.layers.9.mlp.up_proj": true,
217
+ "model.layers.9.input_layernorm": false,
218
+ "model.layers.9.post_attention_layernorm": false,
219
+ "model.layers.10.self_attn.q_proj": true,
220
+ "model.layers.10.self_attn.k_proj": {
221
+ "bits": 6,
222
+ "group_size": 64
223
+ },
224
+ "model.layers.10.self_attn.v_proj": {
225
+ "bits": 6,
226
+ "group_size": 64
227
+ },
228
+ "model.layers.10.self_attn.o_proj": true,
229
+ "model.layers.10.self_attn.q_norm": false,
230
+ "model.layers.10.self_attn.k_norm": false,
231
+ "model.layers.10.self_attn.rope": false,
232
+ "model.layers.10.mlp.gate_proj": true,
233
+ "model.layers.10.mlp.down_proj": true,
234
+ "model.layers.10.mlp.up_proj": true,
235
+ "model.layers.10.input_layernorm": false,
236
+ "model.layers.10.post_attention_layernorm": false,
237
+ "model.layers.11.self_attn.q_proj": true,
238
+ "model.layers.11.self_attn.k_proj": {
239
+ "bits": 6,
240
+ "group_size": 64
241
+ },
242
+ "model.layers.11.self_attn.v_proj": {
243
+ "bits": 6,
244
+ "group_size": 64
245
+ },
246
+ "model.layers.11.self_attn.o_proj": true,
247
+ "model.layers.11.self_attn.q_norm": false,
248
+ "model.layers.11.self_attn.k_norm": false,
249
+ "model.layers.11.self_attn.rope": false,
250
+ "model.layers.11.mlp.gate_proj": true,
251
+ "model.layers.11.mlp.down_proj": true,
252
+ "model.layers.11.mlp.up_proj": true,
253
+ "model.layers.11.input_layernorm": false,
254
+ "model.layers.11.post_attention_layernorm": false,
255
+ "model.layers.12.self_attn.q_proj": true,
256
+ "model.layers.12.self_attn.k_proj": {
257
+ "bits": 6,
258
+ "group_size": 64
259
+ },
260
+ "model.layers.12.self_attn.v_proj": {
261
+ "bits": 6,
262
+ "group_size": 64
263
+ },
264
+ "model.layers.12.self_attn.o_proj": true,
265
+ "model.layers.12.self_attn.q_norm": false,
266
+ "model.layers.12.self_attn.k_norm": false,
267
+ "model.layers.12.self_attn.rope": false,
268
+ "model.layers.12.mlp.gate_proj": true,
269
+ "model.layers.12.mlp.down_proj": true,
270
+ "model.layers.12.mlp.up_proj": true,
271
+ "model.layers.12.input_layernorm": false,
272
+ "model.layers.12.post_attention_layernorm": false,
273
+ "model.layers.13.self_attn.q_proj": true,
274
+ "model.layers.13.self_attn.k_proj": true,
275
+ "model.layers.13.self_attn.v_proj": true,
276
+ "model.layers.13.self_attn.o_proj": true,
277
+ "model.layers.13.self_attn.q_norm": false,
278
+ "model.layers.13.self_attn.k_norm": false,
279
+ "model.layers.13.self_attn.rope": false,
280
+ "model.layers.13.mlp.gate_proj": true,
281
+ "model.layers.13.mlp.down_proj": true,
282
+ "model.layers.13.mlp.up_proj": true,
283
+ "model.layers.13.input_layernorm": false,
284
+ "model.layers.13.post_attention_layernorm": false,
285
+ "model.layers.14.self_attn.q_proj": true,
286
+ "model.layers.14.self_attn.k_proj": true,
287
+ "model.layers.14.self_attn.v_proj": {
288
+ "bits": 6,
289
+ "group_size": 64
290
+ },
291
+ "model.layers.14.self_attn.o_proj": {
292
+ "bits": 6,
293
+ "group_size": 64
294
+ },
295
+ "model.layers.14.self_attn.q_norm": false,
296
+ "model.layers.14.self_attn.k_norm": false,
297
+ "model.layers.14.self_attn.rope": false,
298
+ "model.layers.14.mlp.gate_proj": true,
299
+ "model.layers.14.mlp.down_proj": true,
300
+ "model.layers.14.mlp.up_proj": true,
301
+ "model.layers.14.input_layernorm": false,
302
+ "model.layers.14.post_attention_layernorm": false,
303
+ "model.layers.15.self_attn.q_proj": true,
304
+ "model.layers.15.self_attn.k_proj": {
305
+ "bits": 6,
306
+ "group_size": 64
307
+ },
308
+ "model.layers.15.self_attn.v_proj": {
309
+ "bits": 6,
310
+ "group_size": 64
311
+ },
312
+ "model.layers.15.self_attn.o_proj": {
313
+ "bits": 6,
314
+ "group_size": 64
315
+ },
316
+ "model.layers.15.self_attn.q_norm": false,
317
+ "model.layers.15.self_attn.k_norm": false,
318
+ "model.layers.15.self_attn.rope": false,
319
+ "model.layers.15.mlp.gate_proj": true,
320
+ "model.layers.15.mlp.down_proj": true,
321
+ "model.layers.15.mlp.up_proj": true,
322
+ "model.layers.15.input_layernorm": false,
323
+ "model.layers.15.post_attention_layernorm": false,
324
+ "model.layers.16.self_attn.q_proj": true,
325
+ "model.layers.16.self_attn.k_proj": {
326
+ "bits": 6,
327
+ "group_size": 64
328
+ },
329
+ "model.layers.16.self_attn.v_proj": {
330
+ "bits": 6,
331
+ "group_size": 64
332
+ },
333
+ "model.layers.16.self_attn.o_proj": true,
334
+ "model.layers.16.self_attn.q_norm": false,
335
+ "model.layers.16.self_attn.k_norm": false,
336
+ "model.layers.16.self_attn.rope": false,
337
+ "model.layers.16.mlp.gate_proj": true,
338
+ "model.layers.16.mlp.down_proj": true,
339
+ "model.layers.16.mlp.up_proj": true,
340
+ "model.layers.16.input_layernorm": false,
341
+ "model.layers.16.post_attention_layernorm": false,
342
+ "model.layers.17.self_attn.q_proj": true,
343
+ "model.layers.17.self_attn.k_proj": {
344
+ "bits": 6,
345
+ "group_size": 64
346
+ },
347
+ "model.layers.17.self_attn.v_proj": {
348
+ "bits": 6,
349
+ "group_size": 64
350
+ },
351
+ "model.layers.17.self_attn.o_proj": {
352
+ "bits": 6,
353
+ "group_size": 64
354
+ },
355
+ "model.layers.17.self_attn.q_norm": false,
356
+ "model.layers.17.self_attn.k_norm": false,
357
+ "model.layers.17.self_attn.rope": false,
358
+ "model.layers.17.mlp.gate_proj": true,
359
+ "model.layers.17.mlp.down_proj": true,
360
+ "model.layers.17.mlp.up_proj": true,
361
+ "model.layers.17.input_layernorm": false,
362
+ "model.layers.17.post_attention_layernorm": false,
363
+ "model.layers.18.self_attn.q_proj": true,
364
+ "model.layers.18.self_attn.k_proj": {
365
+ "bits": 6,
366
+ "group_size": 64
367
+ },
368
+ "model.layers.18.self_attn.v_proj": {
369
+ "bits": 6,
370
+ "group_size": 64
371
+ },
372
+ "model.layers.18.self_attn.o_proj": {
373
+ "bits": 6,
374
+ "group_size": 64
375
+ },
376
+ "model.layers.18.self_attn.q_norm": false,
377
+ "model.layers.18.self_attn.k_norm": false,
378
+ "model.layers.18.self_attn.rope": false,
379
+ "model.layers.18.mlp.gate_proj": true,
380
+ "model.layers.18.mlp.down_proj": true,
381
+ "model.layers.18.mlp.up_proj": true,
382
+ "model.layers.18.input_layernorm": false,
383
+ "model.layers.18.post_attention_layernorm": false,
384
+ "model.layers.19.self_attn.q_proj": true,
385
+ "model.layers.19.self_attn.k_proj": {
386
+ "bits": 6,
387
+ "group_size": 64
388
+ },
389
+ "model.layers.19.self_attn.v_proj": {
390
+ "bits": 6,
391
+ "group_size": 64
392
+ },
393
+ "model.layers.19.self_attn.o_proj": {
394
+ "bits": 6,
395
+ "group_size": 64
396
+ },
397
+ "model.layers.19.self_attn.q_norm": false,
398
+ "model.layers.19.self_attn.k_norm": false,
399
+ "model.layers.19.self_attn.rope": false,
400
+ "model.layers.19.mlp.gate_proj": true,
401
+ "model.layers.19.mlp.down_proj": true,
402
+ "model.layers.19.mlp.up_proj": true,
403
+ "model.layers.19.input_layernorm": false,
404
+ "model.layers.19.post_attention_layernorm": false,
405
+ "model.layers.20.self_attn.q_proj": true,
406
+ "model.layers.20.self_attn.k_proj": {
407
+ "bits": 6,
408
+ "group_size": 64
409
+ },
410
+ "model.layers.20.self_attn.v_proj": {
411
+ "bits": 6,
412
+ "group_size": 64
413
+ },
414
+ "model.layers.20.self_attn.o_proj": true,
415
+ "model.layers.20.self_attn.q_norm": false,
416
+ "model.layers.20.self_attn.k_norm": false,
417
+ "model.layers.20.self_attn.rope": false,
418
+ "model.layers.20.mlp.gate_proj": true,
419
+ "model.layers.20.mlp.down_proj": true,
420
+ "model.layers.20.mlp.up_proj": true,
421
+ "model.layers.20.input_layernorm": false,
422
+ "model.layers.20.post_attention_layernorm": false,
423
+ "model.layers.21.self_attn.q_proj": true,
424
+ "model.layers.21.self_attn.k_proj": {
425
+ "bits": 6,
426
+ "group_size": 64
427
+ },
428
+ "model.layers.21.self_attn.v_proj": {
429
+ "bits": 6,
430
+ "group_size": 64
431
+ },
432
+ "model.layers.21.self_attn.o_proj": true,
433
+ "model.layers.21.self_attn.q_norm": false,
434
+ "model.layers.21.self_attn.k_norm": false,
435
+ "model.layers.21.self_attn.rope": false,
436
+ "model.layers.21.mlp.gate_proj": true,
437
+ "model.layers.21.mlp.down_proj": true,
438
+ "model.layers.21.mlp.up_proj": true,
439
+ "model.layers.21.input_layernorm": false,
440
+ "model.layers.21.post_attention_layernorm": false,
441
+ "model.layers.22.self_attn.q_proj": true,
442
+ "model.layers.22.self_attn.k_proj": {
443
+ "bits": 6,
444
+ "group_size": 64
445
+ },
446
+ "model.layers.22.self_attn.v_proj": {
447
+ "bits": 6,
448
+ "group_size": 64
449
+ },
450
+ "model.layers.22.self_attn.o_proj": {
451
+ "bits": 6,
452
+ "group_size": 64
453
+ },
454
+ "model.layers.22.self_attn.q_norm": false,
455
+ "model.layers.22.self_attn.k_norm": false,
456
+ "model.layers.22.self_attn.rope": false,
457
+ "model.layers.22.mlp.gate_proj": true,
458
+ "model.layers.22.mlp.down_proj": true,
459
+ "model.layers.22.mlp.up_proj": true,
460
+ "model.layers.22.input_layernorm": false,
461
+ "model.layers.22.post_attention_layernorm": false,
462
+ "model.layers.23.self_attn.q_proj": true,
463
+ "model.layers.23.self_attn.k_proj": {
464
+ "bits": 6,
465
+ "group_size": 64
466
+ },
467
+ "model.layers.23.self_attn.v_proj": {
468
+ "bits": 6,
469
+ "group_size": 64
470
+ },
471
+ "model.layers.23.self_attn.o_proj": {
472
+ "bits": 6,
473
+ "group_size": 64
474
+ },
475
+ "model.layers.23.self_attn.q_norm": false,
476
+ "model.layers.23.self_attn.k_norm": false,
477
+ "model.layers.23.self_attn.rope": false,
478
+ "model.layers.23.mlp.gate_proj": true,
479
+ "model.layers.23.mlp.down_proj": true,
480
+ "model.layers.23.mlp.up_proj": true,
481
+ "model.layers.23.input_layernorm": false,
482
+ "model.layers.23.post_attention_layernorm": false,
483
+ "model.layers.24.self_attn.q_proj": {
484
+ "bits": 6,
485
+ "group_size": 64
486
+ },
487
+ "model.layers.24.self_attn.k_proj": {
488
+ "bits": 6,
489
+ "group_size": 64
490
+ },
491
+ "model.layers.24.self_attn.v_proj": {
492
+ "bits": 6,
493
+ "group_size": 64
494
+ },
495
+ "model.layers.24.self_attn.o_proj": {
496
+ "bits": 6,
497
+ "group_size": 64
498
+ },
499
+ "model.layers.24.self_attn.q_norm": false,
500
+ "model.layers.24.self_attn.k_norm": false,
501
+ "model.layers.24.self_attn.rope": false,
502
+ "model.layers.24.mlp.gate_proj": true,
503
+ "model.layers.24.mlp.down_proj": true,
504
+ "model.layers.24.mlp.up_proj": true,
505
+ "model.layers.24.input_layernorm": false,
506
+ "model.layers.24.post_attention_layernorm": false,
507
+ "model.layers.25.self_attn.q_proj": true,
508
+ "model.layers.25.self_attn.k_proj": {
509
+ "bits": 6,
510
+ "group_size": 64
511
+ },
512
+ "model.layers.25.self_attn.v_proj": {
513
+ "bits": 6,
514
+ "group_size": 64
515
+ },
516
+ "model.layers.25.self_attn.o_proj": true,
517
+ "model.layers.25.self_attn.q_norm": false,
518
+ "model.layers.25.self_attn.k_norm": false,
519
+ "model.layers.25.self_attn.rope": false,
520
+ "model.layers.25.mlp.gate_proj": true,
521
+ "model.layers.25.mlp.down_proj": true,
522
+ "model.layers.25.mlp.up_proj": true,
523
+ "model.layers.25.input_layernorm": false,
524
+ "model.layers.25.post_attention_layernorm": false,
525
+ "model.layers.26.self_attn.q_proj": true,
526
+ "model.layers.26.self_attn.k_proj": {
527
+ "bits": 6,
528
+ "group_size": 64
529
+ },
530
+ "model.layers.26.self_attn.v_proj": {
531
+ "bits": 6,
532
+ "group_size": 64
533
+ },
534
+ "model.layers.26.self_attn.o_proj": true,
535
+ "model.layers.26.self_attn.q_norm": false,
536
+ "model.layers.26.self_attn.k_norm": false,
537
+ "model.layers.26.self_attn.rope": false,
538
+ "model.layers.26.mlp.gate_proj": true,
539
+ "model.layers.26.mlp.down_proj": true,
540
+ "model.layers.26.mlp.up_proj": true,
541
+ "model.layers.26.input_layernorm": false,
542
+ "model.layers.26.post_attention_layernorm": false,
543
+ "model.layers.27.self_attn.q_proj": true,
544
+ "model.layers.27.self_attn.k_proj": {
545
+ "bits": 6,
546
+ "group_size": 64
547
+ },
548
+ "model.layers.27.self_attn.v_proj": {
549
+ "bits": 6,
550
+ "group_size": 64
551
+ },
552
+ "model.layers.27.self_attn.o_proj": true,
553
+ "model.layers.27.self_attn.q_norm": false,
554
+ "model.layers.27.self_attn.k_norm": false,
555
+ "model.layers.27.self_attn.rope": false,
556
+ "model.layers.27.mlp.gate_proj": true,
557
+ "model.layers.27.mlp.down_proj": true,
558
+ "model.layers.27.mlp.up_proj": true,
559
+ "model.layers.27.input_layernorm": false,
560
+ "model.layers.27.post_attention_layernorm": false,
561
+ "model.layers.28.self_attn.q_proj": true,
562
+ "model.layers.28.self_attn.k_proj": {
563
+ "bits": 6,
564
+ "group_size": 64
565
+ },
566
+ "model.layers.28.self_attn.v_proj": {
567
+ "bits": 6,
568
+ "group_size": 64
569
+ },
570
+ "model.layers.28.self_attn.o_proj": true,
571
+ "model.layers.28.self_attn.q_norm": false,
572
+ "model.layers.28.self_attn.k_norm": false,
573
+ "model.layers.28.self_attn.rope": false,
574
+ "model.layers.28.mlp.gate_proj": true,
575
+ "model.layers.28.mlp.down_proj": true,
576
+ "model.layers.28.mlp.up_proj": true,
577
+ "model.layers.28.input_layernorm": false,
578
+ "model.layers.28.post_attention_layernorm": false,
579
+ "model.layers.29.self_attn.q_proj": true,
580
+ "model.layers.29.self_attn.k_proj": {
581
+ "bits": 6,
582
+ "group_size": 64
583
+ },
584
+ "model.layers.29.self_attn.v_proj": {
585
+ "bits": 6,
586
+ "group_size": 64
587
+ },
588
+ "model.layers.29.self_attn.o_proj": true,
589
+ "model.layers.29.self_attn.q_norm": false,
590
+ "model.layers.29.self_attn.k_norm": false,
591
+ "model.layers.29.self_attn.rope": false,
592
+ "model.layers.29.mlp.gate_proj": true,
593
+ "model.layers.29.mlp.down_proj": true,
594
+ "model.layers.29.mlp.up_proj": true,
595
+ "model.layers.29.input_layernorm": false,
596
+ "model.layers.29.post_attention_layernorm": false,
597
+ "model.layers.30.self_attn.q_proj": true,
598
+ "model.layers.30.self_attn.k_proj": {
599
+ "bits": 6,
600
+ "group_size": 64
601
+ },
602
+ "model.layers.30.self_attn.v_proj": true,
603
+ "model.layers.30.self_attn.o_proj": true,
604
+ "model.layers.30.self_attn.q_norm": false,
605
+ "model.layers.30.self_attn.k_norm": false,
606
+ "model.layers.30.self_attn.rope": false,
607
+ "model.layers.30.mlp.gate_proj": true,
608
+ "model.layers.30.mlp.down_proj": true,
609
+ "model.layers.30.mlp.up_proj": true,
610
+ "model.layers.30.input_layernorm": false,
611
+ "model.layers.30.post_attention_layernorm": false,
612
+ "model.layers.31.self_attn.q_proj": true,
613
+ "model.layers.31.self_attn.k_proj": {
614
+ "bits": 6,
615
+ "group_size": 64
616
+ },
617
+ "model.layers.31.self_attn.v_proj": {
618
+ "bits": 6,
619
+ "group_size": 64
620
+ },
621
+ "model.layers.31.self_attn.o_proj": true,
622
+ "model.layers.31.self_attn.q_norm": false,
623
+ "model.layers.31.self_attn.k_norm": false,
624
+ "model.layers.31.self_attn.rope": false,
625
+ "model.layers.31.mlp.gate_proj": true,
626
+ "model.layers.31.mlp.down_proj": true,
627
+ "model.layers.31.mlp.up_proj": true,
628
+ "model.layers.31.input_layernorm": false,
629
+ "model.layers.31.post_attention_layernorm": false,
630
+ "model.layers.32.self_attn.q_proj": {
631
+ "bits": 6,
632
+ "group_size": 64
633
+ },
634
+ "model.layers.32.self_attn.k_proj": {
635
+ "bits": 6,
636
+ "group_size": 64
637
+ },
638
+ "model.layers.32.self_attn.v_proj": {
639
+ "bits": 6,
640
+ "group_size": 64
641
+ },
642
+ "model.layers.32.self_attn.o_proj": true,
643
+ "model.layers.32.self_attn.q_norm": false,
644
+ "model.layers.32.self_attn.k_norm": false,
645
+ "model.layers.32.self_attn.rope": false,
646
+ "model.layers.32.mlp.gate_proj": true,
647
+ "model.layers.32.mlp.down_proj": true,
648
+ "model.layers.32.mlp.up_proj": true,
649
+ "model.layers.32.input_layernorm": false,
650
+ "model.layers.32.post_attention_layernorm": false,
651
+ "model.layers.33.self_attn.q_proj": true,
652
+ "model.layers.33.self_attn.k_proj": {
653
+ "bits": 6,
654
+ "group_size": 64
655
+ },
656
+ "model.layers.33.self_attn.v_proj": true,
657
+ "model.layers.33.self_attn.o_proj": true,
658
+ "model.layers.33.self_attn.q_norm": false,
659
+ "model.layers.33.self_attn.k_norm": false,
660
+ "model.layers.33.self_attn.rope": false,
661
+ "model.layers.33.mlp.gate_proj": true,
662
+ "model.layers.33.mlp.down_proj": true,
663
+ "model.layers.33.mlp.up_proj": true,
664
+ "model.layers.33.input_layernorm": false,
665
+ "model.layers.33.post_attention_layernorm": false,
666
+ "model.layers.34.self_attn.q_proj": {
667
+ "bits": 6,
668
+ "group_size": 64
669
+ },
670
+ "model.layers.34.self_attn.k_proj": {
671
+ "bits": 6,
672
+ "group_size": 64
673
+ },
674
+ "model.layers.34.self_attn.v_proj": {
675
+ "bits": 6,
676
+ "group_size": 64
677
+ },
678
+ "model.layers.34.self_attn.o_proj": true,
679
+ "model.layers.34.self_attn.q_norm": false,
680
+ "model.layers.34.self_attn.k_norm": false,
681
+ "model.layers.34.self_attn.rope": false,
682
+ "model.layers.34.mlp.gate_proj": {
683
+ "bits": 6,
684
+ "group_size": 64
685
+ },
686
+ "model.layers.34.mlp.down_proj": true,
687
+ "model.layers.34.mlp.up_proj": {
688
+ "bits": 6,
689
+ "group_size": 64
690
+ },
691
+ "model.layers.34.input_layernorm": false,
692
+ "model.layers.34.post_attention_layernorm": false,
693
+ "model.layers.35.self_attn.q_proj": true,
694
+ "model.layers.35.self_attn.k_proj": {
695
+ "bits": 6,
696
+ "group_size": 64
697
+ },
698
+ "model.layers.35.self_attn.v_proj": {
699
+ "bits": 6,
700
+ "group_size": 64
701
+ },
702
+ "model.layers.35.self_attn.o_proj": true,
703
+ "model.layers.35.self_attn.q_norm": false,
704
+ "model.layers.35.self_attn.k_norm": false,
705
+ "model.layers.35.self_attn.rope": false,
706
+ "model.layers.35.mlp.gate_proj": {
707
+ "bits": 6,
708
+ "group_size": 64
709
+ },
710
+ "model.layers.35.mlp.down_proj": {
711
+ "bits": 6,
712
+ "group_size": 64
713
+ },
714
+ "model.layers.35.mlp.up_proj": {
715
+ "bits": 6,
716
+ "group_size": 64
717
+ },
718
+ "model.layers.35.input_layernorm": false,
719
+ "model.layers.35.post_attention_layernorm": false,
720
+ "model.norm": false
721
+ },
722
+ "quantization_config": {
723
+ "group_size": 64,
724
+ "bits": 4,
725
+ "model.embed_tokens": {
726
+ "bits": 6,
727
+ "group_size": 64
728
+ },
729
+ "model.layers.0.self_attn.q_proj": true,
730
+ "model.layers.0.self_attn.k_proj": {
731
+ "bits": 6,
732
+ "group_size": 64
733
+ },
734
+ "model.layers.0.self_attn.v_proj": {
735
+ "bits": 6,
736
+ "group_size": 64
737
+ },
738
+ "model.layers.0.self_attn.o_proj": {
739
+ "bits": 6,
740
+ "group_size": 64
741
+ },
742
+ "model.layers.0.self_attn.q_norm": false,
743
+ "model.layers.0.self_attn.k_norm": false,
744
+ "model.layers.0.self_attn.rope": false,
745
+ "model.layers.0.mlp.gate_proj": true,
746
+ "model.layers.0.mlp.down_proj": true,
747
+ "model.layers.0.mlp.up_proj": true,
748
+ "model.layers.0.input_layernorm": false,
749
+ "model.layers.0.post_attention_layernorm": false,
750
+ "model.layers.1.self_attn.q_proj": true,
751
+ "model.layers.1.self_attn.k_proj": true,
752
+ "model.layers.1.self_attn.v_proj": true,
753
+ "model.layers.1.self_attn.o_proj": true,
754
+ "model.layers.1.self_attn.q_norm": false,
755
+ "model.layers.1.self_attn.k_norm": false,
756
+ "model.layers.1.self_attn.rope": false,
757
+ "model.layers.1.mlp.gate_proj": {
758
+ "bits": 6,
759
+ "group_size": 64
760
+ },
761
+ "model.layers.1.mlp.down_proj": true,
762
+ "model.layers.1.mlp.up_proj": {
763
+ "bits": 6,
764
+ "group_size": 64
765
+ },
766
+ "model.layers.1.input_layernorm": false,
767
+ "model.layers.1.post_attention_layernorm": false,
768
+ "model.layers.2.self_attn.q_proj": true,
769
+ "model.layers.2.self_attn.k_proj": {
770
+ "bits": 6,
771
+ "group_size": 64
772
+ },
773
+ "model.layers.2.self_attn.v_proj": {
774
+ "bits": 6,
775
+ "group_size": 64
776
+ },
777
+ "model.layers.2.self_attn.o_proj": true,
778
+ "model.layers.2.self_attn.q_norm": false,
779
+ "model.layers.2.self_attn.k_norm": false,
780
+ "model.layers.2.self_attn.rope": false,
781
+ "model.layers.2.mlp.gate_proj": {
782
+ "bits": 6,
783
+ "group_size": 64
784
+ },
785
+ "model.layers.2.mlp.down_proj": true,
786
+ "model.layers.2.mlp.up_proj": {
787
+ "bits": 6,
788
+ "group_size": 64
789
+ },
790
+ "model.layers.2.input_layernorm": false,
791
+ "model.layers.2.post_attention_layernorm": false,
792
+ "model.layers.3.self_attn.q_proj": true,
793
+ "model.layers.3.self_attn.k_proj": true,
794
+ "model.layers.3.self_attn.v_proj": {
795
+ "bits": 6,
796
+ "group_size": 64
797
+ },
798
+ "model.layers.3.self_attn.o_proj": true,
799
+ "model.layers.3.self_attn.q_norm": false,
800
+ "model.layers.3.self_attn.k_norm": false,
801
+ "model.layers.3.self_attn.rope": false,
802
+ "model.layers.3.mlp.gate_proj": {
803
+ "bits": 6,
804
+ "group_size": 64
805
+ },
806
+ "model.layers.3.mlp.down_proj": true,
807
+ "model.layers.3.mlp.up_proj": true,
808
+ "model.layers.3.input_layernorm": false,
809
+ "model.layers.3.post_attention_layernorm": false,
810
+ "model.layers.4.self_attn.q_proj": true,
811
+ "model.layers.4.self_attn.k_proj": {
812
+ "bits": 6,
813
+ "group_size": 64
814
+ },
815
+ "model.layers.4.self_attn.v_proj": {
816
+ "bits": 6,
817
+ "group_size": 64
818
+ },
819
+ "model.layers.4.self_attn.o_proj": true,
820
+ "model.layers.4.self_attn.q_norm": false,
821
+ "model.layers.4.self_attn.k_norm": false,
822
+ "model.layers.4.self_attn.rope": false,
823
+ "model.layers.4.mlp.gate_proj": {
824
+ "bits": 6,
825
+ "group_size": 64
826
+ },
827
+ "model.layers.4.mlp.down_proj": true,
828
+ "model.layers.4.mlp.up_proj": {
829
+ "bits": 6,
830
+ "group_size": 64
831
+ },
832
+ "model.layers.4.input_layernorm": false,
833
+ "model.layers.4.post_attention_layernorm": false,
834
+ "model.layers.5.self_attn.q_proj": true,
835
+ "model.layers.5.self_attn.k_proj": true,
836
+ "model.layers.5.self_attn.v_proj": {
837
+ "bits": 6,
838
+ "group_size": 64
839
+ },
840
+ "model.layers.5.self_attn.o_proj": true,
841
+ "model.layers.5.self_attn.q_norm": false,
842
+ "model.layers.5.self_attn.k_norm": false,
843
+ "model.layers.5.self_attn.rope": false,
844
+ "model.layers.5.mlp.gate_proj": true,
845
+ "model.layers.5.mlp.down_proj": true,
846
+ "model.layers.5.mlp.up_proj": true,
847
+ "model.layers.5.input_layernorm": false,
848
+ "model.layers.5.post_attention_layernorm": false,
849
+ "model.layers.6.self_attn.q_proj": true,
850
+ "model.layers.6.self_attn.k_proj": true,
851
+ "model.layers.6.self_attn.v_proj": {
852
+ "bits": 6,
853
+ "group_size": 64
854
+ },
855
+ "model.layers.6.self_attn.o_proj": true,
856
+ "model.layers.6.self_attn.q_norm": false,
857
+ "model.layers.6.self_attn.k_norm": false,
858
+ "model.layers.6.self_attn.rope": false,
859
+ "model.layers.6.mlp.gate_proj": true,
860
+ "model.layers.6.mlp.down_proj": {
861
+ "bits": 6,
862
+ "group_size": 64
863
+ },
864
+ "model.layers.6.mlp.up_proj": true,
865
+ "model.layers.6.input_layernorm": false,
866
+ "model.layers.6.post_attention_layernorm": false,
867
+ "model.layers.7.self_attn.q_proj": true,
868
+ "model.layers.7.self_attn.k_proj": {
869
+ "bits": 6,
870
+ "group_size": 64
871
+ },
872
+ "model.layers.7.self_attn.v_proj": {
873
+ "bits": 6,
874
+ "group_size": 64
875
+ },
876
+ "model.layers.7.self_attn.o_proj": true,
877
+ "model.layers.7.self_attn.q_norm": false,
878
+ "model.layers.7.self_attn.k_norm": false,
879
+ "model.layers.7.self_attn.rope": false,
880
+ "model.layers.7.mlp.gate_proj": true,
881
+ "model.layers.7.mlp.down_proj": true,
882
+ "model.layers.7.mlp.up_proj": true,
883
+ "model.layers.7.input_layernorm": false,
884
+ "model.layers.7.post_attention_layernorm": false,
885
+ "model.layers.8.self_attn.q_proj": true,
886
+ "model.layers.8.self_attn.k_proj": {
887
+ "bits": 6,
888
+ "group_size": 64
889
+ },
890
+ "model.layers.8.self_attn.v_proj": {
891
+ "bits": 6,
892
+ "group_size": 64
893
+ },
894
+ "model.layers.8.self_attn.o_proj": true,
895
+ "model.layers.8.self_attn.q_norm": false,
896
+ "model.layers.8.self_attn.k_norm": false,
897
+ "model.layers.8.self_attn.rope": false,
898
+ "model.layers.8.mlp.gate_proj": true,
899
+ "model.layers.8.mlp.down_proj": true,
900
+ "model.layers.8.mlp.up_proj": true,
901
+ "model.layers.8.input_layernorm": false,
902
+ "model.layers.8.post_attention_layernorm": false,
903
+ "model.layers.9.self_attn.q_proj": true,
904
+ "model.layers.9.self_attn.k_proj": {
905
+ "bits": 6,
906
+ "group_size": 64
907
+ },
908
+ "model.layers.9.self_attn.v_proj": {
909
+ "bits": 6,
910
+ "group_size": 64
911
+ },
912
+ "model.layers.9.self_attn.o_proj": true,
913
+ "model.layers.9.self_attn.q_norm": false,
914
+ "model.layers.9.self_attn.k_norm": false,
915
+ "model.layers.9.self_attn.rope": false,
916
+ "model.layers.9.mlp.gate_proj": true,
917
+ "model.layers.9.mlp.down_proj": true,
918
+ "model.layers.9.mlp.up_proj": true,
919
+ "model.layers.9.input_layernorm": false,
920
+ "model.layers.9.post_attention_layernorm": false,
921
+ "model.layers.10.self_attn.q_proj": true,
922
+ "model.layers.10.self_attn.k_proj": {
923
+ "bits": 6,
924
+ "group_size": 64
925
+ },
926
+ "model.layers.10.self_attn.v_proj": {
927
+ "bits": 6,
928
+ "group_size": 64
929
+ },
930
+ "model.layers.10.self_attn.o_proj": true,
931
+ "model.layers.10.self_attn.q_norm": false,
932
+ "model.layers.10.self_attn.k_norm": false,
933
+ "model.layers.10.self_attn.rope": false,
934
+ "model.layers.10.mlp.gate_proj": true,
935
+ "model.layers.10.mlp.down_proj": true,
936
+ "model.layers.10.mlp.up_proj": true,
937
+ "model.layers.10.input_layernorm": false,
938
+ "model.layers.10.post_attention_layernorm": false,
939
+ "model.layers.11.self_attn.q_proj": true,
940
+ "model.layers.11.self_attn.k_proj": {
941
+ "bits": 6,
942
+ "group_size": 64
943
+ },
944
+ "model.layers.11.self_attn.v_proj": {
945
+ "bits": 6,
946
+ "group_size": 64
947
+ },
948
+ "model.layers.11.self_attn.o_proj": true,
949
+ "model.layers.11.self_attn.q_norm": false,
950
+ "model.layers.11.self_attn.k_norm": false,
951
+ "model.layers.11.self_attn.rope": false,
952
+ "model.layers.11.mlp.gate_proj": true,
953
+ "model.layers.11.mlp.down_proj": true,
954
+ "model.layers.11.mlp.up_proj": true,
955
+ "model.layers.11.input_layernorm": false,
956
+ "model.layers.11.post_attention_layernorm": false,
957
+ "model.layers.12.self_attn.q_proj": true,
958
+ "model.layers.12.self_attn.k_proj": {
959
+ "bits": 6,
960
+ "group_size": 64
961
+ },
962
+ "model.layers.12.self_attn.v_proj": {
963
+ "bits": 6,
964
+ "group_size": 64
965
+ },
966
+ "model.layers.12.self_attn.o_proj": true,
967
+ "model.layers.12.self_attn.q_norm": false,
968
+ "model.layers.12.self_attn.k_norm": false,
969
+ "model.layers.12.self_attn.rope": false,
970
+ "model.layers.12.mlp.gate_proj": true,
971
+ "model.layers.12.mlp.down_proj": true,
972
+ "model.layers.12.mlp.up_proj": true,
973
+ "model.layers.12.input_layernorm": false,
974
+ "model.layers.12.post_attention_layernorm": false,
975
+ "model.layers.13.self_attn.q_proj": true,
976
+ "model.layers.13.self_attn.k_proj": true,
977
+ "model.layers.13.self_attn.v_proj": true,
978
+ "model.layers.13.self_attn.o_proj": true,
979
+ "model.layers.13.self_attn.q_norm": false,
980
+ "model.layers.13.self_attn.k_norm": false,
981
+ "model.layers.13.self_attn.rope": false,
982
+ "model.layers.13.mlp.gate_proj": true,
983
+ "model.layers.13.mlp.down_proj": true,
984
+ "model.layers.13.mlp.up_proj": true,
985
+ "model.layers.13.input_layernorm": false,
986
+ "model.layers.13.post_attention_layernorm": false,
987
+ "model.layers.14.self_attn.q_proj": true,
988
+ "model.layers.14.self_attn.k_proj": true,
989
+ "model.layers.14.self_attn.v_proj": {
990
+ "bits": 6,
991
+ "group_size": 64
992
+ },
993
+ "model.layers.14.self_attn.o_proj": {
994
+ "bits": 6,
995
+ "group_size": 64
996
+ },
997
+ "model.layers.14.self_attn.q_norm": false,
998
+ "model.layers.14.self_attn.k_norm": false,
999
+ "model.layers.14.self_attn.rope": false,
1000
+ "model.layers.14.mlp.gate_proj": true,
1001
+ "model.layers.14.mlp.down_proj": true,
1002
+ "model.layers.14.mlp.up_proj": true,
1003
+ "model.layers.14.input_layernorm": false,
1004
+ "model.layers.14.post_attention_layernorm": false,
1005
+ "model.layers.15.self_attn.q_proj": true,
1006
+ "model.layers.15.self_attn.k_proj": {
1007
+ "bits": 6,
1008
+ "group_size": 64
1009
+ },
1010
+ "model.layers.15.self_attn.v_proj": {
1011
+ "bits": 6,
1012
+ "group_size": 64
1013
+ },
1014
+ "model.layers.15.self_attn.o_proj": {
1015
+ "bits": 6,
1016
+ "group_size": 64
1017
+ },
1018
+ "model.layers.15.self_attn.q_norm": false,
1019
+ "model.layers.15.self_attn.k_norm": false,
1020
+ "model.layers.15.self_attn.rope": false,
1021
+ "model.layers.15.mlp.gate_proj": true,
1022
+ "model.layers.15.mlp.down_proj": true,
1023
+ "model.layers.15.mlp.up_proj": true,
1024
+ "model.layers.15.input_layernorm": false,
1025
+ "model.layers.15.post_attention_layernorm": false,
1026
+ "model.layers.16.self_attn.q_proj": true,
1027
+ "model.layers.16.self_attn.k_proj": {
1028
+ "bits": 6,
1029
+ "group_size": 64
1030
+ },
1031
+ "model.layers.16.self_attn.v_proj": {
1032
+ "bits": 6,
1033
+ "group_size": 64
1034
+ },
1035
+ "model.layers.16.self_attn.o_proj": true,
1036
+ "model.layers.16.self_attn.q_norm": false,
1037
+ "model.layers.16.self_attn.k_norm": false,
1038
+ "model.layers.16.self_attn.rope": false,
1039
+ "model.layers.16.mlp.gate_proj": true,
1040
+ "model.layers.16.mlp.down_proj": true,
1041
+ "model.layers.16.mlp.up_proj": true,
1042
+ "model.layers.16.input_layernorm": false,
1043
+ "model.layers.16.post_attention_layernorm": false,
1044
+ "model.layers.17.self_attn.q_proj": true,
1045
+ "model.layers.17.self_attn.k_proj": {
1046
+ "bits": 6,
1047
+ "group_size": 64
1048
+ },
1049
+ "model.layers.17.self_attn.v_proj": {
1050
+ "bits": 6,
1051
+ "group_size": 64
1052
+ },
1053
+ "model.layers.17.self_attn.o_proj": {
1054
+ "bits": 6,
1055
+ "group_size": 64
1056
+ },
1057
+ "model.layers.17.self_attn.q_norm": false,
1058
+ "model.layers.17.self_attn.k_norm": false,
1059
+ "model.layers.17.self_attn.rope": false,
1060
+ "model.layers.17.mlp.gate_proj": true,
1061
+ "model.layers.17.mlp.down_proj": true,
1062
+ "model.layers.17.mlp.up_proj": true,
1063
+ "model.layers.17.input_layernorm": false,
1064
+ "model.layers.17.post_attention_layernorm": false,
1065
+ "model.layers.18.self_attn.q_proj": true,
1066
+ "model.layers.18.self_attn.k_proj": {
1067
+ "bits": 6,
1068
+ "group_size": 64
1069
+ },
1070
+ "model.layers.18.self_attn.v_proj": {
1071
+ "bits": 6,
1072
+ "group_size": 64
1073
+ },
1074
+ "model.layers.18.self_attn.o_proj": {
1075
+ "bits": 6,
1076
+ "group_size": 64
1077
+ },
1078
+ "model.layers.18.self_attn.q_norm": false,
1079
+ "model.layers.18.self_attn.k_norm": false,
1080
+ "model.layers.18.self_attn.rope": false,
1081
+ "model.layers.18.mlp.gate_proj": true,
1082
+ "model.layers.18.mlp.down_proj": true,
1083
+ "model.layers.18.mlp.up_proj": true,
1084
+ "model.layers.18.input_layernorm": false,
1085
+ "model.layers.18.post_attention_layernorm": false,
1086
+ "model.layers.19.self_attn.q_proj": true,
1087
+ "model.layers.19.self_attn.k_proj": {
1088
+ "bits": 6,
1089
+ "group_size": 64
1090
+ },
1091
+ "model.layers.19.self_attn.v_proj": {
1092
+ "bits": 6,
1093
+ "group_size": 64
1094
+ },
1095
+ "model.layers.19.self_attn.o_proj": {
1096
+ "bits": 6,
1097
+ "group_size": 64
1098
+ },
1099
+ "model.layers.19.self_attn.q_norm": false,
1100
+ "model.layers.19.self_attn.k_norm": false,
1101
+ "model.layers.19.self_attn.rope": false,
1102
+ "model.layers.19.mlp.gate_proj": true,
1103
+ "model.layers.19.mlp.down_proj": true,
1104
+ "model.layers.19.mlp.up_proj": true,
1105
+ "model.layers.19.input_layernorm": false,
1106
+ "model.layers.19.post_attention_layernorm": false,
1107
+ "model.layers.20.self_attn.q_proj": true,
1108
+ "model.layers.20.self_attn.k_proj": {
1109
+ "bits": 6,
1110
+ "group_size": 64
1111
+ },
1112
+ "model.layers.20.self_attn.v_proj": {
1113
+ "bits": 6,
1114
+ "group_size": 64
1115
+ },
1116
+ "model.layers.20.self_attn.o_proj": true,
1117
+ "model.layers.20.self_attn.q_norm": false,
1118
+ "model.layers.20.self_attn.k_norm": false,
1119
+ "model.layers.20.self_attn.rope": false,
1120
+ "model.layers.20.mlp.gate_proj": true,
1121
+ "model.layers.20.mlp.down_proj": true,
1122
+ "model.layers.20.mlp.up_proj": true,
1123
+ "model.layers.20.input_layernorm": false,
1124
+ "model.layers.20.post_attention_layernorm": false,
1125
+ "model.layers.21.self_attn.q_proj": true,
1126
+ "model.layers.21.self_attn.k_proj": {
1127
+ "bits": 6,
1128
+ "group_size": 64
1129
+ },
1130
+ "model.layers.21.self_attn.v_proj": {
1131
+ "bits": 6,
1132
+ "group_size": 64
1133
+ },
1134
+ "model.layers.21.self_attn.o_proj": true,
1135
+ "model.layers.21.self_attn.q_norm": false,
1136
+ "model.layers.21.self_attn.k_norm": false,
1137
+ "model.layers.21.self_attn.rope": false,
1138
+ "model.layers.21.mlp.gate_proj": true,
1139
+ "model.layers.21.mlp.down_proj": true,
1140
+ "model.layers.21.mlp.up_proj": true,
1141
+ "model.layers.21.input_layernorm": false,
1142
+ "model.layers.21.post_attention_layernorm": false,
1143
+ "model.layers.22.self_attn.q_proj": true,
1144
+ "model.layers.22.self_attn.k_proj": {
1145
+ "bits": 6,
1146
+ "group_size": 64
1147
+ },
1148
+ "model.layers.22.self_attn.v_proj": {
1149
+ "bits": 6,
1150
+ "group_size": 64
1151
+ },
1152
+ "model.layers.22.self_attn.o_proj": {
1153
+ "bits": 6,
1154
+ "group_size": 64
1155
+ },
1156
+ "model.layers.22.self_attn.q_norm": false,
1157
+ "model.layers.22.self_attn.k_norm": false,
1158
+ "model.layers.22.self_attn.rope": false,
1159
+ "model.layers.22.mlp.gate_proj": true,
1160
+ "model.layers.22.mlp.down_proj": true,
1161
+ "model.layers.22.mlp.up_proj": true,
1162
+ "model.layers.22.input_layernorm": false,
1163
+ "model.layers.22.post_attention_layernorm": false,
1164
+ "model.layers.23.self_attn.q_proj": true,
1165
+ "model.layers.23.self_attn.k_proj": {
1166
+ "bits": 6,
1167
+ "group_size": 64
1168
+ },
1169
+ "model.layers.23.self_attn.v_proj": {
1170
+ "bits": 6,
1171
+ "group_size": 64
1172
+ },
1173
+ "model.layers.23.self_attn.o_proj": {
1174
+ "bits": 6,
1175
+ "group_size": 64
1176
+ },
1177
+ "model.layers.23.self_attn.q_norm": false,
1178
+ "model.layers.23.self_attn.k_norm": false,
1179
+ "model.layers.23.self_attn.rope": false,
1180
+ "model.layers.23.mlp.gate_proj": true,
1181
+ "model.layers.23.mlp.down_proj": true,
1182
+ "model.layers.23.mlp.up_proj": true,
1183
+ "model.layers.23.input_layernorm": false,
1184
+ "model.layers.23.post_attention_layernorm": false,
1185
+ "model.layers.24.self_attn.q_proj": {
1186
+ "bits": 6,
1187
+ "group_size": 64
1188
+ },
1189
+ "model.layers.24.self_attn.k_proj": {
1190
+ "bits": 6,
1191
+ "group_size": 64
1192
+ },
1193
+ "model.layers.24.self_attn.v_proj": {
1194
+ "bits": 6,
1195
+ "group_size": 64
1196
+ },
1197
+ "model.layers.24.self_attn.o_proj": {
1198
+ "bits": 6,
1199
+ "group_size": 64
1200
+ },
1201
+ "model.layers.24.self_attn.q_norm": false,
1202
+ "model.layers.24.self_attn.k_norm": false,
1203
+ "model.layers.24.self_attn.rope": false,
1204
+ "model.layers.24.mlp.gate_proj": true,
1205
+ "model.layers.24.mlp.down_proj": true,
1206
+ "model.layers.24.mlp.up_proj": true,
1207
+ "model.layers.24.input_layernorm": false,
1208
+ "model.layers.24.post_attention_layernorm": false,
1209
+ "model.layers.25.self_attn.q_proj": true,
1210
+ "model.layers.25.self_attn.k_proj": {
1211
+ "bits": 6,
1212
+ "group_size": 64
1213
+ },
1214
+ "model.layers.25.self_attn.v_proj": {
1215
+ "bits": 6,
1216
+ "group_size": 64
1217
+ },
1218
+ "model.layers.25.self_attn.o_proj": true,
1219
+ "model.layers.25.self_attn.q_norm": false,
1220
+ "model.layers.25.self_attn.k_norm": false,
1221
+ "model.layers.25.self_attn.rope": false,
1222
+ "model.layers.25.mlp.gate_proj": true,
1223
+ "model.layers.25.mlp.down_proj": true,
1224
+ "model.layers.25.mlp.up_proj": true,
1225
+ "model.layers.25.input_layernorm": false,
1226
+ "model.layers.25.post_attention_layernorm": false,
1227
+ "model.layers.26.self_attn.q_proj": true,
1228
+ "model.layers.26.self_attn.k_proj": {
1229
+ "bits": 6,
1230
+ "group_size": 64
1231
+ },
1232
+ "model.layers.26.self_attn.v_proj": {
1233
+ "bits": 6,
1234
+ "group_size": 64
1235
+ },
1236
+ "model.layers.26.self_attn.o_proj": true,
1237
+ "model.layers.26.self_attn.q_norm": false,
1238
+ "model.layers.26.self_attn.k_norm": false,
1239
+ "model.layers.26.self_attn.rope": false,
1240
+ "model.layers.26.mlp.gate_proj": true,
1241
+ "model.layers.26.mlp.down_proj": true,
1242
+ "model.layers.26.mlp.up_proj": true,
1243
+ "model.layers.26.input_layernorm": false,
1244
+ "model.layers.26.post_attention_layernorm": false,
1245
+ "model.layers.27.self_attn.q_proj": true,
1246
+ "model.layers.27.self_attn.k_proj": {
1247
+ "bits": 6,
1248
+ "group_size": 64
1249
+ },
1250
+ "model.layers.27.self_attn.v_proj": {
1251
+ "bits": 6,
1252
+ "group_size": 64
1253
+ },
1254
+ "model.layers.27.self_attn.o_proj": true,
1255
+ "model.layers.27.self_attn.q_norm": false,
1256
+ "model.layers.27.self_attn.k_norm": false,
1257
+ "model.layers.27.self_attn.rope": false,
1258
+ "model.layers.27.mlp.gate_proj": true,
1259
+ "model.layers.27.mlp.down_proj": true,
1260
+ "model.layers.27.mlp.up_proj": true,
1261
+ "model.layers.27.input_layernorm": false,
1262
+ "model.layers.27.post_attention_layernorm": false,
1263
+ "model.layers.28.self_attn.q_proj": true,
1264
+ "model.layers.28.self_attn.k_proj": {
1265
+ "bits": 6,
1266
+ "group_size": 64
1267
+ },
1268
+ "model.layers.28.self_attn.v_proj": {
1269
+ "bits": 6,
1270
+ "group_size": 64
1271
+ },
1272
+ "model.layers.28.self_attn.o_proj": true,
1273
+ "model.layers.28.self_attn.q_norm": false,
1274
+ "model.layers.28.self_attn.k_norm": false,
1275
+ "model.layers.28.self_attn.rope": false,
1276
+ "model.layers.28.mlp.gate_proj": true,
1277
+ "model.layers.28.mlp.down_proj": true,
1278
+ "model.layers.28.mlp.up_proj": true,
1279
+ "model.layers.28.input_layernorm": false,
1280
+ "model.layers.28.post_attention_layernorm": false,
1281
+ "model.layers.29.self_attn.q_proj": true,
1282
+ "model.layers.29.self_attn.k_proj": {
1283
+ "bits": 6,
1284
+ "group_size": 64
1285
+ },
1286
+ "model.layers.29.self_attn.v_proj": {
1287
+ "bits": 6,
1288
+ "group_size": 64
1289
+ },
1290
+ "model.layers.29.self_attn.o_proj": true,
1291
+ "model.layers.29.self_attn.q_norm": false,
1292
+ "model.layers.29.self_attn.k_norm": false,
1293
+ "model.layers.29.self_attn.rope": false,
1294
+ "model.layers.29.mlp.gate_proj": true,
1295
+ "model.layers.29.mlp.down_proj": true,
1296
+ "model.layers.29.mlp.up_proj": true,
1297
+ "model.layers.29.input_layernorm": false,
1298
+ "model.layers.29.post_attention_layernorm": false,
1299
+ "model.layers.30.self_attn.q_proj": true,
1300
+ "model.layers.30.self_attn.k_proj": {
1301
+ "bits": 6,
1302
+ "group_size": 64
1303
+ },
1304
+ "model.layers.30.self_attn.v_proj": true,
1305
+ "model.layers.30.self_attn.o_proj": true,
1306
+ "model.layers.30.self_attn.q_norm": false,
1307
+ "model.layers.30.self_attn.k_norm": false,
1308
+ "model.layers.30.self_attn.rope": false,
1309
+ "model.layers.30.mlp.gate_proj": true,
1310
+ "model.layers.30.mlp.down_proj": true,
1311
+ "model.layers.30.mlp.up_proj": true,
1312
+ "model.layers.30.input_layernorm": false,
1313
+ "model.layers.30.post_attention_layernorm": false,
1314
+ "model.layers.31.self_attn.q_proj": true,
1315
+ "model.layers.31.self_attn.k_proj": {
1316
+ "bits": 6,
1317
+ "group_size": 64
1318
+ },
1319
+ "model.layers.31.self_attn.v_proj": {
1320
+ "bits": 6,
1321
+ "group_size": 64
1322
+ },
1323
+ "model.layers.31.self_attn.o_proj": true,
1324
+ "model.layers.31.self_attn.q_norm": false,
1325
+ "model.layers.31.self_attn.k_norm": false,
1326
+ "model.layers.31.self_attn.rope": false,
1327
+ "model.layers.31.mlp.gate_proj": true,
1328
+ "model.layers.31.mlp.down_proj": true,
1329
+ "model.layers.31.mlp.up_proj": true,
1330
+ "model.layers.31.input_layernorm": false,
1331
+ "model.layers.31.post_attention_layernorm": false,
1332
+ "model.layers.32.self_attn.q_proj": {
1333
+ "bits": 6,
1334
+ "group_size": 64
1335
+ },
1336
+ "model.layers.32.self_attn.k_proj": {
1337
+ "bits": 6,
1338
+ "group_size": 64
1339
+ },
1340
+ "model.layers.32.self_attn.v_proj": {
1341
+ "bits": 6,
1342
+ "group_size": 64
1343
+ },
1344
+ "model.layers.32.self_attn.o_proj": true,
1345
+ "model.layers.32.self_attn.q_norm": false,
1346
+ "model.layers.32.self_attn.k_norm": false,
1347
+ "model.layers.32.self_attn.rope": false,
1348
+ "model.layers.32.mlp.gate_proj": true,
1349
+ "model.layers.32.mlp.down_proj": true,
1350
+ "model.layers.32.mlp.up_proj": true,
1351
+ "model.layers.32.input_layernorm": false,
1352
+ "model.layers.32.post_attention_layernorm": false,
1353
+ "model.layers.33.self_attn.q_proj": true,
1354
+ "model.layers.33.self_attn.k_proj": {
1355
+ "bits": 6,
1356
+ "group_size": 64
1357
+ },
1358
+ "model.layers.33.self_attn.v_proj": true,
1359
+ "model.layers.33.self_attn.o_proj": true,
1360
+ "model.layers.33.self_attn.q_norm": false,
1361
+ "model.layers.33.self_attn.k_norm": false,
1362
+ "model.layers.33.self_attn.rope": false,
1363
+ "model.layers.33.mlp.gate_proj": true,
1364
+ "model.layers.33.mlp.down_proj": true,
1365
+ "model.layers.33.mlp.up_proj": true,
1366
+ "model.layers.33.input_layernorm": false,
1367
+ "model.layers.33.post_attention_layernorm": false,
1368
+ "model.layers.34.self_attn.q_proj": {
1369
+ "bits": 6,
1370
+ "group_size": 64
1371
+ },
1372
+ "model.layers.34.self_attn.k_proj": {
1373
+ "bits": 6,
1374
+ "group_size": 64
1375
+ },
1376
+ "model.layers.34.self_attn.v_proj": {
1377
+ "bits": 6,
1378
+ "group_size": 64
1379
+ },
1380
+ "model.layers.34.self_attn.o_proj": true,
1381
+ "model.layers.34.self_attn.q_norm": false,
1382
+ "model.layers.34.self_attn.k_norm": false,
1383
+ "model.layers.34.self_attn.rope": false,
1384
+ "model.layers.34.mlp.gate_proj": {
1385
+ "bits": 6,
1386
+ "group_size": 64
1387
+ },
1388
+ "model.layers.34.mlp.down_proj": true,
1389
+ "model.layers.34.mlp.up_proj": {
1390
+ "bits": 6,
1391
+ "group_size": 64
1392
+ },
1393
+ "model.layers.34.input_layernorm": false,
1394
+ "model.layers.34.post_attention_layernorm": false,
1395
+ "model.layers.35.self_attn.q_proj": true,
1396
+ "model.layers.35.self_attn.k_proj": {
1397
+ "bits": 6,
1398
+ "group_size": 64
1399
+ },
1400
+ "model.layers.35.self_attn.v_proj": {
1401
+ "bits": 6,
1402
+ "group_size": 64
1403
+ },
1404
+ "model.layers.35.self_attn.o_proj": true,
1405
+ "model.layers.35.self_attn.q_norm": false,
1406
+ "model.layers.35.self_attn.k_norm": false,
1407
+ "model.layers.35.self_attn.rope": false,
1408
+ "model.layers.35.mlp.gate_proj": {
1409
+ "bits": 6,
1410
+ "group_size": 64
1411
+ },
1412
+ "model.layers.35.mlp.down_proj": {
1413
+ "bits": 6,
1414
+ "group_size": 64
1415
+ },
1416
+ "model.layers.35.mlp.up_proj": {
1417
+ "bits": 6,
1418
+ "group_size": 64
1419
+ },
1420
+ "model.layers.35.input_layernorm": false,
1421
+ "model.layers.35.post_attention_layernorm": false,
1422
+ "model.norm": false
1423
+ },
1424
+ "rms_norm_eps": 1e-06,
1425
+ "rope_scaling": null,
1426
+ "rope_theta": 5000000,
1427
+ "sliding_window": null,
1428
+ "tie_word_embeddings": true,
1429
+ "torch_dtype": "bfloat16",
1430
+ "transformers_version": "4.51.0",
1431
+ "use_cache": true,
1432
+ "use_sliding_window": false,
1433
+ "vocab_size": 151936
1434
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.7,
10
+ "top_k": 20,
11
+ "top_p": 0.8,
12
+ "transformers_version": "4.51.0"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93302f8b5d39da32ecc2b175472d5e31f6776ecfa813285833aa7470a24f3e5b
3
+ size 2513288145
model.safetensors.index.json ADDED
@@ -0,0 +1,912 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 2513185792,
4
+ "total_parameters": 4022468096
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.biases": "model.safetensors",
8
+ "model.embed_tokens.scales": "model.safetensors",
9
+ "model.embed_tokens.weight": "model.safetensors",
10
+ "model.layers.0.input_layernorm.weight": "model.safetensors",
11
+ "model.layers.0.mlp.down_proj.biases": "model.safetensors",
12
+ "model.layers.0.mlp.down_proj.scales": "model.safetensors",
13
+ "model.layers.0.mlp.down_proj.weight": "model.safetensors",
14
+ "model.layers.0.mlp.gate_proj.biases": "model.safetensors",
15
+ "model.layers.0.mlp.gate_proj.scales": "model.safetensors",
16
+ "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
17
+ "model.layers.0.mlp.up_proj.biases": "model.safetensors",
18
+ "model.layers.0.mlp.up_proj.scales": "model.safetensors",
19
+ "model.layers.0.mlp.up_proj.weight": "model.safetensors",
20
+ "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
21
+ "model.layers.0.self_attn.k_norm.weight": "model.safetensors",
22
+ "model.layers.0.self_attn.k_proj.biases": "model.safetensors",
23
+ "model.layers.0.self_attn.k_proj.scales": "model.safetensors",
24
+ "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
25
+ "model.layers.0.self_attn.o_proj.biases": "model.safetensors",
26
+ "model.layers.0.self_attn.o_proj.scales": "model.safetensors",
27
+ "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
28
+ "model.layers.0.self_attn.q_norm.weight": "model.safetensors",
29
+ "model.layers.0.self_attn.q_proj.biases": "model.safetensors",
30
+ "model.layers.0.self_attn.q_proj.scales": "model.safetensors",
31
+ "model.layers.0.self_attn.q_proj.weight": "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_norm.weight": "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_norm.weight": "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.biases": "model.safetensors",
58
+ "model.layers.1.self_attn.v_proj.scales": "model.safetensors",
59
+ "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
60
+ "model.layers.10.input_layernorm.weight": "model.safetensors",
61
+ "model.layers.10.mlp.down_proj.biases": "model.safetensors",
62
+ "model.layers.10.mlp.down_proj.scales": "model.safetensors",
63
+ "model.layers.10.mlp.down_proj.weight": "model.safetensors",
64
+ "model.layers.10.mlp.gate_proj.biases": "model.safetensors",
65
+ "model.layers.10.mlp.gate_proj.scales": "model.safetensors",
66
+ "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
67
+ "model.layers.10.mlp.up_proj.biases": "model.safetensors",
68
+ "model.layers.10.mlp.up_proj.scales": "model.safetensors",
69
+ "model.layers.10.mlp.up_proj.weight": "model.safetensors",
70
+ "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
71
+ "model.layers.10.self_attn.k_norm.weight": "model.safetensors",
72
+ "model.layers.10.self_attn.k_proj.biases": "model.safetensors",
73
+ "model.layers.10.self_attn.k_proj.scales": "model.safetensors",
74
+ "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
75
+ "model.layers.10.self_attn.o_proj.biases": "model.safetensors",
76
+ "model.layers.10.self_attn.o_proj.scales": "model.safetensors",
77
+ "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
78
+ "model.layers.10.self_attn.q_norm.weight": "model.safetensors",
79
+ "model.layers.10.self_attn.q_proj.biases": "model.safetensors",
80
+ "model.layers.10.self_attn.q_proj.scales": "model.safetensors",
81
+ "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
82
+ "model.layers.10.self_attn.v_proj.biases": "model.safetensors",
83
+ "model.layers.10.self_attn.v_proj.scales": "model.safetensors",
84
+ "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
85
+ "model.layers.11.input_layernorm.weight": "model.safetensors",
86
+ "model.layers.11.mlp.down_proj.biases": "model.safetensors",
87
+ "model.layers.11.mlp.down_proj.scales": "model.safetensors",
88
+ "model.layers.11.mlp.down_proj.weight": "model.safetensors",
89
+ "model.layers.11.mlp.gate_proj.biases": "model.safetensors",
90
+ "model.layers.11.mlp.gate_proj.scales": "model.safetensors",
91
+ "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
92
+ "model.layers.11.mlp.up_proj.biases": "model.safetensors",
93
+ "model.layers.11.mlp.up_proj.scales": "model.safetensors",
94
+ "model.layers.11.mlp.up_proj.weight": "model.safetensors",
95
+ "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
96
+ "model.layers.11.self_attn.k_norm.weight": "model.safetensors",
97
+ "model.layers.11.self_attn.k_proj.biases": "model.safetensors",
98
+ "model.layers.11.self_attn.k_proj.scales": "model.safetensors",
99
+ "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
100
+ "model.layers.11.self_attn.o_proj.biases": "model.safetensors",
101
+ "model.layers.11.self_attn.o_proj.scales": "model.safetensors",
102
+ "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
103
+ "model.layers.11.self_attn.q_norm.weight": "model.safetensors",
104
+ "model.layers.11.self_attn.q_proj.biases": "model.safetensors",
105
+ "model.layers.11.self_attn.q_proj.scales": "model.safetensors",
106
+ "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
107
+ "model.layers.11.self_attn.v_proj.biases": "model.safetensors",
108
+ "model.layers.11.self_attn.v_proj.scales": "model.safetensors",
109
+ "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
110
+ "model.layers.12.input_layernorm.weight": "model.safetensors",
111
+ "model.layers.12.mlp.down_proj.biases": "model.safetensors",
112
+ "model.layers.12.mlp.down_proj.scales": "model.safetensors",
113
+ "model.layers.12.mlp.down_proj.weight": "model.safetensors",
114
+ "model.layers.12.mlp.gate_proj.biases": "model.safetensors",
115
+ "model.layers.12.mlp.gate_proj.scales": "model.safetensors",
116
+ "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
117
+ "model.layers.12.mlp.up_proj.biases": "model.safetensors",
118
+ "model.layers.12.mlp.up_proj.scales": "model.safetensors",
119
+ "model.layers.12.mlp.up_proj.weight": "model.safetensors",
120
+ "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
121
+ "model.layers.12.self_attn.k_norm.weight": "model.safetensors",
122
+ "model.layers.12.self_attn.k_proj.biases": "model.safetensors",
123
+ "model.layers.12.self_attn.k_proj.scales": "model.safetensors",
124
+ "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
125
+ "model.layers.12.self_attn.o_proj.biases": "model.safetensors",
126
+ "model.layers.12.self_attn.o_proj.scales": "model.safetensors",
127
+ "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
128
+ "model.layers.12.self_attn.q_norm.weight": "model.safetensors",
129
+ "model.layers.12.self_attn.q_proj.biases": "model.safetensors",
130
+ "model.layers.12.self_attn.q_proj.scales": "model.safetensors",
131
+ "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
132
+ "model.layers.12.self_attn.v_proj.biases": "model.safetensors",
133
+ "model.layers.12.self_attn.v_proj.scales": "model.safetensors",
134
+ "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
135
+ "model.layers.13.input_layernorm.weight": "model.safetensors",
136
+ "model.layers.13.mlp.down_proj.biases": "model.safetensors",
137
+ "model.layers.13.mlp.down_proj.scales": "model.safetensors",
138
+ "model.layers.13.mlp.down_proj.weight": "model.safetensors",
139
+ "model.layers.13.mlp.gate_proj.biases": "model.safetensors",
140
+ "model.layers.13.mlp.gate_proj.scales": "model.safetensors",
141
+ "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
142
+ "model.layers.13.mlp.up_proj.biases": "model.safetensors",
143
+ "model.layers.13.mlp.up_proj.scales": "model.safetensors",
144
+ "model.layers.13.mlp.up_proj.weight": "model.safetensors",
145
+ "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
146
+ "model.layers.13.self_attn.k_norm.weight": "model.safetensors",
147
+ "model.layers.13.self_attn.k_proj.biases": "model.safetensors",
148
+ "model.layers.13.self_attn.k_proj.scales": "model.safetensors",
149
+ "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
150
+ "model.layers.13.self_attn.o_proj.biases": "model.safetensors",
151
+ "model.layers.13.self_attn.o_proj.scales": "model.safetensors",
152
+ "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
153
+ "model.layers.13.self_attn.q_norm.weight": "model.safetensors",
154
+ "model.layers.13.self_attn.q_proj.biases": "model.safetensors",
155
+ "model.layers.13.self_attn.q_proj.scales": "model.safetensors",
156
+ "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
157
+ "model.layers.13.self_attn.v_proj.biases": "model.safetensors",
158
+ "model.layers.13.self_attn.v_proj.scales": "model.safetensors",
159
+ "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
160
+ "model.layers.14.input_layernorm.weight": "model.safetensors",
161
+ "model.layers.14.mlp.down_proj.biases": "model.safetensors",
162
+ "model.layers.14.mlp.down_proj.scales": "model.safetensors",
163
+ "model.layers.14.mlp.down_proj.weight": "model.safetensors",
164
+ "model.layers.14.mlp.gate_proj.biases": "model.safetensors",
165
+ "model.layers.14.mlp.gate_proj.scales": "model.safetensors",
166
+ "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
167
+ "model.layers.14.mlp.up_proj.biases": "model.safetensors",
168
+ "model.layers.14.mlp.up_proj.scales": "model.safetensors",
169
+ "model.layers.14.mlp.up_proj.weight": "model.safetensors",
170
+ "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
171
+ "model.layers.14.self_attn.k_norm.weight": "model.safetensors",
172
+ "model.layers.14.self_attn.k_proj.biases": "model.safetensors",
173
+ "model.layers.14.self_attn.k_proj.scales": "model.safetensors",
174
+ "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
175
+ "model.layers.14.self_attn.o_proj.biases": "model.safetensors",
176
+ "model.layers.14.self_attn.o_proj.scales": "model.safetensors",
177
+ "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
178
+ "model.layers.14.self_attn.q_norm.weight": "model.safetensors",
179
+ "model.layers.14.self_attn.q_proj.biases": "model.safetensors",
180
+ "model.layers.14.self_attn.q_proj.scales": "model.safetensors",
181
+ "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
182
+ "model.layers.14.self_attn.v_proj.biases": "model.safetensors",
183
+ "model.layers.14.self_attn.v_proj.scales": "model.safetensors",
184
+ "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
185
+ "model.layers.15.input_layernorm.weight": "model.safetensors",
186
+ "model.layers.15.mlp.down_proj.biases": "model.safetensors",
187
+ "model.layers.15.mlp.down_proj.scales": "model.safetensors",
188
+ "model.layers.15.mlp.down_proj.weight": "model.safetensors",
189
+ "model.layers.15.mlp.gate_proj.biases": "model.safetensors",
190
+ "model.layers.15.mlp.gate_proj.scales": "model.safetensors",
191
+ "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
192
+ "model.layers.15.mlp.up_proj.biases": "model.safetensors",
193
+ "model.layers.15.mlp.up_proj.scales": "model.safetensors",
194
+ "model.layers.15.mlp.up_proj.weight": "model.safetensors",
195
+ "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
196
+ "model.layers.15.self_attn.k_norm.weight": "model.safetensors",
197
+ "model.layers.15.self_attn.k_proj.biases": "model.safetensors",
198
+ "model.layers.15.self_attn.k_proj.scales": "model.safetensors",
199
+ "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
200
+ "model.layers.15.self_attn.o_proj.biases": "model.safetensors",
201
+ "model.layers.15.self_attn.o_proj.scales": "model.safetensors",
202
+ "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
203
+ "model.layers.15.self_attn.q_norm.weight": "model.safetensors",
204
+ "model.layers.15.self_attn.q_proj.biases": "model.safetensors",
205
+ "model.layers.15.self_attn.q_proj.scales": "model.safetensors",
206
+ "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
207
+ "model.layers.15.self_attn.v_proj.biases": "model.safetensors",
208
+ "model.layers.15.self_attn.v_proj.scales": "model.safetensors",
209
+ "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
210
+ "model.layers.16.input_layernorm.weight": "model.safetensors",
211
+ "model.layers.16.mlp.down_proj.biases": "model.safetensors",
212
+ "model.layers.16.mlp.down_proj.scales": "model.safetensors",
213
+ "model.layers.16.mlp.down_proj.weight": "model.safetensors",
214
+ "model.layers.16.mlp.gate_proj.biases": "model.safetensors",
215
+ "model.layers.16.mlp.gate_proj.scales": "model.safetensors",
216
+ "model.layers.16.mlp.gate_proj.weight": "model.safetensors",
217
+ "model.layers.16.mlp.up_proj.biases": "model.safetensors",
218
+ "model.layers.16.mlp.up_proj.scales": "model.safetensors",
219
+ "model.layers.16.mlp.up_proj.weight": "model.safetensors",
220
+ "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
221
+ "model.layers.16.self_attn.k_norm.weight": "model.safetensors",
222
+ "model.layers.16.self_attn.k_proj.biases": "model.safetensors",
223
+ "model.layers.16.self_attn.k_proj.scales": "model.safetensors",
224
+ "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
225
+ "model.layers.16.self_attn.o_proj.biases": "model.safetensors",
226
+ "model.layers.16.self_attn.o_proj.scales": "model.safetensors",
227
+ "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
228
+ "model.layers.16.self_attn.q_norm.weight": "model.safetensors",
229
+ "model.layers.16.self_attn.q_proj.biases": "model.safetensors",
230
+ "model.layers.16.self_attn.q_proj.scales": "model.safetensors",
231
+ "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
232
+ "model.layers.16.self_attn.v_proj.biases": "model.safetensors",
233
+ "model.layers.16.self_attn.v_proj.scales": "model.safetensors",
234
+ "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
235
+ "model.layers.17.input_layernorm.weight": "model.safetensors",
236
+ "model.layers.17.mlp.down_proj.biases": "model.safetensors",
237
+ "model.layers.17.mlp.down_proj.scales": "model.safetensors",
238
+ "model.layers.17.mlp.down_proj.weight": "model.safetensors",
239
+ "model.layers.17.mlp.gate_proj.biases": "model.safetensors",
240
+ "model.layers.17.mlp.gate_proj.scales": "model.safetensors",
241
+ "model.layers.17.mlp.gate_proj.weight": "model.safetensors",
242
+ "model.layers.17.mlp.up_proj.biases": "model.safetensors",
243
+ "model.layers.17.mlp.up_proj.scales": "model.safetensors",
244
+ "model.layers.17.mlp.up_proj.weight": "model.safetensors",
245
+ "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
246
+ "model.layers.17.self_attn.k_norm.weight": "model.safetensors",
247
+ "model.layers.17.self_attn.k_proj.biases": "model.safetensors",
248
+ "model.layers.17.self_attn.k_proj.scales": "model.safetensors",
249
+ "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
250
+ "model.layers.17.self_attn.o_proj.biases": "model.safetensors",
251
+ "model.layers.17.self_attn.o_proj.scales": "model.safetensors",
252
+ "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
253
+ "model.layers.17.self_attn.q_norm.weight": "model.safetensors",
254
+ "model.layers.17.self_attn.q_proj.biases": "model.safetensors",
255
+ "model.layers.17.self_attn.q_proj.scales": "model.safetensors",
256
+ "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
257
+ "model.layers.17.self_attn.v_proj.biases": "model.safetensors",
258
+ "model.layers.17.self_attn.v_proj.scales": "model.safetensors",
259
+ "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
260
+ "model.layers.18.input_layernorm.weight": "model.safetensors",
261
+ "model.layers.18.mlp.down_proj.biases": "model.safetensors",
262
+ "model.layers.18.mlp.down_proj.scales": "model.safetensors",
263
+ "model.layers.18.mlp.down_proj.weight": "model.safetensors",
264
+ "model.layers.18.mlp.gate_proj.biases": "model.safetensors",
265
+ "model.layers.18.mlp.gate_proj.scales": "model.safetensors",
266
+ "model.layers.18.mlp.gate_proj.weight": "model.safetensors",
267
+ "model.layers.18.mlp.up_proj.biases": "model.safetensors",
268
+ "model.layers.18.mlp.up_proj.scales": "model.safetensors",
269
+ "model.layers.18.mlp.up_proj.weight": "model.safetensors",
270
+ "model.layers.18.post_attention_layernorm.weight": "model.safetensors",
271
+ "model.layers.18.self_attn.k_norm.weight": "model.safetensors",
272
+ "model.layers.18.self_attn.k_proj.biases": "model.safetensors",
273
+ "model.layers.18.self_attn.k_proj.scales": "model.safetensors",
274
+ "model.layers.18.self_attn.k_proj.weight": "model.safetensors",
275
+ "model.layers.18.self_attn.o_proj.biases": "model.safetensors",
276
+ "model.layers.18.self_attn.o_proj.scales": "model.safetensors",
277
+ "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
278
+ "model.layers.18.self_attn.q_norm.weight": "model.safetensors",
279
+ "model.layers.18.self_attn.q_proj.biases": "model.safetensors",
280
+ "model.layers.18.self_attn.q_proj.scales": "model.safetensors",
281
+ "model.layers.18.self_attn.q_proj.weight": "model.safetensors",
282
+ "model.layers.18.self_attn.v_proj.biases": "model.safetensors",
283
+ "model.layers.18.self_attn.v_proj.scales": "model.safetensors",
284
+ "model.layers.18.self_attn.v_proj.weight": "model.safetensors",
285
+ "model.layers.19.input_layernorm.weight": "model.safetensors",
286
+ "model.layers.19.mlp.down_proj.biases": "model.safetensors",
287
+ "model.layers.19.mlp.down_proj.scales": "model.safetensors",
288
+ "model.layers.19.mlp.down_proj.weight": "model.safetensors",
289
+ "model.layers.19.mlp.gate_proj.biases": "model.safetensors",
290
+ "model.layers.19.mlp.gate_proj.scales": "model.safetensors",
291
+ "model.layers.19.mlp.gate_proj.weight": "model.safetensors",
292
+ "model.layers.19.mlp.up_proj.biases": "model.safetensors",
293
+ "model.layers.19.mlp.up_proj.scales": "model.safetensors",
294
+ "model.layers.19.mlp.up_proj.weight": "model.safetensors",
295
+ "model.layers.19.post_attention_layernorm.weight": "model.safetensors",
296
+ "model.layers.19.self_attn.k_norm.weight": "model.safetensors",
297
+ "model.layers.19.self_attn.k_proj.biases": "model.safetensors",
298
+ "model.layers.19.self_attn.k_proj.scales": "model.safetensors",
299
+ "model.layers.19.self_attn.k_proj.weight": "model.safetensors",
300
+ "model.layers.19.self_attn.o_proj.biases": "model.safetensors",
301
+ "model.layers.19.self_attn.o_proj.scales": "model.safetensors",
302
+ "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
303
+ "model.layers.19.self_attn.q_norm.weight": "model.safetensors",
304
+ "model.layers.19.self_attn.q_proj.biases": "model.safetensors",
305
+ "model.layers.19.self_attn.q_proj.scales": "model.safetensors",
306
+ "model.layers.19.self_attn.q_proj.weight": "model.safetensors",
307
+ "model.layers.19.self_attn.v_proj.biases": "model.safetensors",
308
+ "model.layers.19.self_attn.v_proj.scales": "model.safetensors",
309
+ "model.layers.19.self_attn.v_proj.weight": "model.safetensors",
310
+ "model.layers.2.input_layernorm.weight": "model.safetensors",
311
+ "model.layers.2.mlp.down_proj.biases": "model.safetensors",
312
+ "model.layers.2.mlp.down_proj.scales": "model.safetensors",
313
+ "model.layers.2.mlp.down_proj.weight": "model.safetensors",
314
+ "model.layers.2.mlp.gate_proj.biases": "model.safetensors",
315
+ "model.layers.2.mlp.gate_proj.scales": "model.safetensors",
316
+ "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
317
+ "model.layers.2.mlp.up_proj.biases": "model.safetensors",
318
+ "model.layers.2.mlp.up_proj.scales": "model.safetensors",
319
+ "model.layers.2.mlp.up_proj.weight": "model.safetensors",
320
+ "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
321
+ "model.layers.2.self_attn.k_norm.weight": "model.safetensors",
322
+ "model.layers.2.self_attn.k_proj.biases": "model.safetensors",
323
+ "model.layers.2.self_attn.k_proj.scales": "model.safetensors",
324
+ "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
325
+ "model.layers.2.self_attn.o_proj.biases": "model.safetensors",
326
+ "model.layers.2.self_attn.o_proj.scales": "model.safetensors",
327
+ "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
328
+ "model.layers.2.self_attn.q_norm.weight": "model.safetensors",
329
+ "model.layers.2.self_attn.q_proj.biases": "model.safetensors",
330
+ "model.layers.2.self_attn.q_proj.scales": "model.safetensors",
331
+ "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
332
+ "model.layers.2.self_attn.v_proj.biases": "model.safetensors",
333
+ "model.layers.2.self_attn.v_proj.scales": "model.safetensors",
334
+ "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
335
+ "model.layers.20.input_layernorm.weight": "model.safetensors",
336
+ "model.layers.20.mlp.down_proj.biases": "model.safetensors",
337
+ "model.layers.20.mlp.down_proj.scales": "model.safetensors",
338
+ "model.layers.20.mlp.down_proj.weight": "model.safetensors",
339
+ "model.layers.20.mlp.gate_proj.biases": "model.safetensors",
340
+ "model.layers.20.mlp.gate_proj.scales": "model.safetensors",
341
+ "model.layers.20.mlp.gate_proj.weight": "model.safetensors",
342
+ "model.layers.20.mlp.up_proj.biases": "model.safetensors",
343
+ "model.layers.20.mlp.up_proj.scales": "model.safetensors",
344
+ "model.layers.20.mlp.up_proj.weight": "model.safetensors",
345
+ "model.layers.20.post_attention_layernorm.weight": "model.safetensors",
346
+ "model.layers.20.self_attn.k_norm.weight": "model.safetensors",
347
+ "model.layers.20.self_attn.k_proj.biases": "model.safetensors",
348
+ "model.layers.20.self_attn.k_proj.scales": "model.safetensors",
349
+ "model.layers.20.self_attn.k_proj.weight": "model.safetensors",
350
+ "model.layers.20.self_attn.o_proj.biases": "model.safetensors",
351
+ "model.layers.20.self_attn.o_proj.scales": "model.safetensors",
352
+ "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
353
+ "model.layers.20.self_attn.q_norm.weight": "model.safetensors",
354
+ "model.layers.20.self_attn.q_proj.biases": "model.safetensors",
355
+ "model.layers.20.self_attn.q_proj.scales": "model.safetensors",
356
+ "model.layers.20.self_attn.q_proj.weight": "model.safetensors",
357
+ "model.layers.20.self_attn.v_proj.biases": "model.safetensors",
358
+ "model.layers.20.self_attn.v_proj.scales": "model.safetensors",
359
+ "model.layers.20.self_attn.v_proj.weight": "model.safetensors",
360
+ "model.layers.21.input_layernorm.weight": "model.safetensors",
361
+ "model.layers.21.mlp.down_proj.biases": "model.safetensors",
362
+ "model.layers.21.mlp.down_proj.scales": "model.safetensors",
363
+ "model.layers.21.mlp.down_proj.weight": "model.safetensors",
364
+ "model.layers.21.mlp.gate_proj.biases": "model.safetensors",
365
+ "model.layers.21.mlp.gate_proj.scales": "model.safetensors",
366
+ "model.layers.21.mlp.gate_proj.weight": "model.safetensors",
367
+ "model.layers.21.mlp.up_proj.biases": "model.safetensors",
368
+ "model.layers.21.mlp.up_proj.scales": "model.safetensors",
369
+ "model.layers.21.mlp.up_proj.weight": "model.safetensors",
370
+ "model.layers.21.post_attention_layernorm.weight": "model.safetensors",
371
+ "model.layers.21.self_attn.k_norm.weight": "model.safetensors",
372
+ "model.layers.21.self_attn.k_proj.biases": "model.safetensors",
373
+ "model.layers.21.self_attn.k_proj.scales": "model.safetensors",
374
+ "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
375
+ "model.layers.21.self_attn.o_proj.biases": "model.safetensors",
376
+ "model.layers.21.self_attn.o_proj.scales": "model.safetensors",
377
+ "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
378
+ "model.layers.21.self_attn.q_norm.weight": "model.safetensors",
379
+ "model.layers.21.self_attn.q_proj.biases": "model.safetensors",
380
+ "model.layers.21.self_attn.q_proj.scales": "model.safetensors",
381
+ "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
382
+ "model.layers.21.self_attn.v_proj.biases": "model.safetensors",
383
+ "model.layers.21.self_attn.v_proj.scales": "model.safetensors",
384
+ "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
385
+ "model.layers.22.input_layernorm.weight": "model.safetensors",
386
+ "model.layers.22.mlp.down_proj.biases": "model.safetensors",
387
+ "model.layers.22.mlp.down_proj.scales": "model.safetensors",
388
+ "model.layers.22.mlp.down_proj.weight": "model.safetensors",
389
+ "model.layers.22.mlp.gate_proj.biases": "model.safetensors",
390
+ "model.layers.22.mlp.gate_proj.scales": "model.safetensors",
391
+ "model.layers.22.mlp.gate_proj.weight": "model.safetensors",
392
+ "model.layers.22.mlp.up_proj.biases": "model.safetensors",
393
+ "model.layers.22.mlp.up_proj.scales": "model.safetensors",
394
+ "model.layers.22.mlp.up_proj.weight": "model.safetensors",
395
+ "model.layers.22.post_attention_layernorm.weight": "model.safetensors",
396
+ "model.layers.22.self_attn.k_norm.weight": "model.safetensors",
397
+ "model.layers.22.self_attn.k_proj.biases": "model.safetensors",
398
+ "model.layers.22.self_attn.k_proj.scales": "model.safetensors",
399
+ "model.layers.22.self_attn.k_proj.weight": "model.safetensors",
400
+ "model.layers.22.self_attn.o_proj.biases": "model.safetensors",
401
+ "model.layers.22.self_attn.o_proj.scales": "model.safetensors",
402
+ "model.layers.22.self_attn.o_proj.weight": "model.safetensors",
403
+ "model.layers.22.self_attn.q_norm.weight": "model.safetensors",
404
+ "model.layers.22.self_attn.q_proj.biases": "model.safetensors",
405
+ "model.layers.22.self_attn.q_proj.scales": "model.safetensors",
406
+ "model.layers.22.self_attn.q_proj.weight": "model.safetensors",
407
+ "model.layers.22.self_attn.v_proj.biases": "model.safetensors",
408
+ "model.layers.22.self_attn.v_proj.scales": "model.safetensors",
409
+ "model.layers.22.self_attn.v_proj.weight": "model.safetensors",
410
+ "model.layers.23.input_layernorm.weight": "model.safetensors",
411
+ "model.layers.23.mlp.down_proj.biases": "model.safetensors",
412
+ "model.layers.23.mlp.down_proj.scales": "model.safetensors",
413
+ "model.layers.23.mlp.down_proj.weight": "model.safetensors",
414
+ "model.layers.23.mlp.gate_proj.biases": "model.safetensors",
415
+ "model.layers.23.mlp.gate_proj.scales": "model.safetensors",
416
+ "model.layers.23.mlp.gate_proj.weight": "model.safetensors",
417
+ "model.layers.23.mlp.up_proj.biases": "model.safetensors",
418
+ "model.layers.23.mlp.up_proj.scales": "model.safetensors",
419
+ "model.layers.23.mlp.up_proj.weight": "model.safetensors",
420
+ "model.layers.23.post_attention_layernorm.weight": "model.safetensors",
421
+ "model.layers.23.self_attn.k_norm.weight": "model.safetensors",
422
+ "model.layers.23.self_attn.k_proj.biases": "model.safetensors",
423
+ "model.layers.23.self_attn.k_proj.scales": "model.safetensors",
424
+ "model.layers.23.self_attn.k_proj.weight": "model.safetensors",
425
+ "model.layers.23.self_attn.o_proj.biases": "model.safetensors",
426
+ "model.layers.23.self_attn.o_proj.scales": "model.safetensors",
427
+ "model.layers.23.self_attn.o_proj.weight": "model.safetensors",
428
+ "model.layers.23.self_attn.q_norm.weight": "model.safetensors",
429
+ "model.layers.23.self_attn.q_proj.biases": "model.safetensors",
430
+ "model.layers.23.self_attn.q_proj.scales": "model.safetensors",
431
+ "model.layers.23.self_attn.q_proj.weight": "model.safetensors",
432
+ "model.layers.23.self_attn.v_proj.biases": "model.safetensors",
433
+ "model.layers.23.self_attn.v_proj.scales": "model.safetensors",
434
+ "model.layers.23.self_attn.v_proj.weight": "model.safetensors",
435
+ "model.layers.24.input_layernorm.weight": "model.safetensors",
436
+ "model.layers.24.mlp.down_proj.biases": "model.safetensors",
437
+ "model.layers.24.mlp.down_proj.scales": "model.safetensors",
438
+ "model.layers.24.mlp.down_proj.weight": "model.safetensors",
439
+ "model.layers.24.mlp.gate_proj.biases": "model.safetensors",
440
+ "model.layers.24.mlp.gate_proj.scales": "model.safetensors",
441
+ "model.layers.24.mlp.gate_proj.weight": "model.safetensors",
442
+ "model.layers.24.mlp.up_proj.biases": "model.safetensors",
443
+ "model.layers.24.mlp.up_proj.scales": "model.safetensors",
444
+ "model.layers.24.mlp.up_proj.weight": "model.safetensors",
445
+ "model.layers.24.post_attention_layernorm.weight": "model.safetensors",
446
+ "model.layers.24.self_attn.k_norm.weight": "model.safetensors",
447
+ "model.layers.24.self_attn.k_proj.biases": "model.safetensors",
448
+ "model.layers.24.self_attn.k_proj.scales": "model.safetensors",
449
+ "model.layers.24.self_attn.k_proj.weight": "model.safetensors",
450
+ "model.layers.24.self_attn.o_proj.biases": "model.safetensors",
451
+ "model.layers.24.self_attn.o_proj.scales": "model.safetensors",
452
+ "model.layers.24.self_attn.o_proj.weight": "model.safetensors",
453
+ "model.layers.24.self_attn.q_norm.weight": "model.safetensors",
454
+ "model.layers.24.self_attn.q_proj.biases": "model.safetensors",
455
+ "model.layers.24.self_attn.q_proj.scales": "model.safetensors",
456
+ "model.layers.24.self_attn.q_proj.weight": "model.safetensors",
457
+ "model.layers.24.self_attn.v_proj.biases": "model.safetensors",
458
+ "model.layers.24.self_attn.v_proj.scales": "model.safetensors",
459
+ "model.layers.24.self_attn.v_proj.weight": "model.safetensors",
460
+ "model.layers.25.input_layernorm.weight": "model.safetensors",
461
+ "model.layers.25.mlp.down_proj.biases": "model.safetensors",
462
+ "model.layers.25.mlp.down_proj.scales": "model.safetensors",
463
+ "model.layers.25.mlp.down_proj.weight": "model.safetensors",
464
+ "model.layers.25.mlp.gate_proj.biases": "model.safetensors",
465
+ "model.layers.25.mlp.gate_proj.scales": "model.safetensors",
466
+ "model.layers.25.mlp.gate_proj.weight": "model.safetensors",
467
+ "model.layers.25.mlp.up_proj.biases": "model.safetensors",
468
+ "model.layers.25.mlp.up_proj.scales": "model.safetensors",
469
+ "model.layers.25.mlp.up_proj.weight": "model.safetensors",
470
+ "model.layers.25.post_attention_layernorm.weight": "model.safetensors",
471
+ "model.layers.25.self_attn.k_norm.weight": "model.safetensors",
472
+ "model.layers.25.self_attn.k_proj.biases": "model.safetensors",
473
+ "model.layers.25.self_attn.k_proj.scales": "model.safetensors",
474
+ "model.layers.25.self_attn.k_proj.weight": "model.safetensors",
475
+ "model.layers.25.self_attn.o_proj.biases": "model.safetensors",
476
+ "model.layers.25.self_attn.o_proj.scales": "model.safetensors",
477
+ "model.layers.25.self_attn.o_proj.weight": "model.safetensors",
478
+ "model.layers.25.self_attn.q_norm.weight": "model.safetensors",
479
+ "model.layers.25.self_attn.q_proj.biases": "model.safetensors",
480
+ "model.layers.25.self_attn.q_proj.scales": "model.safetensors",
481
+ "model.layers.25.self_attn.q_proj.weight": "model.safetensors",
482
+ "model.layers.25.self_attn.v_proj.biases": "model.safetensors",
483
+ "model.layers.25.self_attn.v_proj.scales": "model.safetensors",
484
+ "model.layers.25.self_attn.v_proj.weight": "model.safetensors",
485
+ "model.layers.26.input_layernorm.weight": "model.safetensors",
486
+ "model.layers.26.mlp.down_proj.biases": "model.safetensors",
487
+ "model.layers.26.mlp.down_proj.scales": "model.safetensors",
488
+ "model.layers.26.mlp.down_proj.weight": "model.safetensors",
489
+ "model.layers.26.mlp.gate_proj.biases": "model.safetensors",
490
+ "model.layers.26.mlp.gate_proj.scales": "model.safetensors",
491
+ "model.layers.26.mlp.gate_proj.weight": "model.safetensors",
492
+ "model.layers.26.mlp.up_proj.biases": "model.safetensors",
493
+ "model.layers.26.mlp.up_proj.scales": "model.safetensors",
494
+ "model.layers.26.mlp.up_proj.weight": "model.safetensors",
495
+ "model.layers.26.post_attention_layernorm.weight": "model.safetensors",
496
+ "model.layers.26.self_attn.k_norm.weight": "model.safetensors",
497
+ "model.layers.26.self_attn.k_proj.biases": "model.safetensors",
498
+ "model.layers.26.self_attn.k_proj.scales": "model.safetensors",
499
+ "model.layers.26.self_attn.k_proj.weight": "model.safetensors",
500
+ "model.layers.26.self_attn.o_proj.biases": "model.safetensors",
501
+ "model.layers.26.self_attn.o_proj.scales": "model.safetensors",
502
+ "model.layers.26.self_attn.o_proj.weight": "model.safetensors",
503
+ "model.layers.26.self_attn.q_norm.weight": "model.safetensors",
504
+ "model.layers.26.self_attn.q_proj.biases": "model.safetensors",
505
+ "model.layers.26.self_attn.q_proj.scales": "model.safetensors",
506
+ "model.layers.26.self_attn.q_proj.weight": "model.safetensors",
507
+ "model.layers.26.self_attn.v_proj.biases": "model.safetensors",
508
+ "model.layers.26.self_attn.v_proj.scales": "model.safetensors",
509
+ "model.layers.26.self_attn.v_proj.weight": "model.safetensors",
510
+ "model.layers.27.input_layernorm.weight": "model.safetensors",
511
+ "model.layers.27.mlp.down_proj.biases": "model.safetensors",
512
+ "model.layers.27.mlp.down_proj.scales": "model.safetensors",
513
+ "model.layers.27.mlp.down_proj.weight": "model.safetensors",
514
+ "model.layers.27.mlp.gate_proj.biases": "model.safetensors",
515
+ "model.layers.27.mlp.gate_proj.scales": "model.safetensors",
516
+ "model.layers.27.mlp.gate_proj.weight": "model.safetensors",
517
+ "model.layers.27.mlp.up_proj.biases": "model.safetensors",
518
+ "model.layers.27.mlp.up_proj.scales": "model.safetensors",
519
+ "model.layers.27.mlp.up_proj.weight": "model.safetensors",
520
+ "model.layers.27.post_attention_layernorm.weight": "model.safetensors",
521
+ "model.layers.27.self_attn.k_norm.weight": "model.safetensors",
522
+ "model.layers.27.self_attn.k_proj.biases": "model.safetensors",
523
+ "model.layers.27.self_attn.k_proj.scales": "model.safetensors",
524
+ "model.layers.27.self_attn.k_proj.weight": "model.safetensors",
525
+ "model.layers.27.self_attn.o_proj.biases": "model.safetensors",
526
+ "model.layers.27.self_attn.o_proj.scales": "model.safetensors",
527
+ "model.layers.27.self_attn.o_proj.weight": "model.safetensors",
528
+ "model.layers.27.self_attn.q_norm.weight": "model.safetensors",
529
+ "model.layers.27.self_attn.q_proj.biases": "model.safetensors",
530
+ "model.layers.27.self_attn.q_proj.scales": "model.safetensors",
531
+ "model.layers.27.self_attn.q_proj.weight": "model.safetensors",
532
+ "model.layers.27.self_attn.v_proj.biases": "model.safetensors",
533
+ "model.layers.27.self_attn.v_proj.scales": "model.safetensors",
534
+ "model.layers.27.self_attn.v_proj.weight": "model.safetensors",
535
+ "model.layers.28.input_layernorm.weight": "model.safetensors",
536
+ "model.layers.28.mlp.down_proj.biases": "model.safetensors",
537
+ "model.layers.28.mlp.down_proj.scales": "model.safetensors",
538
+ "model.layers.28.mlp.down_proj.weight": "model.safetensors",
539
+ "model.layers.28.mlp.gate_proj.biases": "model.safetensors",
540
+ "model.layers.28.mlp.gate_proj.scales": "model.safetensors",
541
+ "model.layers.28.mlp.gate_proj.weight": "model.safetensors",
542
+ "model.layers.28.mlp.up_proj.biases": "model.safetensors",
543
+ "model.layers.28.mlp.up_proj.scales": "model.safetensors",
544
+ "model.layers.28.mlp.up_proj.weight": "model.safetensors",
545
+ "model.layers.28.post_attention_layernorm.weight": "model.safetensors",
546
+ "model.layers.28.self_attn.k_norm.weight": "model.safetensors",
547
+ "model.layers.28.self_attn.k_proj.biases": "model.safetensors",
548
+ "model.layers.28.self_attn.k_proj.scales": "model.safetensors",
549
+ "model.layers.28.self_attn.k_proj.weight": "model.safetensors",
550
+ "model.layers.28.self_attn.o_proj.biases": "model.safetensors",
551
+ "model.layers.28.self_attn.o_proj.scales": "model.safetensors",
552
+ "model.layers.28.self_attn.o_proj.weight": "model.safetensors",
553
+ "model.layers.28.self_attn.q_norm.weight": "model.safetensors",
554
+ "model.layers.28.self_attn.q_proj.biases": "model.safetensors",
555
+ "model.layers.28.self_attn.q_proj.scales": "model.safetensors",
556
+ "model.layers.28.self_attn.q_proj.weight": "model.safetensors",
557
+ "model.layers.28.self_attn.v_proj.biases": "model.safetensors",
558
+ "model.layers.28.self_attn.v_proj.scales": "model.safetensors",
559
+ "model.layers.28.self_attn.v_proj.weight": "model.safetensors",
560
+ "model.layers.29.input_layernorm.weight": "model.safetensors",
561
+ "model.layers.29.mlp.down_proj.biases": "model.safetensors",
562
+ "model.layers.29.mlp.down_proj.scales": "model.safetensors",
563
+ "model.layers.29.mlp.down_proj.weight": "model.safetensors",
564
+ "model.layers.29.mlp.gate_proj.biases": "model.safetensors",
565
+ "model.layers.29.mlp.gate_proj.scales": "model.safetensors",
566
+ "model.layers.29.mlp.gate_proj.weight": "model.safetensors",
567
+ "model.layers.29.mlp.up_proj.biases": "model.safetensors",
568
+ "model.layers.29.mlp.up_proj.scales": "model.safetensors",
569
+ "model.layers.29.mlp.up_proj.weight": "model.safetensors",
570
+ "model.layers.29.post_attention_layernorm.weight": "model.safetensors",
571
+ "model.layers.29.self_attn.k_norm.weight": "model.safetensors",
572
+ "model.layers.29.self_attn.k_proj.biases": "model.safetensors",
573
+ "model.layers.29.self_attn.k_proj.scales": "model.safetensors",
574
+ "model.layers.29.self_attn.k_proj.weight": "model.safetensors",
575
+ "model.layers.29.self_attn.o_proj.biases": "model.safetensors",
576
+ "model.layers.29.self_attn.o_proj.scales": "model.safetensors",
577
+ "model.layers.29.self_attn.o_proj.weight": "model.safetensors",
578
+ "model.layers.29.self_attn.q_norm.weight": "model.safetensors",
579
+ "model.layers.29.self_attn.q_proj.biases": "model.safetensors",
580
+ "model.layers.29.self_attn.q_proj.scales": "model.safetensors",
581
+ "model.layers.29.self_attn.q_proj.weight": "model.safetensors",
582
+ "model.layers.29.self_attn.v_proj.biases": "model.safetensors",
583
+ "model.layers.29.self_attn.v_proj.scales": "model.safetensors",
584
+ "model.layers.29.self_attn.v_proj.weight": "model.safetensors",
585
+ "model.layers.3.input_layernorm.weight": "model.safetensors",
586
+ "model.layers.3.mlp.down_proj.biases": "model.safetensors",
587
+ "model.layers.3.mlp.down_proj.scales": "model.safetensors",
588
+ "model.layers.3.mlp.down_proj.weight": "model.safetensors",
589
+ "model.layers.3.mlp.gate_proj.biases": "model.safetensors",
590
+ "model.layers.3.mlp.gate_proj.scales": "model.safetensors",
591
+ "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
592
+ "model.layers.3.mlp.up_proj.biases": "model.safetensors",
593
+ "model.layers.3.mlp.up_proj.scales": "model.safetensors",
594
+ "model.layers.3.mlp.up_proj.weight": "model.safetensors",
595
+ "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
596
+ "model.layers.3.self_attn.k_norm.weight": "model.safetensors",
597
+ "model.layers.3.self_attn.k_proj.biases": "model.safetensors",
598
+ "model.layers.3.self_attn.k_proj.scales": "model.safetensors",
599
+ "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
600
+ "model.layers.3.self_attn.o_proj.biases": "model.safetensors",
601
+ "model.layers.3.self_attn.o_proj.scales": "model.safetensors",
602
+ "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
603
+ "model.layers.3.self_attn.q_norm.weight": "model.safetensors",
604
+ "model.layers.3.self_attn.q_proj.biases": "model.safetensors",
605
+ "model.layers.3.self_attn.q_proj.scales": "model.safetensors",
606
+ "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
607
+ "model.layers.3.self_attn.v_proj.biases": "model.safetensors",
608
+ "model.layers.3.self_attn.v_proj.scales": "model.safetensors",
609
+ "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
610
+ "model.layers.30.input_layernorm.weight": "model.safetensors",
611
+ "model.layers.30.mlp.down_proj.biases": "model.safetensors",
612
+ "model.layers.30.mlp.down_proj.scales": "model.safetensors",
613
+ "model.layers.30.mlp.down_proj.weight": "model.safetensors",
614
+ "model.layers.30.mlp.gate_proj.biases": "model.safetensors",
615
+ "model.layers.30.mlp.gate_proj.scales": "model.safetensors",
616
+ "model.layers.30.mlp.gate_proj.weight": "model.safetensors",
617
+ "model.layers.30.mlp.up_proj.biases": "model.safetensors",
618
+ "model.layers.30.mlp.up_proj.scales": "model.safetensors",
619
+ "model.layers.30.mlp.up_proj.weight": "model.safetensors",
620
+ "model.layers.30.post_attention_layernorm.weight": "model.safetensors",
621
+ "model.layers.30.self_attn.k_norm.weight": "model.safetensors",
622
+ "model.layers.30.self_attn.k_proj.biases": "model.safetensors",
623
+ "model.layers.30.self_attn.k_proj.scales": "model.safetensors",
624
+ "model.layers.30.self_attn.k_proj.weight": "model.safetensors",
625
+ "model.layers.30.self_attn.o_proj.biases": "model.safetensors",
626
+ "model.layers.30.self_attn.o_proj.scales": "model.safetensors",
627
+ "model.layers.30.self_attn.o_proj.weight": "model.safetensors",
628
+ "model.layers.30.self_attn.q_norm.weight": "model.safetensors",
629
+ "model.layers.30.self_attn.q_proj.biases": "model.safetensors",
630
+ "model.layers.30.self_attn.q_proj.scales": "model.safetensors",
631
+ "model.layers.30.self_attn.q_proj.weight": "model.safetensors",
632
+ "model.layers.30.self_attn.v_proj.biases": "model.safetensors",
633
+ "model.layers.30.self_attn.v_proj.scales": "model.safetensors",
634
+ "model.layers.30.self_attn.v_proj.weight": "model.safetensors",
635
+ "model.layers.31.input_layernorm.weight": "model.safetensors",
636
+ "model.layers.31.mlp.down_proj.biases": "model.safetensors",
637
+ "model.layers.31.mlp.down_proj.scales": "model.safetensors",
638
+ "model.layers.31.mlp.down_proj.weight": "model.safetensors",
639
+ "model.layers.31.mlp.gate_proj.biases": "model.safetensors",
640
+ "model.layers.31.mlp.gate_proj.scales": "model.safetensors",
641
+ "model.layers.31.mlp.gate_proj.weight": "model.safetensors",
642
+ "model.layers.31.mlp.up_proj.biases": "model.safetensors",
643
+ "model.layers.31.mlp.up_proj.scales": "model.safetensors",
644
+ "model.layers.31.mlp.up_proj.weight": "model.safetensors",
645
+ "model.layers.31.post_attention_layernorm.weight": "model.safetensors",
646
+ "model.layers.31.self_attn.k_norm.weight": "model.safetensors",
647
+ "model.layers.31.self_attn.k_proj.biases": "model.safetensors",
648
+ "model.layers.31.self_attn.k_proj.scales": "model.safetensors",
649
+ "model.layers.31.self_attn.k_proj.weight": "model.safetensors",
650
+ "model.layers.31.self_attn.o_proj.biases": "model.safetensors",
651
+ "model.layers.31.self_attn.o_proj.scales": "model.safetensors",
652
+ "model.layers.31.self_attn.o_proj.weight": "model.safetensors",
653
+ "model.layers.31.self_attn.q_norm.weight": "model.safetensors",
654
+ "model.layers.31.self_attn.q_proj.biases": "model.safetensors",
655
+ "model.layers.31.self_attn.q_proj.scales": "model.safetensors",
656
+ "model.layers.31.self_attn.q_proj.weight": "model.safetensors",
657
+ "model.layers.31.self_attn.v_proj.biases": "model.safetensors",
658
+ "model.layers.31.self_attn.v_proj.scales": "model.safetensors",
659
+ "model.layers.31.self_attn.v_proj.weight": "model.safetensors",
660
+ "model.layers.32.input_layernorm.weight": "model.safetensors",
661
+ "model.layers.32.mlp.down_proj.biases": "model.safetensors",
662
+ "model.layers.32.mlp.down_proj.scales": "model.safetensors",
663
+ "model.layers.32.mlp.down_proj.weight": "model.safetensors",
664
+ "model.layers.32.mlp.gate_proj.biases": "model.safetensors",
665
+ "model.layers.32.mlp.gate_proj.scales": "model.safetensors",
666
+ "model.layers.32.mlp.gate_proj.weight": "model.safetensors",
667
+ "model.layers.32.mlp.up_proj.biases": "model.safetensors",
668
+ "model.layers.32.mlp.up_proj.scales": "model.safetensors",
669
+ "model.layers.32.mlp.up_proj.weight": "model.safetensors",
670
+ "model.layers.32.post_attention_layernorm.weight": "model.safetensors",
671
+ "model.layers.32.self_attn.k_norm.weight": "model.safetensors",
672
+ "model.layers.32.self_attn.k_proj.biases": "model.safetensors",
673
+ "model.layers.32.self_attn.k_proj.scales": "model.safetensors",
674
+ "model.layers.32.self_attn.k_proj.weight": "model.safetensors",
675
+ "model.layers.32.self_attn.o_proj.biases": "model.safetensors",
676
+ "model.layers.32.self_attn.o_proj.scales": "model.safetensors",
677
+ "model.layers.32.self_attn.o_proj.weight": "model.safetensors",
678
+ "model.layers.32.self_attn.q_norm.weight": "model.safetensors",
679
+ "model.layers.32.self_attn.q_proj.biases": "model.safetensors",
680
+ "model.layers.32.self_attn.q_proj.scales": "model.safetensors",
681
+ "model.layers.32.self_attn.q_proj.weight": "model.safetensors",
682
+ "model.layers.32.self_attn.v_proj.biases": "model.safetensors",
683
+ "model.layers.32.self_attn.v_proj.scales": "model.safetensors",
684
+ "model.layers.32.self_attn.v_proj.weight": "model.safetensors",
685
+ "model.layers.33.input_layernorm.weight": "model.safetensors",
686
+ "model.layers.33.mlp.down_proj.biases": "model.safetensors",
687
+ "model.layers.33.mlp.down_proj.scales": "model.safetensors",
688
+ "model.layers.33.mlp.down_proj.weight": "model.safetensors",
689
+ "model.layers.33.mlp.gate_proj.biases": "model.safetensors",
690
+ "model.layers.33.mlp.gate_proj.scales": "model.safetensors",
691
+ "model.layers.33.mlp.gate_proj.weight": "model.safetensors",
692
+ "model.layers.33.mlp.up_proj.biases": "model.safetensors",
693
+ "model.layers.33.mlp.up_proj.scales": "model.safetensors",
694
+ "model.layers.33.mlp.up_proj.weight": "model.safetensors",
695
+ "model.layers.33.post_attention_layernorm.weight": "model.safetensors",
696
+ "model.layers.33.self_attn.k_norm.weight": "model.safetensors",
697
+ "model.layers.33.self_attn.k_proj.biases": "model.safetensors",
698
+ "model.layers.33.self_attn.k_proj.scales": "model.safetensors",
699
+ "model.layers.33.self_attn.k_proj.weight": "model.safetensors",
700
+ "model.layers.33.self_attn.o_proj.biases": "model.safetensors",
701
+ "model.layers.33.self_attn.o_proj.scales": "model.safetensors",
702
+ "model.layers.33.self_attn.o_proj.weight": "model.safetensors",
703
+ "model.layers.33.self_attn.q_norm.weight": "model.safetensors",
704
+ "model.layers.33.self_attn.q_proj.biases": "model.safetensors",
705
+ "model.layers.33.self_attn.q_proj.scales": "model.safetensors",
706
+ "model.layers.33.self_attn.q_proj.weight": "model.safetensors",
707
+ "model.layers.33.self_attn.v_proj.biases": "model.safetensors",
708
+ "model.layers.33.self_attn.v_proj.scales": "model.safetensors",
709
+ "model.layers.33.self_attn.v_proj.weight": "model.safetensors",
710
+ "model.layers.34.input_layernorm.weight": "model.safetensors",
711
+ "model.layers.34.mlp.down_proj.biases": "model.safetensors",
712
+ "model.layers.34.mlp.down_proj.scales": "model.safetensors",
713
+ "model.layers.34.mlp.down_proj.weight": "model.safetensors",
714
+ "model.layers.34.mlp.gate_proj.biases": "model.safetensors",
715
+ "model.layers.34.mlp.gate_proj.scales": "model.safetensors",
716
+ "model.layers.34.mlp.gate_proj.weight": "model.safetensors",
717
+ "model.layers.34.mlp.up_proj.biases": "model.safetensors",
718
+ "model.layers.34.mlp.up_proj.scales": "model.safetensors",
719
+ "model.layers.34.mlp.up_proj.weight": "model.safetensors",
720
+ "model.layers.34.post_attention_layernorm.weight": "model.safetensors",
721
+ "model.layers.34.self_attn.k_norm.weight": "model.safetensors",
722
+ "model.layers.34.self_attn.k_proj.biases": "model.safetensors",
723
+ "model.layers.34.self_attn.k_proj.scales": "model.safetensors",
724
+ "model.layers.34.self_attn.k_proj.weight": "model.safetensors",
725
+ "model.layers.34.self_attn.o_proj.biases": "model.safetensors",
726
+ "model.layers.34.self_attn.o_proj.scales": "model.safetensors",
727
+ "model.layers.34.self_attn.o_proj.weight": "model.safetensors",
728
+ "model.layers.34.self_attn.q_norm.weight": "model.safetensors",
729
+ "model.layers.34.self_attn.q_proj.biases": "model.safetensors",
730
+ "model.layers.34.self_attn.q_proj.scales": "model.safetensors",
731
+ "model.layers.34.self_attn.q_proj.weight": "model.safetensors",
732
+ "model.layers.34.self_attn.v_proj.biases": "model.safetensors",
733
+ "model.layers.34.self_attn.v_proj.scales": "model.safetensors",
734
+ "model.layers.34.self_attn.v_proj.weight": "model.safetensors",
735
+ "model.layers.35.input_layernorm.weight": "model.safetensors",
736
+ "model.layers.35.mlp.down_proj.biases": "model.safetensors",
737
+ "model.layers.35.mlp.down_proj.scales": "model.safetensors",
738
+ "model.layers.35.mlp.down_proj.weight": "model.safetensors",
739
+ "model.layers.35.mlp.gate_proj.biases": "model.safetensors",
740
+ "model.layers.35.mlp.gate_proj.scales": "model.safetensors",
741
+ "model.layers.35.mlp.gate_proj.weight": "model.safetensors",
742
+ "model.layers.35.mlp.up_proj.biases": "model.safetensors",
743
+ "model.layers.35.mlp.up_proj.scales": "model.safetensors",
744
+ "model.layers.35.mlp.up_proj.weight": "model.safetensors",
745
+ "model.layers.35.post_attention_layernorm.weight": "model.safetensors",
746
+ "model.layers.35.self_attn.k_norm.weight": "model.safetensors",
747
+ "model.layers.35.self_attn.k_proj.biases": "model.safetensors",
748
+ "model.layers.35.self_attn.k_proj.scales": "model.safetensors",
749
+ "model.layers.35.self_attn.k_proj.weight": "model.safetensors",
750
+ "model.layers.35.self_attn.o_proj.biases": "model.safetensors",
751
+ "model.layers.35.self_attn.o_proj.scales": "model.safetensors",
752
+ "model.layers.35.self_attn.o_proj.weight": "model.safetensors",
753
+ "model.layers.35.self_attn.q_norm.weight": "model.safetensors",
754
+ "model.layers.35.self_attn.q_proj.biases": "model.safetensors",
755
+ "model.layers.35.self_attn.q_proj.scales": "model.safetensors",
756
+ "model.layers.35.self_attn.q_proj.weight": "model.safetensors",
757
+ "model.layers.35.self_attn.v_proj.biases": "model.safetensors",
758
+ "model.layers.35.self_attn.v_proj.scales": "model.safetensors",
759
+ "model.layers.35.self_attn.v_proj.weight": "model.safetensors",
760
+ "model.layers.4.input_layernorm.weight": "model.safetensors",
761
+ "model.layers.4.mlp.down_proj.biases": "model.safetensors",
762
+ "model.layers.4.mlp.down_proj.scales": "model.safetensors",
763
+ "model.layers.4.mlp.down_proj.weight": "model.safetensors",
764
+ "model.layers.4.mlp.gate_proj.biases": "model.safetensors",
765
+ "model.layers.4.mlp.gate_proj.scales": "model.safetensors",
766
+ "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
767
+ "model.layers.4.mlp.up_proj.biases": "model.safetensors",
768
+ "model.layers.4.mlp.up_proj.scales": "model.safetensors",
769
+ "model.layers.4.mlp.up_proj.weight": "model.safetensors",
770
+ "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
771
+ "model.layers.4.self_attn.k_norm.weight": "model.safetensors",
772
+ "model.layers.4.self_attn.k_proj.biases": "model.safetensors",
773
+ "model.layers.4.self_attn.k_proj.scales": "model.safetensors",
774
+ "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
775
+ "model.layers.4.self_attn.o_proj.biases": "model.safetensors",
776
+ "model.layers.4.self_attn.o_proj.scales": "model.safetensors",
777
+ "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
778
+ "model.layers.4.self_attn.q_norm.weight": "model.safetensors",
779
+ "model.layers.4.self_attn.q_proj.biases": "model.safetensors",
780
+ "model.layers.4.self_attn.q_proj.scales": "model.safetensors",
781
+ "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
782
+ "model.layers.4.self_attn.v_proj.biases": "model.safetensors",
783
+ "model.layers.4.self_attn.v_proj.scales": "model.safetensors",
784
+ "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
785
+ "model.layers.5.input_layernorm.weight": "model.safetensors",
786
+ "model.layers.5.mlp.down_proj.biases": "model.safetensors",
787
+ "model.layers.5.mlp.down_proj.scales": "model.safetensors",
788
+ "model.layers.5.mlp.down_proj.weight": "model.safetensors",
789
+ "model.layers.5.mlp.gate_proj.biases": "model.safetensors",
790
+ "model.layers.5.mlp.gate_proj.scales": "model.safetensors",
791
+ "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
792
+ "model.layers.5.mlp.up_proj.biases": "model.safetensors",
793
+ "model.layers.5.mlp.up_proj.scales": "model.safetensors",
794
+ "model.layers.5.mlp.up_proj.weight": "model.safetensors",
795
+ "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
796
+ "model.layers.5.self_attn.k_norm.weight": "model.safetensors",
797
+ "model.layers.5.self_attn.k_proj.biases": "model.safetensors",
798
+ "model.layers.5.self_attn.k_proj.scales": "model.safetensors",
799
+ "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
800
+ "model.layers.5.self_attn.o_proj.biases": "model.safetensors",
801
+ "model.layers.5.self_attn.o_proj.scales": "model.safetensors",
802
+ "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
803
+ "model.layers.5.self_attn.q_norm.weight": "model.safetensors",
804
+ "model.layers.5.self_attn.q_proj.biases": "model.safetensors",
805
+ "model.layers.5.self_attn.q_proj.scales": "model.safetensors",
806
+ "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
807
+ "model.layers.5.self_attn.v_proj.biases": "model.safetensors",
808
+ "model.layers.5.self_attn.v_proj.scales": "model.safetensors",
809
+ "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
810
+ "model.layers.6.input_layernorm.weight": "model.safetensors",
811
+ "model.layers.6.mlp.down_proj.biases": "model.safetensors",
812
+ "model.layers.6.mlp.down_proj.scales": "model.safetensors",
813
+ "model.layers.6.mlp.down_proj.weight": "model.safetensors",
814
+ "model.layers.6.mlp.gate_proj.biases": "model.safetensors",
815
+ "model.layers.6.mlp.gate_proj.scales": "model.safetensors",
816
+ "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
817
+ "model.layers.6.mlp.up_proj.biases": "model.safetensors",
818
+ "model.layers.6.mlp.up_proj.scales": "model.safetensors",
819
+ "model.layers.6.mlp.up_proj.weight": "model.safetensors",
820
+ "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
821
+ "model.layers.6.self_attn.k_norm.weight": "model.safetensors",
822
+ "model.layers.6.self_attn.k_proj.biases": "model.safetensors",
823
+ "model.layers.6.self_attn.k_proj.scales": "model.safetensors",
824
+ "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
825
+ "model.layers.6.self_attn.o_proj.biases": "model.safetensors",
826
+ "model.layers.6.self_attn.o_proj.scales": "model.safetensors",
827
+ "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
828
+ "model.layers.6.self_attn.q_norm.weight": "model.safetensors",
829
+ "model.layers.6.self_attn.q_proj.biases": "model.safetensors",
830
+ "model.layers.6.self_attn.q_proj.scales": "model.safetensors",
831
+ "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
832
+ "model.layers.6.self_attn.v_proj.biases": "model.safetensors",
833
+ "model.layers.6.self_attn.v_proj.scales": "model.safetensors",
834
+ "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
835
+ "model.layers.7.input_layernorm.weight": "model.safetensors",
836
+ "model.layers.7.mlp.down_proj.biases": "model.safetensors",
837
+ "model.layers.7.mlp.down_proj.scales": "model.safetensors",
838
+ "model.layers.7.mlp.down_proj.weight": "model.safetensors",
839
+ "model.layers.7.mlp.gate_proj.biases": "model.safetensors",
840
+ "model.layers.7.mlp.gate_proj.scales": "model.safetensors",
841
+ "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
842
+ "model.layers.7.mlp.up_proj.biases": "model.safetensors",
843
+ "model.layers.7.mlp.up_proj.scales": "model.safetensors",
844
+ "model.layers.7.mlp.up_proj.weight": "model.safetensors",
845
+ "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
846
+ "model.layers.7.self_attn.k_norm.weight": "model.safetensors",
847
+ "model.layers.7.self_attn.k_proj.biases": "model.safetensors",
848
+ "model.layers.7.self_attn.k_proj.scales": "model.safetensors",
849
+ "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
850
+ "model.layers.7.self_attn.o_proj.biases": "model.safetensors",
851
+ "model.layers.7.self_attn.o_proj.scales": "model.safetensors",
852
+ "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
853
+ "model.layers.7.self_attn.q_norm.weight": "model.safetensors",
854
+ "model.layers.7.self_attn.q_proj.biases": "model.safetensors",
855
+ "model.layers.7.self_attn.q_proj.scales": "model.safetensors",
856
+ "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
857
+ "model.layers.7.self_attn.v_proj.biases": "model.safetensors",
858
+ "model.layers.7.self_attn.v_proj.scales": "model.safetensors",
859
+ "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
860
+ "model.layers.8.input_layernorm.weight": "model.safetensors",
861
+ "model.layers.8.mlp.down_proj.biases": "model.safetensors",
862
+ "model.layers.8.mlp.down_proj.scales": "model.safetensors",
863
+ "model.layers.8.mlp.down_proj.weight": "model.safetensors",
864
+ "model.layers.8.mlp.gate_proj.biases": "model.safetensors",
865
+ "model.layers.8.mlp.gate_proj.scales": "model.safetensors",
866
+ "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
867
+ "model.layers.8.mlp.up_proj.biases": "model.safetensors",
868
+ "model.layers.8.mlp.up_proj.scales": "model.safetensors",
869
+ "model.layers.8.mlp.up_proj.weight": "model.safetensors",
870
+ "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
871
+ "model.layers.8.self_attn.k_norm.weight": "model.safetensors",
872
+ "model.layers.8.self_attn.k_proj.biases": "model.safetensors",
873
+ "model.layers.8.self_attn.k_proj.scales": "model.safetensors",
874
+ "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
875
+ "model.layers.8.self_attn.o_proj.biases": "model.safetensors",
876
+ "model.layers.8.self_attn.o_proj.scales": "model.safetensors",
877
+ "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
878
+ "model.layers.8.self_attn.q_norm.weight": "model.safetensors",
879
+ "model.layers.8.self_attn.q_proj.biases": "model.safetensors",
880
+ "model.layers.8.self_attn.q_proj.scales": "model.safetensors",
881
+ "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
882
+ "model.layers.8.self_attn.v_proj.biases": "model.safetensors",
883
+ "model.layers.8.self_attn.v_proj.scales": "model.safetensors",
884
+ "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
885
+ "model.layers.9.input_layernorm.weight": "model.safetensors",
886
+ "model.layers.9.mlp.down_proj.biases": "model.safetensors",
887
+ "model.layers.9.mlp.down_proj.scales": "model.safetensors",
888
+ "model.layers.9.mlp.down_proj.weight": "model.safetensors",
889
+ "model.layers.9.mlp.gate_proj.biases": "model.safetensors",
890
+ "model.layers.9.mlp.gate_proj.scales": "model.safetensors",
891
+ "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
892
+ "model.layers.9.mlp.up_proj.biases": "model.safetensors",
893
+ "model.layers.9.mlp.up_proj.scales": "model.safetensors",
894
+ "model.layers.9.mlp.up_proj.weight": "model.safetensors",
895
+ "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
896
+ "model.layers.9.self_attn.k_norm.weight": "model.safetensors",
897
+ "model.layers.9.self_attn.k_proj.biases": "model.safetensors",
898
+ "model.layers.9.self_attn.k_proj.scales": "model.safetensors",
899
+ "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
900
+ "model.layers.9.self_attn.o_proj.biases": "model.safetensors",
901
+ "model.layers.9.self_attn.o_proj.scales": "model.safetensors",
902
+ "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
903
+ "model.layers.9.self_attn.q_norm.weight": "model.safetensors",
904
+ "model.layers.9.self_attn.q_proj.biases": "model.safetensors",
905
+ "model.layers.9.self_attn.q_proj.scales": "model.safetensors",
906
+ "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
907
+ "model.layers.9.self_attn.v_proj.biases": "model.safetensors",
908
+ "model.layers.9.self_attn.v_proj.scales": "model.safetensors",
909
+ "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
910
+ "model.norm.weight": "model.safetensors"
911
+ }
912
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}",
231
+ "clean_up_tokenization_spaces": false,
232
+ "eos_token": "<|im_end|>",
233
+ "errors": "replace",
234
+ "extra_special_tokens": {},
235
+ "model_max_length": 262144,
236
+ "pad_token": "<|endoftext|>",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff