introvoyz041 commited on
Commit
7f914c7
·
verified ·
1 Parent(s): 3976706

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +2112 -0
config.json ADDED
@@ -0,0 +1,2112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "eos_token_id": 151645,
8
+ "head_dim": 128,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 12288,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention"
50
+ ],
51
+ "max_position_embeddings": 40960,
52
+ "max_window_layers": 36,
53
+ "model_type": "qwen3",
54
+ "num_attention_heads": 32,
55
+ "num_hidden_layers": 36,
56
+ "num_key_value_heads": 8,
57
+ "pad_token_id": 151654,
58
+ "quantization": {
59
+ "group_size": 64,
60
+ "bits": 4,
61
+ "mode": "affine",
62
+ "model.embed_tokens": {
63
+ "bits": 6,
64
+ "group_size": 64
65
+ },
66
+ "model.layers.0.self_attn.q_proj": {
67
+ "bits": 4,
68
+ "group_size": 64
69
+ },
70
+ "model.layers.0.self_attn.k_proj": {
71
+ "bits": 4,
72
+ "group_size": 64
73
+ },
74
+ "model.layers.0.self_attn.v_proj": {
75
+ "bits": 4,
76
+ "group_size": 64
77
+ },
78
+ "model.layers.0.self_attn.o_proj": {
79
+ "bits": 4,
80
+ "group_size": 64
81
+ },
82
+ "model.layers.0.mlp.gate_proj": {
83
+ "bits": 4,
84
+ "group_size": 64
85
+ },
86
+ "model.layers.0.mlp.down_proj": {
87
+ "bits": 4,
88
+ "group_size": 64
89
+ },
90
+ "model.layers.0.mlp.up_proj": {
91
+ "bits": 4,
92
+ "group_size": 64
93
+ },
94
+ "model.layers.1.self_attn.q_proj": {
95
+ "bits": 4,
96
+ "group_size": 64
97
+ },
98
+ "model.layers.1.self_attn.k_proj": {
99
+ "bits": 4,
100
+ "group_size": 64
101
+ },
102
+ "model.layers.1.self_attn.v_proj": {
103
+ "bits": 4,
104
+ "group_size": 64
105
+ },
106
+ "model.layers.1.self_attn.o_proj": {
107
+ "bits": 4,
108
+ "group_size": 64
109
+ },
110
+ "model.layers.1.mlp.gate_proj": {
111
+ "bits": 4,
112
+ "group_size": 64
113
+ },
114
+ "model.layers.1.mlp.down_proj": {
115
+ "bits": 4,
116
+ "group_size": 64
117
+ },
118
+ "model.layers.1.mlp.up_proj": {
119
+ "bits": 4,
120
+ "group_size": 64
121
+ },
122
+ "model.layers.2.self_attn.q_proj": {
123
+ "bits": 4,
124
+ "group_size": 64
125
+ },
126
+ "model.layers.2.self_attn.k_proj": {
127
+ "bits": 4,
128
+ "group_size": 64
129
+ },
130
+ "model.layers.2.self_attn.v_proj": {
131
+ "bits": 4,
132
+ "group_size": 64
133
+ },
134
+ "model.layers.2.self_attn.o_proj": {
135
+ "bits": 4,
136
+ "group_size": 64
137
+ },
138
+ "model.layers.2.mlp.gate_proj": {
139
+ "bits": 4,
140
+ "group_size": 64
141
+ },
142
+ "model.layers.2.mlp.down_proj": {
143
+ "bits": 4,
144
+ "group_size": 64
145
+ },
146
+ "model.layers.2.mlp.up_proj": {
147
+ "bits": 4,
148
+ "group_size": 64
149
+ },
150
+ "model.layers.3.self_attn.q_proj": {
151
+ "bits": 4,
152
+ "group_size": 64
153
+ },
154
+ "model.layers.3.self_attn.k_proj": {
155
+ "bits": 4,
156
+ "group_size": 64
157
+ },
158
+ "model.layers.3.self_attn.v_proj": {
159
+ "bits": 4,
160
+ "group_size": 64
161
+ },
162
+ "model.layers.3.self_attn.o_proj": {
163
+ "bits": 4,
164
+ "group_size": 64
165
+ },
166
+ "model.layers.3.mlp.gate_proj": {
167
+ "bits": 4,
168
+ "group_size": 64
169
+ },
170
+ "model.layers.3.mlp.down_proj": {
171
+ "bits": 4,
172
+ "group_size": 64
173
+ },
174
+ "model.layers.3.mlp.up_proj": {
175
+ "bits": 4,
176
+ "group_size": 64
177
+ },
178
+ "model.layers.4.self_attn.q_proj": {
179
+ "bits": 4,
180
+ "group_size": 64
181
+ },
182
+ "model.layers.4.self_attn.k_proj": {
183
+ "bits": 4,
184
+ "group_size": 64
185
+ },
186
+ "model.layers.4.self_attn.v_proj": {
187
+ "bits": 4,
188
+ "group_size": 64
189
+ },
190
+ "model.layers.4.self_attn.o_proj": {
191
+ "bits": 4,
192
+ "group_size": 64
193
+ },
194
+ "model.layers.4.mlp.gate_proj": {
195
+ "bits": 4,
196
+ "group_size": 64
197
+ },
198
+ "model.layers.4.mlp.down_proj": {
199
+ "bits": 4,
200
+ "group_size": 64
201
+ },
202
+ "model.layers.4.mlp.up_proj": {
203
+ "bits": 4,
204
+ "group_size": 64
205
+ },
206
+ "model.layers.5.self_attn.q_proj": {
207
+ "bits": 4,
208
+ "group_size": 64
209
+ },
210
+ "model.layers.5.self_attn.k_proj": {
211
+ "bits": 4,
212
+ "group_size": 64
213
+ },
214
+ "model.layers.5.self_attn.v_proj": {
215
+ "bits": 4,
216
+ "group_size": 64
217
+ },
218
+ "model.layers.5.self_attn.o_proj": {
219
+ "bits": 4,
220
+ "group_size": 64
221
+ },
222
+ "model.layers.5.mlp.gate_proj": {
223
+ "bits": 4,
224
+ "group_size": 64
225
+ },
226
+ "model.layers.5.mlp.down_proj": {
227
+ "bits": 4,
228
+ "group_size": 64
229
+ },
230
+ "model.layers.5.mlp.up_proj": {
231
+ "bits": 4,
232
+ "group_size": 64
233
+ },
234
+ "model.layers.6.self_attn.q_proj": {
235
+ "bits": 4,
236
+ "group_size": 64
237
+ },
238
+ "model.layers.6.self_attn.k_proj": {
239
+ "bits": 4,
240
+ "group_size": 64
241
+ },
242
+ "model.layers.6.self_attn.v_proj": {
243
+ "bits": 4,
244
+ "group_size": 64
245
+ },
246
+ "model.layers.6.self_attn.o_proj": {
247
+ "bits": 4,
248
+ "group_size": 64
249
+ },
250
+ "model.layers.6.mlp.gate_proj": {
251
+ "bits": 4,
252
+ "group_size": 64
253
+ },
254
+ "model.layers.6.mlp.down_proj": {
255
+ "bits": 4,
256
+ "group_size": 64
257
+ },
258
+ "model.layers.6.mlp.up_proj": {
259
+ "bits": 4,
260
+ "group_size": 64
261
+ },
262
+ "model.layers.7.self_attn.q_proj": {
263
+ "bits": 4,
264
+ "group_size": 64
265
+ },
266
+ "model.layers.7.self_attn.k_proj": {
267
+ "bits": 4,
268
+ "group_size": 64
269
+ },
270
+ "model.layers.7.self_attn.v_proj": {
271
+ "bits": 4,
272
+ "group_size": 64
273
+ },
274
+ "model.layers.7.self_attn.o_proj": {
275
+ "bits": 4,
276
+ "group_size": 64
277
+ },
278
+ "model.layers.7.mlp.gate_proj": {
279
+ "bits": 4,
280
+ "group_size": 64
281
+ },
282
+ "model.layers.7.mlp.down_proj": {
283
+ "bits": 4,
284
+ "group_size": 64
285
+ },
286
+ "model.layers.7.mlp.up_proj": {
287
+ "bits": 4,
288
+ "group_size": 64
289
+ },
290
+ "model.layers.8.self_attn.q_proj": {
291
+ "bits": 4,
292
+ "group_size": 64
293
+ },
294
+ "model.layers.8.self_attn.k_proj": {
295
+ "bits": 4,
296
+ "group_size": 64
297
+ },
298
+ "model.layers.8.self_attn.v_proj": {
299
+ "bits": 4,
300
+ "group_size": 64
301
+ },
302
+ "model.layers.8.self_attn.o_proj": {
303
+ "bits": 4,
304
+ "group_size": 64
305
+ },
306
+ "model.layers.8.mlp.gate_proj": {
307
+ "bits": 4,
308
+ "group_size": 64
309
+ },
310
+ "model.layers.8.mlp.down_proj": {
311
+ "bits": 4,
312
+ "group_size": 64
313
+ },
314
+ "model.layers.8.mlp.up_proj": {
315
+ "bits": 4,
316
+ "group_size": 64
317
+ },
318
+ "model.layers.9.self_attn.q_proj": {
319
+ "bits": 4,
320
+ "group_size": 64
321
+ },
322
+ "model.layers.9.self_attn.k_proj": {
323
+ "bits": 4,
324
+ "group_size": 64
325
+ },
326
+ "model.layers.9.self_attn.v_proj": {
327
+ "bits": 4,
328
+ "group_size": 64
329
+ },
330
+ "model.layers.9.self_attn.o_proj": {
331
+ "bits": 4,
332
+ "group_size": 64
333
+ },
334
+ "model.layers.9.mlp.gate_proj": {
335
+ "bits": 4,
336
+ "group_size": 64
337
+ },
338
+ "model.layers.9.mlp.down_proj": {
339
+ "bits": 4,
340
+ "group_size": 64
341
+ },
342
+ "model.layers.9.mlp.up_proj": {
343
+ "bits": 4,
344
+ "group_size": 64
345
+ },
346
+ "model.layers.10.self_attn.q_proj": {
347
+ "bits": 4,
348
+ "group_size": 64
349
+ },
350
+ "model.layers.10.self_attn.k_proj": {
351
+ "bits": 4,
352
+ "group_size": 64
353
+ },
354
+ "model.layers.10.self_attn.v_proj": {
355
+ "bits": 4,
356
+ "group_size": 64
357
+ },
358
+ "model.layers.10.self_attn.o_proj": {
359
+ "bits": 4,
360
+ "group_size": 64
361
+ },
362
+ "model.layers.10.mlp.gate_proj": {
363
+ "bits": 4,
364
+ "group_size": 64
365
+ },
366
+ "model.layers.10.mlp.down_proj": {
367
+ "bits": 4,
368
+ "group_size": 64
369
+ },
370
+ "model.layers.10.mlp.up_proj": {
371
+ "bits": 4,
372
+ "group_size": 64
373
+ },
374
+ "model.layers.11.self_attn.q_proj": {
375
+ "bits": 4,
376
+ "group_size": 64
377
+ },
378
+ "model.layers.11.self_attn.k_proj": {
379
+ "bits": 4,
380
+ "group_size": 64
381
+ },
382
+ "model.layers.11.self_attn.v_proj": {
383
+ "bits": 4,
384
+ "group_size": 64
385
+ },
386
+ "model.layers.11.self_attn.o_proj": {
387
+ "bits": 4,
388
+ "group_size": 64
389
+ },
390
+ "model.layers.11.mlp.gate_proj": {
391
+ "bits": 4,
392
+ "group_size": 64
393
+ },
394
+ "model.layers.11.mlp.down_proj": {
395
+ "bits": 4,
396
+ "group_size": 64
397
+ },
398
+ "model.layers.11.mlp.up_proj": {
399
+ "bits": 4,
400
+ "group_size": 64
401
+ },
402
+ "model.layers.12.self_attn.q_proj": {
403
+ "bits": 4,
404
+ "group_size": 64
405
+ },
406
+ "model.layers.12.self_attn.k_proj": {
407
+ "bits": 4,
408
+ "group_size": 64
409
+ },
410
+ "model.layers.12.self_attn.v_proj": {
411
+ "bits": 4,
412
+ "group_size": 64
413
+ },
414
+ "model.layers.12.self_attn.o_proj": {
415
+ "bits": 4,
416
+ "group_size": 64
417
+ },
418
+ "model.layers.12.mlp.gate_proj": {
419
+ "bits": 4,
420
+ "group_size": 64
421
+ },
422
+ "model.layers.12.mlp.down_proj": {
423
+ "bits": 4,
424
+ "group_size": 64
425
+ },
426
+ "model.layers.12.mlp.up_proj": {
427
+ "bits": 4,
428
+ "group_size": 64
429
+ },
430
+ "model.layers.13.self_attn.q_proj": {
431
+ "bits": 4,
432
+ "group_size": 64
433
+ },
434
+ "model.layers.13.self_attn.k_proj": {
435
+ "bits": 4,
436
+ "group_size": 64
437
+ },
438
+ "model.layers.13.self_attn.v_proj": {
439
+ "bits": 4,
440
+ "group_size": 64
441
+ },
442
+ "model.layers.13.self_attn.o_proj": {
443
+ "bits": 4,
444
+ "group_size": 64
445
+ },
446
+ "model.layers.13.mlp.gate_proj": {
447
+ "bits": 4,
448
+ "group_size": 64
449
+ },
450
+ "model.layers.13.mlp.down_proj": {
451
+ "bits": 4,
452
+ "group_size": 64
453
+ },
454
+ "model.layers.13.mlp.up_proj": {
455
+ "bits": 4,
456
+ "group_size": 64
457
+ },
458
+ "model.layers.14.self_attn.q_proj": {
459
+ "bits": 4,
460
+ "group_size": 64
461
+ },
462
+ "model.layers.14.self_attn.k_proj": {
463
+ "bits": 4,
464
+ "group_size": 64
465
+ },
466
+ "model.layers.14.self_attn.v_proj": {
467
+ "bits": 4,
468
+ "group_size": 64
469
+ },
470
+ "model.layers.14.self_attn.o_proj": {
471
+ "bits": 4,
472
+ "group_size": 64
473
+ },
474
+ "model.layers.14.mlp.gate_proj": {
475
+ "bits": 4,
476
+ "group_size": 64
477
+ },
478
+ "model.layers.14.mlp.down_proj": {
479
+ "bits": 4,
480
+ "group_size": 64
481
+ },
482
+ "model.layers.14.mlp.up_proj": {
483
+ "bits": 4,
484
+ "group_size": 64
485
+ },
486
+ "model.layers.15.self_attn.q_proj": {
487
+ "bits": 4,
488
+ "group_size": 64
489
+ },
490
+ "model.layers.15.self_attn.k_proj": {
491
+ "bits": 4,
492
+ "group_size": 64
493
+ },
494
+ "model.layers.15.self_attn.v_proj": {
495
+ "bits": 4,
496
+ "group_size": 64
497
+ },
498
+ "model.layers.15.self_attn.o_proj": {
499
+ "bits": 4,
500
+ "group_size": 64
501
+ },
502
+ "model.layers.15.mlp.gate_proj": {
503
+ "bits": 4,
504
+ "group_size": 64
505
+ },
506
+ "model.layers.15.mlp.down_proj": {
507
+ "bits": 4,
508
+ "group_size": 64
509
+ },
510
+ "model.layers.15.mlp.up_proj": {
511
+ "bits": 4,
512
+ "group_size": 64
513
+ },
514
+ "model.layers.16.self_attn.q_proj": {
515
+ "bits": 4,
516
+ "group_size": 64
517
+ },
518
+ "model.layers.16.self_attn.k_proj": {
519
+ "bits": 4,
520
+ "group_size": 64
521
+ },
522
+ "model.layers.16.self_attn.v_proj": {
523
+ "bits": 4,
524
+ "group_size": 64
525
+ },
526
+ "model.layers.16.self_attn.o_proj": {
527
+ "bits": 4,
528
+ "group_size": 64
529
+ },
530
+ "model.layers.16.mlp.gate_proj": {
531
+ "bits": 4,
532
+ "group_size": 64
533
+ },
534
+ "model.layers.16.mlp.down_proj": {
535
+ "bits": 4,
536
+ "group_size": 64
537
+ },
538
+ "model.layers.16.mlp.up_proj": {
539
+ "bits": 4,
540
+ "group_size": 64
541
+ },
542
+ "model.layers.17.self_attn.q_proj": {
543
+ "bits": 4,
544
+ "group_size": 64
545
+ },
546
+ "model.layers.17.self_attn.k_proj": {
547
+ "bits": 4,
548
+ "group_size": 64
549
+ },
550
+ "model.layers.17.self_attn.v_proj": {
551
+ "bits": 4,
552
+ "group_size": 64
553
+ },
554
+ "model.layers.17.self_attn.o_proj": {
555
+ "bits": 4,
556
+ "group_size": 64
557
+ },
558
+ "model.layers.17.mlp.gate_proj": {
559
+ "bits": 4,
560
+ "group_size": 64
561
+ },
562
+ "model.layers.17.mlp.down_proj": {
563
+ "bits": 4,
564
+ "group_size": 64
565
+ },
566
+ "model.layers.17.mlp.up_proj": {
567
+ "bits": 4,
568
+ "group_size": 64
569
+ },
570
+ "model.layers.18.self_attn.q_proj": {
571
+ "bits": 4,
572
+ "group_size": 64
573
+ },
574
+ "model.layers.18.self_attn.k_proj": {
575
+ "bits": 4,
576
+ "group_size": 64
577
+ },
578
+ "model.layers.18.self_attn.v_proj": {
579
+ "bits": 4,
580
+ "group_size": 64
581
+ },
582
+ "model.layers.18.self_attn.o_proj": {
583
+ "bits": 4,
584
+ "group_size": 64
585
+ },
586
+ "model.layers.18.mlp.gate_proj": {
587
+ "bits": 4,
588
+ "group_size": 64
589
+ },
590
+ "model.layers.18.mlp.down_proj": {
591
+ "bits": 4,
592
+ "group_size": 64
593
+ },
594
+ "model.layers.18.mlp.up_proj": {
595
+ "bits": 4,
596
+ "group_size": 64
597
+ },
598
+ "model.layers.19.self_attn.q_proj": {
599
+ "bits": 4,
600
+ "group_size": 64
601
+ },
602
+ "model.layers.19.self_attn.k_proj": {
603
+ "bits": 4,
604
+ "group_size": 64
605
+ },
606
+ "model.layers.19.self_attn.v_proj": {
607
+ "bits": 4,
608
+ "group_size": 64
609
+ },
610
+ "model.layers.19.self_attn.o_proj": {
611
+ "bits": 4,
612
+ "group_size": 64
613
+ },
614
+ "model.layers.19.mlp.gate_proj": {
615
+ "bits": 4,
616
+ "group_size": 64
617
+ },
618
+ "model.layers.19.mlp.down_proj": {
619
+ "bits": 4,
620
+ "group_size": 64
621
+ },
622
+ "model.layers.19.mlp.up_proj": {
623
+ "bits": 4,
624
+ "group_size": 64
625
+ },
626
+ "model.layers.20.self_attn.q_proj": {
627
+ "bits": 4,
628
+ "group_size": 64
629
+ },
630
+ "model.layers.20.self_attn.k_proj": {
631
+ "bits": 4,
632
+ "group_size": 64
633
+ },
634
+ "model.layers.20.self_attn.v_proj": {
635
+ "bits": 4,
636
+ "group_size": 64
637
+ },
638
+ "model.layers.20.self_attn.o_proj": {
639
+ "bits": 4,
640
+ "group_size": 64
641
+ },
642
+ "model.layers.20.mlp.gate_proj": {
643
+ "bits": 4,
644
+ "group_size": 64
645
+ },
646
+ "model.layers.20.mlp.down_proj": {
647
+ "bits": 4,
648
+ "group_size": 64
649
+ },
650
+ "model.layers.20.mlp.up_proj": {
651
+ "bits": 4,
652
+ "group_size": 64
653
+ },
654
+ "model.layers.21.self_attn.q_proj": {
655
+ "bits": 4,
656
+ "group_size": 64
657
+ },
658
+ "model.layers.21.self_attn.k_proj": {
659
+ "bits": 4,
660
+ "group_size": 64
661
+ },
662
+ "model.layers.21.self_attn.v_proj": {
663
+ "bits": 4,
664
+ "group_size": 64
665
+ },
666
+ "model.layers.21.self_attn.o_proj": {
667
+ "bits": 4,
668
+ "group_size": 64
669
+ },
670
+ "model.layers.21.mlp.gate_proj": {
671
+ "bits": 4,
672
+ "group_size": 64
673
+ },
674
+ "model.layers.21.mlp.down_proj": {
675
+ "bits": 4,
676
+ "group_size": 64
677
+ },
678
+ "model.layers.21.mlp.up_proj": {
679
+ "bits": 4,
680
+ "group_size": 64
681
+ },
682
+ "model.layers.22.self_attn.q_proj": {
683
+ "bits": 4,
684
+ "group_size": 64
685
+ },
686
+ "model.layers.22.self_attn.k_proj": {
687
+ "bits": 4,
688
+ "group_size": 64
689
+ },
690
+ "model.layers.22.self_attn.v_proj": {
691
+ "bits": 4,
692
+ "group_size": 64
693
+ },
694
+ "model.layers.22.self_attn.o_proj": {
695
+ "bits": 4,
696
+ "group_size": 64
697
+ },
698
+ "model.layers.22.mlp.gate_proj": {
699
+ "bits": 4,
700
+ "group_size": 64
701
+ },
702
+ "model.layers.22.mlp.down_proj": {
703
+ "bits": 4,
704
+ "group_size": 64
705
+ },
706
+ "model.layers.22.mlp.up_proj": {
707
+ "bits": 4,
708
+ "group_size": 64
709
+ },
710
+ "model.layers.23.self_attn.q_proj": {
711
+ "bits": 4,
712
+ "group_size": 64
713
+ },
714
+ "model.layers.23.self_attn.k_proj": {
715
+ "bits": 4,
716
+ "group_size": 64
717
+ },
718
+ "model.layers.23.self_attn.v_proj": {
719
+ "bits": 4,
720
+ "group_size": 64
721
+ },
722
+ "model.layers.23.self_attn.o_proj": {
723
+ "bits": 4,
724
+ "group_size": 64
725
+ },
726
+ "model.layers.23.mlp.gate_proj": {
727
+ "bits": 4,
728
+ "group_size": 64
729
+ },
730
+ "model.layers.23.mlp.down_proj": {
731
+ "bits": 4,
732
+ "group_size": 64
733
+ },
734
+ "model.layers.23.mlp.up_proj": {
735
+ "bits": 4,
736
+ "group_size": 64
737
+ },
738
+ "model.layers.24.self_attn.q_proj": {
739
+ "bits": 4,
740
+ "group_size": 64
741
+ },
742
+ "model.layers.24.self_attn.k_proj": {
743
+ "bits": 4,
744
+ "group_size": 64
745
+ },
746
+ "model.layers.24.self_attn.v_proj": {
747
+ "bits": 4,
748
+ "group_size": 64
749
+ },
750
+ "model.layers.24.self_attn.o_proj": {
751
+ "bits": 4,
752
+ "group_size": 64
753
+ },
754
+ "model.layers.24.mlp.gate_proj": {
755
+ "bits": 4,
756
+ "group_size": 64
757
+ },
758
+ "model.layers.24.mlp.down_proj": {
759
+ "bits": 4,
760
+ "group_size": 64
761
+ },
762
+ "model.layers.24.mlp.up_proj": {
763
+ "bits": 4,
764
+ "group_size": 64
765
+ },
766
+ "model.layers.25.self_attn.q_proj": {
767
+ "bits": 4,
768
+ "group_size": 64
769
+ },
770
+ "model.layers.25.self_attn.k_proj": {
771
+ "bits": 4,
772
+ "group_size": 64
773
+ },
774
+ "model.layers.25.self_attn.v_proj": {
775
+ "bits": 4,
776
+ "group_size": 64
777
+ },
778
+ "model.layers.25.self_attn.o_proj": {
779
+ "bits": 4,
780
+ "group_size": 64
781
+ },
782
+ "model.layers.25.mlp.gate_proj": {
783
+ "bits": 4,
784
+ "group_size": 64
785
+ },
786
+ "model.layers.25.mlp.down_proj": {
787
+ "bits": 4,
788
+ "group_size": 64
789
+ },
790
+ "model.layers.25.mlp.up_proj": {
791
+ "bits": 4,
792
+ "group_size": 64
793
+ },
794
+ "model.layers.26.self_attn.q_proj": {
795
+ "bits": 4,
796
+ "group_size": 64
797
+ },
798
+ "model.layers.26.self_attn.k_proj": {
799
+ "bits": 4,
800
+ "group_size": 64
801
+ },
802
+ "model.layers.26.self_attn.v_proj": {
803
+ "bits": 4,
804
+ "group_size": 64
805
+ },
806
+ "model.layers.26.self_attn.o_proj": {
807
+ "bits": 4,
808
+ "group_size": 64
809
+ },
810
+ "model.layers.26.mlp.gate_proj": {
811
+ "bits": 4,
812
+ "group_size": 64
813
+ },
814
+ "model.layers.26.mlp.down_proj": {
815
+ "bits": 4,
816
+ "group_size": 64
817
+ },
818
+ "model.layers.26.mlp.up_proj": {
819
+ "bits": 4,
820
+ "group_size": 64
821
+ },
822
+ "model.layers.27.self_attn.q_proj": {
823
+ "bits": 4,
824
+ "group_size": 64
825
+ },
826
+ "model.layers.27.self_attn.k_proj": {
827
+ "bits": 4,
828
+ "group_size": 64
829
+ },
830
+ "model.layers.27.self_attn.v_proj": {
831
+ "bits": 4,
832
+ "group_size": 64
833
+ },
834
+ "model.layers.27.self_attn.o_proj": {
835
+ "bits": 4,
836
+ "group_size": 64
837
+ },
838
+ "model.layers.27.mlp.gate_proj": {
839
+ "bits": 4,
840
+ "group_size": 64
841
+ },
842
+ "model.layers.27.mlp.down_proj": {
843
+ "bits": 4,
844
+ "group_size": 64
845
+ },
846
+ "model.layers.27.mlp.up_proj": {
847
+ "bits": 4,
848
+ "group_size": 64
849
+ },
850
+ "model.layers.28.self_attn.q_proj": {
851
+ "bits": 4,
852
+ "group_size": 64
853
+ },
854
+ "model.layers.28.self_attn.k_proj": {
855
+ "bits": 4,
856
+ "group_size": 64
857
+ },
858
+ "model.layers.28.self_attn.v_proj": {
859
+ "bits": 4,
860
+ "group_size": 64
861
+ },
862
+ "model.layers.28.self_attn.o_proj": {
863
+ "bits": 4,
864
+ "group_size": 64
865
+ },
866
+ "model.layers.28.mlp.gate_proj": {
867
+ "bits": 4,
868
+ "group_size": 64
869
+ },
870
+ "model.layers.28.mlp.down_proj": {
871
+ "bits": 4,
872
+ "group_size": 64
873
+ },
874
+ "model.layers.28.mlp.up_proj": {
875
+ "bits": 4,
876
+ "group_size": 64
877
+ },
878
+ "model.layers.29.self_attn.q_proj": {
879
+ "bits": 4,
880
+ "group_size": 64
881
+ },
882
+ "model.layers.29.self_attn.k_proj": {
883
+ "bits": 4,
884
+ "group_size": 64
885
+ },
886
+ "model.layers.29.self_attn.v_proj": {
887
+ "bits": 4,
888
+ "group_size": 64
889
+ },
890
+ "model.layers.29.self_attn.o_proj": {
891
+ "bits": 4,
892
+ "group_size": 64
893
+ },
894
+ "model.layers.29.mlp.gate_proj": {
895
+ "bits": 4,
896
+ "group_size": 64
897
+ },
898
+ "model.layers.29.mlp.down_proj": {
899
+ "bits": 4,
900
+ "group_size": 64
901
+ },
902
+ "model.layers.29.mlp.up_proj": {
903
+ "bits": 4,
904
+ "group_size": 64
905
+ },
906
+ "model.layers.30.self_attn.q_proj": {
907
+ "bits": 4,
908
+ "group_size": 64
909
+ },
910
+ "model.layers.30.self_attn.k_proj": {
911
+ "bits": 4,
912
+ "group_size": 64
913
+ },
914
+ "model.layers.30.self_attn.v_proj": {
915
+ "bits": 4,
916
+ "group_size": 64
917
+ },
918
+ "model.layers.30.self_attn.o_proj": {
919
+ "bits": 4,
920
+ "group_size": 64
921
+ },
922
+ "model.layers.30.mlp.gate_proj": {
923
+ "bits": 4,
924
+ "group_size": 64
925
+ },
926
+ "model.layers.30.mlp.down_proj": {
927
+ "bits": 4,
928
+ "group_size": 64
929
+ },
930
+ "model.layers.30.mlp.up_proj": {
931
+ "bits": 4,
932
+ "group_size": 64
933
+ },
934
+ "model.layers.31.self_attn.q_proj": {
935
+ "bits": 4,
936
+ "group_size": 64
937
+ },
938
+ "model.layers.31.self_attn.k_proj": {
939
+ "bits": 4,
940
+ "group_size": 64
941
+ },
942
+ "model.layers.31.self_attn.v_proj": {
943
+ "bits": 4,
944
+ "group_size": 64
945
+ },
946
+ "model.layers.31.self_attn.o_proj": {
947
+ "bits": 4,
948
+ "group_size": 64
949
+ },
950
+ "model.layers.31.mlp.gate_proj": {
951
+ "bits": 4,
952
+ "group_size": 64
953
+ },
954
+ "model.layers.31.mlp.down_proj": {
955
+ "bits": 4,
956
+ "group_size": 64
957
+ },
958
+ "model.layers.31.mlp.up_proj": {
959
+ "bits": 4,
960
+ "group_size": 64
961
+ },
962
+ "model.layers.32.self_attn.q_proj": {
963
+ "bits": 4,
964
+ "group_size": 64
965
+ },
966
+ "model.layers.32.self_attn.k_proj": {
967
+ "bits": 4,
968
+ "group_size": 64
969
+ },
970
+ "model.layers.32.self_attn.v_proj": {
971
+ "bits": 4,
972
+ "group_size": 64
973
+ },
974
+ "model.layers.32.self_attn.o_proj": {
975
+ "bits": 4,
976
+ "group_size": 64
977
+ },
978
+ "model.layers.32.mlp.gate_proj": {
979
+ "bits": 4,
980
+ "group_size": 64
981
+ },
982
+ "model.layers.32.mlp.down_proj": {
983
+ "bits": 4,
984
+ "group_size": 64
985
+ },
986
+ "model.layers.32.mlp.up_proj": {
987
+ "bits": 4,
988
+ "group_size": 64
989
+ },
990
+ "model.layers.33.self_attn.q_proj": {
991
+ "bits": 4,
992
+ "group_size": 64
993
+ },
994
+ "model.layers.33.self_attn.k_proj": {
995
+ "bits": 4,
996
+ "group_size": 64
997
+ },
998
+ "model.layers.33.self_attn.v_proj": {
999
+ "bits": 4,
1000
+ "group_size": 64
1001
+ },
1002
+ "model.layers.33.self_attn.o_proj": {
1003
+ "bits": 4,
1004
+ "group_size": 64
1005
+ },
1006
+ "model.layers.33.mlp.gate_proj": {
1007
+ "bits": 4,
1008
+ "group_size": 64
1009
+ },
1010
+ "model.layers.33.mlp.down_proj": {
1011
+ "bits": 4,
1012
+ "group_size": 64
1013
+ },
1014
+ "model.layers.33.mlp.up_proj": {
1015
+ "bits": 4,
1016
+ "group_size": 64
1017
+ },
1018
+ "model.layers.34.self_attn.q_proj": {
1019
+ "bits": 4,
1020
+ "group_size": 64
1021
+ },
1022
+ "model.layers.34.self_attn.k_proj": {
1023
+ "bits": 4,
1024
+ "group_size": 64
1025
+ },
1026
+ "model.layers.34.self_attn.v_proj": {
1027
+ "bits": 4,
1028
+ "group_size": 64
1029
+ },
1030
+ "model.layers.34.self_attn.o_proj": {
1031
+ "bits": 4,
1032
+ "group_size": 64
1033
+ },
1034
+ "model.layers.34.mlp.gate_proj": {
1035
+ "bits": 4,
1036
+ "group_size": 64
1037
+ },
1038
+ "model.layers.34.mlp.down_proj": {
1039
+ "bits": 4,
1040
+ "group_size": 64
1041
+ },
1042
+ "model.layers.34.mlp.up_proj": {
1043
+ "bits": 4,
1044
+ "group_size": 64
1045
+ },
1046
+ "model.layers.35.self_attn.q_proj": {
1047
+ "bits": 4,
1048
+ "group_size": 64
1049
+ },
1050
+ "model.layers.35.self_attn.k_proj": {
1051
+ "bits": 4,
1052
+ "group_size": 64
1053
+ },
1054
+ "model.layers.35.self_attn.v_proj": {
1055
+ "bits": 4,
1056
+ "group_size": 64
1057
+ },
1058
+ "model.layers.35.self_attn.o_proj": {
1059
+ "bits": 4,
1060
+ "group_size": 64
1061
+ },
1062
+ "model.layers.35.mlp.gate_proj": {
1063
+ "bits": 4,
1064
+ "group_size": 64
1065
+ },
1066
+ "model.layers.35.mlp.down_proj": {
1067
+ "bits": 4,
1068
+ "group_size": 64
1069
+ },
1070
+ "model.layers.35.mlp.up_proj": {
1071
+ "bits": 4,
1072
+ "group_size": 64
1073
+ },
1074
+ "lm_head": {
1075
+ "bits": 6,
1076
+ "group_size": 64
1077
+ }
1078
+ },
1079
+ "quantization_config": {
1080
+ "group_size": 64,
1081
+ "bits": 4,
1082
+ "mode": "affine",
1083
+ "model.embed_tokens": {
1084
+ "bits": 6,
1085
+ "group_size": 64
1086
+ },
1087
+ "model.layers.0.self_attn.q_proj": {
1088
+ "bits": 4,
1089
+ "group_size": 64
1090
+ },
1091
+ "model.layers.0.self_attn.k_proj": {
1092
+ "bits": 4,
1093
+ "group_size": 64
1094
+ },
1095
+ "model.layers.0.self_attn.v_proj": {
1096
+ "bits": 4,
1097
+ "group_size": 64
1098
+ },
1099
+ "model.layers.0.self_attn.o_proj": {
1100
+ "bits": 4,
1101
+ "group_size": 64
1102
+ },
1103
+ "model.layers.0.mlp.gate_proj": {
1104
+ "bits": 4,
1105
+ "group_size": 64
1106
+ },
1107
+ "model.layers.0.mlp.down_proj": {
1108
+ "bits": 4,
1109
+ "group_size": 64
1110
+ },
1111
+ "model.layers.0.mlp.up_proj": {
1112
+ "bits": 4,
1113
+ "group_size": 64
1114
+ },
1115
+ "model.layers.1.self_attn.q_proj": {
1116
+ "bits": 4,
1117
+ "group_size": 64
1118
+ },
1119
+ "model.layers.1.self_attn.k_proj": {
1120
+ "bits": 4,
1121
+ "group_size": 64
1122
+ },
1123
+ "model.layers.1.self_attn.v_proj": {
1124
+ "bits": 4,
1125
+ "group_size": 64
1126
+ },
1127
+ "model.layers.1.self_attn.o_proj": {
1128
+ "bits": 4,
1129
+ "group_size": 64
1130
+ },
1131
+ "model.layers.1.mlp.gate_proj": {
1132
+ "bits": 4,
1133
+ "group_size": 64
1134
+ },
1135
+ "model.layers.1.mlp.down_proj": {
1136
+ "bits": 4,
1137
+ "group_size": 64
1138
+ },
1139
+ "model.layers.1.mlp.up_proj": {
1140
+ "bits": 4,
1141
+ "group_size": 64
1142
+ },
1143
+ "model.layers.2.self_attn.q_proj": {
1144
+ "bits": 4,
1145
+ "group_size": 64
1146
+ },
1147
+ "model.layers.2.self_attn.k_proj": {
1148
+ "bits": 4,
1149
+ "group_size": 64
1150
+ },
1151
+ "model.layers.2.self_attn.v_proj": {
1152
+ "bits": 4,
1153
+ "group_size": 64
1154
+ },
1155
+ "model.layers.2.self_attn.o_proj": {
1156
+ "bits": 4,
1157
+ "group_size": 64
1158
+ },
1159
+ "model.layers.2.mlp.gate_proj": {
1160
+ "bits": 4,
1161
+ "group_size": 64
1162
+ },
1163
+ "model.layers.2.mlp.down_proj": {
1164
+ "bits": 4,
1165
+ "group_size": 64
1166
+ },
1167
+ "model.layers.2.mlp.up_proj": {
1168
+ "bits": 4,
1169
+ "group_size": 64
1170
+ },
1171
+ "model.layers.3.self_attn.q_proj": {
1172
+ "bits": 4,
1173
+ "group_size": 64
1174
+ },
1175
+ "model.layers.3.self_attn.k_proj": {
1176
+ "bits": 4,
1177
+ "group_size": 64
1178
+ },
1179
+ "model.layers.3.self_attn.v_proj": {
1180
+ "bits": 4,
1181
+ "group_size": 64
1182
+ },
1183
+ "model.layers.3.self_attn.o_proj": {
1184
+ "bits": 4,
1185
+ "group_size": 64
1186
+ },
1187
+ "model.layers.3.mlp.gate_proj": {
1188
+ "bits": 4,
1189
+ "group_size": 64
1190
+ },
1191
+ "model.layers.3.mlp.down_proj": {
1192
+ "bits": 4,
1193
+ "group_size": 64
1194
+ },
1195
+ "model.layers.3.mlp.up_proj": {
1196
+ "bits": 4,
1197
+ "group_size": 64
1198
+ },
1199
+ "model.layers.4.self_attn.q_proj": {
1200
+ "bits": 4,
1201
+ "group_size": 64
1202
+ },
1203
+ "model.layers.4.self_attn.k_proj": {
1204
+ "bits": 4,
1205
+ "group_size": 64
1206
+ },
1207
+ "model.layers.4.self_attn.v_proj": {
1208
+ "bits": 4,
1209
+ "group_size": 64
1210
+ },
1211
+ "model.layers.4.self_attn.o_proj": {
1212
+ "bits": 4,
1213
+ "group_size": 64
1214
+ },
1215
+ "model.layers.4.mlp.gate_proj": {
1216
+ "bits": 4,
1217
+ "group_size": 64
1218
+ },
1219
+ "model.layers.4.mlp.down_proj": {
1220
+ "bits": 4,
1221
+ "group_size": 64
1222
+ },
1223
+ "model.layers.4.mlp.up_proj": {
1224
+ "bits": 4,
1225
+ "group_size": 64
1226
+ },
1227
+ "model.layers.5.self_attn.q_proj": {
1228
+ "bits": 4,
1229
+ "group_size": 64
1230
+ },
1231
+ "model.layers.5.self_attn.k_proj": {
1232
+ "bits": 4,
1233
+ "group_size": 64
1234
+ },
1235
+ "model.layers.5.self_attn.v_proj": {
1236
+ "bits": 4,
1237
+ "group_size": 64
1238
+ },
1239
+ "model.layers.5.self_attn.o_proj": {
1240
+ "bits": 4,
1241
+ "group_size": 64
1242
+ },
1243
+ "model.layers.5.mlp.gate_proj": {
1244
+ "bits": 4,
1245
+ "group_size": 64
1246
+ },
1247
+ "model.layers.5.mlp.down_proj": {
1248
+ "bits": 4,
1249
+ "group_size": 64
1250
+ },
1251
+ "model.layers.5.mlp.up_proj": {
1252
+ "bits": 4,
1253
+ "group_size": 64
1254
+ },
1255
+ "model.layers.6.self_attn.q_proj": {
1256
+ "bits": 4,
1257
+ "group_size": 64
1258
+ },
1259
+ "model.layers.6.self_attn.k_proj": {
1260
+ "bits": 4,
1261
+ "group_size": 64
1262
+ },
1263
+ "model.layers.6.self_attn.v_proj": {
1264
+ "bits": 4,
1265
+ "group_size": 64
1266
+ },
1267
+ "model.layers.6.self_attn.o_proj": {
1268
+ "bits": 4,
1269
+ "group_size": 64
1270
+ },
1271
+ "model.layers.6.mlp.gate_proj": {
1272
+ "bits": 4,
1273
+ "group_size": 64
1274
+ },
1275
+ "model.layers.6.mlp.down_proj": {
1276
+ "bits": 4,
1277
+ "group_size": 64
1278
+ },
1279
+ "model.layers.6.mlp.up_proj": {
1280
+ "bits": 4,
1281
+ "group_size": 64
1282
+ },
1283
+ "model.layers.7.self_attn.q_proj": {
1284
+ "bits": 4,
1285
+ "group_size": 64
1286
+ },
1287
+ "model.layers.7.self_attn.k_proj": {
1288
+ "bits": 4,
1289
+ "group_size": 64
1290
+ },
1291
+ "model.layers.7.self_attn.v_proj": {
1292
+ "bits": 4,
1293
+ "group_size": 64
1294
+ },
1295
+ "model.layers.7.self_attn.o_proj": {
1296
+ "bits": 4,
1297
+ "group_size": 64
1298
+ },
1299
+ "model.layers.7.mlp.gate_proj": {
1300
+ "bits": 4,
1301
+ "group_size": 64
1302
+ },
1303
+ "model.layers.7.mlp.down_proj": {
1304
+ "bits": 4,
1305
+ "group_size": 64
1306
+ },
1307
+ "model.layers.7.mlp.up_proj": {
1308
+ "bits": 4,
1309
+ "group_size": 64
1310
+ },
1311
+ "model.layers.8.self_attn.q_proj": {
1312
+ "bits": 4,
1313
+ "group_size": 64
1314
+ },
1315
+ "model.layers.8.self_attn.k_proj": {
1316
+ "bits": 4,
1317
+ "group_size": 64
1318
+ },
1319
+ "model.layers.8.self_attn.v_proj": {
1320
+ "bits": 4,
1321
+ "group_size": 64
1322
+ },
1323
+ "model.layers.8.self_attn.o_proj": {
1324
+ "bits": 4,
1325
+ "group_size": 64
1326
+ },
1327
+ "model.layers.8.mlp.gate_proj": {
1328
+ "bits": 4,
1329
+ "group_size": 64
1330
+ },
1331
+ "model.layers.8.mlp.down_proj": {
1332
+ "bits": 4,
1333
+ "group_size": 64
1334
+ },
1335
+ "model.layers.8.mlp.up_proj": {
1336
+ "bits": 4,
1337
+ "group_size": 64
1338
+ },
1339
+ "model.layers.9.self_attn.q_proj": {
1340
+ "bits": 4,
1341
+ "group_size": 64
1342
+ },
1343
+ "model.layers.9.self_attn.k_proj": {
1344
+ "bits": 4,
1345
+ "group_size": 64
1346
+ },
1347
+ "model.layers.9.self_attn.v_proj": {
1348
+ "bits": 4,
1349
+ "group_size": 64
1350
+ },
1351
+ "model.layers.9.self_attn.o_proj": {
1352
+ "bits": 4,
1353
+ "group_size": 64
1354
+ },
1355
+ "model.layers.9.mlp.gate_proj": {
1356
+ "bits": 4,
1357
+ "group_size": 64
1358
+ },
1359
+ "model.layers.9.mlp.down_proj": {
1360
+ "bits": 4,
1361
+ "group_size": 64
1362
+ },
1363
+ "model.layers.9.mlp.up_proj": {
1364
+ "bits": 4,
1365
+ "group_size": 64
1366
+ },
1367
+ "model.layers.10.self_attn.q_proj": {
1368
+ "bits": 4,
1369
+ "group_size": 64
1370
+ },
1371
+ "model.layers.10.self_attn.k_proj": {
1372
+ "bits": 4,
1373
+ "group_size": 64
1374
+ },
1375
+ "model.layers.10.self_attn.v_proj": {
1376
+ "bits": 4,
1377
+ "group_size": 64
1378
+ },
1379
+ "model.layers.10.self_attn.o_proj": {
1380
+ "bits": 4,
1381
+ "group_size": 64
1382
+ },
1383
+ "model.layers.10.mlp.gate_proj": {
1384
+ "bits": 4,
1385
+ "group_size": 64
1386
+ },
1387
+ "model.layers.10.mlp.down_proj": {
1388
+ "bits": 4,
1389
+ "group_size": 64
1390
+ },
1391
+ "model.layers.10.mlp.up_proj": {
1392
+ "bits": 4,
1393
+ "group_size": 64
1394
+ },
1395
+ "model.layers.11.self_attn.q_proj": {
1396
+ "bits": 4,
1397
+ "group_size": 64
1398
+ },
1399
+ "model.layers.11.self_attn.k_proj": {
1400
+ "bits": 4,
1401
+ "group_size": 64
1402
+ },
1403
+ "model.layers.11.self_attn.v_proj": {
1404
+ "bits": 4,
1405
+ "group_size": 64
1406
+ },
1407
+ "model.layers.11.self_attn.o_proj": {
1408
+ "bits": 4,
1409
+ "group_size": 64
1410
+ },
1411
+ "model.layers.11.mlp.gate_proj": {
1412
+ "bits": 4,
1413
+ "group_size": 64
1414
+ },
1415
+ "model.layers.11.mlp.down_proj": {
1416
+ "bits": 4,
1417
+ "group_size": 64
1418
+ },
1419
+ "model.layers.11.mlp.up_proj": {
1420
+ "bits": 4,
1421
+ "group_size": 64
1422
+ },
1423
+ "model.layers.12.self_attn.q_proj": {
1424
+ "bits": 4,
1425
+ "group_size": 64
1426
+ },
1427
+ "model.layers.12.self_attn.k_proj": {
1428
+ "bits": 4,
1429
+ "group_size": 64
1430
+ },
1431
+ "model.layers.12.self_attn.v_proj": {
1432
+ "bits": 4,
1433
+ "group_size": 64
1434
+ },
1435
+ "model.layers.12.self_attn.o_proj": {
1436
+ "bits": 4,
1437
+ "group_size": 64
1438
+ },
1439
+ "model.layers.12.mlp.gate_proj": {
1440
+ "bits": 4,
1441
+ "group_size": 64
1442
+ },
1443
+ "model.layers.12.mlp.down_proj": {
1444
+ "bits": 4,
1445
+ "group_size": 64
1446
+ },
1447
+ "model.layers.12.mlp.up_proj": {
1448
+ "bits": 4,
1449
+ "group_size": 64
1450
+ },
1451
+ "model.layers.13.self_attn.q_proj": {
1452
+ "bits": 4,
1453
+ "group_size": 64
1454
+ },
1455
+ "model.layers.13.self_attn.k_proj": {
1456
+ "bits": 4,
1457
+ "group_size": 64
1458
+ },
1459
+ "model.layers.13.self_attn.v_proj": {
1460
+ "bits": 4,
1461
+ "group_size": 64
1462
+ },
1463
+ "model.layers.13.self_attn.o_proj": {
1464
+ "bits": 4,
1465
+ "group_size": 64
1466
+ },
1467
+ "model.layers.13.mlp.gate_proj": {
1468
+ "bits": 4,
1469
+ "group_size": 64
1470
+ },
1471
+ "model.layers.13.mlp.down_proj": {
1472
+ "bits": 4,
1473
+ "group_size": 64
1474
+ },
1475
+ "model.layers.13.mlp.up_proj": {
1476
+ "bits": 4,
1477
+ "group_size": 64
1478
+ },
1479
+ "model.layers.14.self_attn.q_proj": {
1480
+ "bits": 4,
1481
+ "group_size": 64
1482
+ },
1483
+ "model.layers.14.self_attn.k_proj": {
1484
+ "bits": 4,
1485
+ "group_size": 64
1486
+ },
1487
+ "model.layers.14.self_attn.v_proj": {
1488
+ "bits": 4,
1489
+ "group_size": 64
1490
+ },
1491
+ "model.layers.14.self_attn.o_proj": {
1492
+ "bits": 4,
1493
+ "group_size": 64
1494
+ },
1495
+ "model.layers.14.mlp.gate_proj": {
1496
+ "bits": 4,
1497
+ "group_size": 64
1498
+ },
1499
+ "model.layers.14.mlp.down_proj": {
1500
+ "bits": 4,
1501
+ "group_size": 64
1502
+ },
1503
+ "model.layers.14.mlp.up_proj": {
1504
+ "bits": 4,
1505
+ "group_size": 64
1506
+ },
1507
+ "model.layers.15.self_attn.q_proj": {
1508
+ "bits": 4,
1509
+ "group_size": 64
1510
+ },
1511
+ "model.layers.15.self_attn.k_proj": {
1512
+ "bits": 4,
1513
+ "group_size": 64
1514
+ },
1515
+ "model.layers.15.self_attn.v_proj": {
1516
+ "bits": 4,
1517
+ "group_size": 64
1518
+ },
1519
+ "model.layers.15.self_attn.o_proj": {
1520
+ "bits": 4,
1521
+ "group_size": 64
1522
+ },
1523
+ "model.layers.15.mlp.gate_proj": {
1524
+ "bits": 4,
1525
+ "group_size": 64
1526
+ },
1527
+ "model.layers.15.mlp.down_proj": {
1528
+ "bits": 4,
1529
+ "group_size": 64
1530
+ },
1531
+ "model.layers.15.mlp.up_proj": {
1532
+ "bits": 4,
1533
+ "group_size": 64
1534
+ },
1535
+ "model.layers.16.self_attn.q_proj": {
1536
+ "bits": 4,
1537
+ "group_size": 64
1538
+ },
1539
+ "model.layers.16.self_attn.k_proj": {
1540
+ "bits": 4,
1541
+ "group_size": 64
1542
+ },
1543
+ "model.layers.16.self_attn.v_proj": {
1544
+ "bits": 4,
1545
+ "group_size": 64
1546
+ },
1547
+ "model.layers.16.self_attn.o_proj": {
1548
+ "bits": 4,
1549
+ "group_size": 64
1550
+ },
1551
+ "model.layers.16.mlp.gate_proj": {
1552
+ "bits": 4,
1553
+ "group_size": 64
1554
+ },
1555
+ "model.layers.16.mlp.down_proj": {
1556
+ "bits": 4,
1557
+ "group_size": 64
1558
+ },
1559
+ "model.layers.16.mlp.up_proj": {
1560
+ "bits": 4,
1561
+ "group_size": 64
1562
+ },
1563
+ "model.layers.17.self_attn.q_proj": {
1564
+ "bits": 4,
1565
+ "group_size": 64
1566
+ },
1567
+ "model.layers.17.self_attn.k_proj": {
1568
+ "bits": 4,
1569
+ "group_size": 64
1570
+ },
1571
+ "model.layers.17.self_attn.v_proj": {
1572
+ "bits": 4,
1573
+ "group_size": 64
1574
+ },
1575
+ "model.layers.17.self_attn.o_proj": {
1576
+ "bits": 4,
1577
+ "group_size": 64
1578
+ },
1579
+ "model.layers.17.mlp.gate_proj": {
1580
+ "bits": 4,
1581
+ "group_size": 64
1582
+ },
1583
+ "model.layers.17.mlp.down_proj": {
1584
+ "bits": 4,
1585
+ "group_size": 64
1586
+ },
1587
+ "model.layers.17.mlp.up_proj": {
1588
+ "bits": 4,
1589
+ "group_size": 64
1590
+ },
1591
+ "model.layers.18.self_attn.q_proj": {
1592
+ "bits": 4,
1593
+ "group_size": 64
1594
+ },
1595
+ "model.layers.18.self_attn.k_proj": {
1596
+ "bits": 4,
1597
+ "group_size": 64
1598
+ },
1599
+ "model.layers.18.self_attn.v_proj": {
1600
+ "bits": 4,
1601
+ "group_size": 64
1602
+ },
1603
+ "model.layers.18.self_attn.o_proj": {
1604
+ "bits": 4,
1605
+ "group_size": 64
1606
+ },
1607
+ "model.layers.18.mlp.gate_proj": {
1608
+ "bits": 4,
1609
+ "group_size": 64
1610
+ },
1611
+ "model.layers.18.mlp.down_proj": {
1612
+ "bits": 4,
1613
+ "group_size": 64
1614
+ },
1615
+ "model.layers.18.mlp.up_proj": {
1616
+ "bits": 4,
1617
+ "group_size": 64
1618
+ },
1619
+ "model.layers.19.self_attn.q_proj": {
1620
+ "bits": 4,
1621
+ "group_size": 64
1622
+ },
1623
+ "model.layers.19.self_attn.k_proj": {
1624
+ "bits": 4,
1625
+ "group_size": 64
1626
+ },
1627
+ "model.layers.19.self_attn.v_proj": {
1628
+ "bits": 4,
1629
+ "group_size": 64
1630
+ },
1631
+ "model.layers.19.self_attn.o_proj": {
1632
+ "bits": 4,
1633
+ "group_size": 64
1634
+ },
1635
+ "model.layers.19.mlp.gate_proj": {
1636
+ "bits": 4,
1637
+ "group_size": 64
1638
+ },
1639
+ "model.layers.19.mlp.down_proj": {
1640
+ "bits": 4,
1641
+ "group_size": 64
1642
+ },
1643
+ "model.layers.19.mlp.up_proj": {
1644
+ "bits": 4,
1645
+ "group_size": 64
1646
+ },
1647
+ "model.layers.20.self_attn.q_proj": {
1648
+ "bits": 4,
1649
+ "group_size": 64
1650
+ },
1651
+ "model.layers.20.self_attn.k_proj": {
1652
+ "bits": 4,
1653
+ "group_size": 64
1654
+ },
1655
+ "model.layers.20.self_attn.v_proj": {
1656
+ "bits": 4,
1657
+ "group_size": 64
1658
+ },
1659
+ "model.layers.20.self_attn.o_proj": {
1660
+ "bits": 4,
1661
+ "group_size": 64
1662
+ },
1663
+ "model.layers.20.mlp.gate_proj": {
1664
+ "bits": 4,
1665
+ "group_size": 64
1666
+ },
1667
+ "model.layers.20.mlp.down_proj": {
1668
+ "bits": 4,
1669
+ "group_size": 64
1670
+ },
1671
+ "model.layers.20.mlp.up_proj": {
1672
+ "bits": 4,
1673
+ "group_size": 64
1674
+ },
1675
+ "model.layers.21.self_attn.q_proj": {
1676
+ "bits": 4,
1677
+ "group_size": 64
1678
+ },
1679
+ "model.layers.21.self_attn.k_proj": {
1680
+ "bits": 4,
1681
+ "group_size": 64
1682
+ },
1683
+ "model.layers.21.self_attn.v_proj": {
1684
+ "bits": 4,
1685
+ "group_size": 64
1686
+ },
1687
+ "model.layers.21.self_attn.o_proj": {
1688
+ "bits": 4,
1689
+ "group_size": 64
1690
+ },
1691
+ "model.layers.21.mlp.gate_proj": {
1692
+ "bits": 4,
1693
+ "group_size": 64
1694
+ },
1695
+ "model.layers.21.mlp.down_proj": {
1696
+ "bits": 4,
1697
+ "group_size": 64
1698
+ },
1699
+ "model.layers.21.mlp.up_proj": {
1700
+ "bits": 4,
1701
+ "group_size": 64
1702
+ },
1703
+ "model.layers.22.self_attn.q_proj": {
1704
+ "bits": 4,
1705
+ "group_size": 64
1706
+ },
1707
+ "model.layers.22.self_attn.k_proj": {
1708
+ "bits": 4,
1709
+ "group_size": 64
1710
+ },
1711
+ "model.layers.22.self_attn.v_proj": {
1712
+ "bits": 4,
1713
+ "group_size": 64
1714
+ },
1715
+ "model.layers.22.self_attn.o_proj": {
1716
+ "bits": 4,
1717
+ "group_size": 64
1718
+ },
1719
+ "model.layers.22.mlp.gate_proj": {
1720
+ "bits": 4,
1721
+ "group_size": 64
1722
+ },
1723
+ "model.layers.22.mlp.down_proj": {
1724
+ "bits": 4,
1725
+ "group_size": 64
1726
+ },
1727
+ "model.layers.22.mlp.up_proj": {
1728
+ "bits": 4,
1729
+ "group_size": 64
1730
+ },
1731
+ "model.layers.23.self_attn.q_proj": {
1732
+ "bits": 4,
1733
+ "group_size": 64
1734
+ },
1735
+ "model.layers.23.self_attn.k_proj": {
1736
+ "bits": 4,
1737
+ "group_size": 64
1738
+ },
1739
+ "model.layers.23.self_attn.v_proj": {
1740
+ "bits": 4,
1741
+ "group_size": 64
1742
+ },
1743
+ "model.layers.23.self_attn.o_proj": {
1744
+ "bits": 4,
1745
+ "group_size": 64
1746
+ },
1747
+ "model.layers.23.mlp.gate_proj": {
1748
+ "bits": 4,
1749
+ "group_size": 64
1750
+ },
1751
+ "model.layers.23.mlp.down_proj": {
1752
+ "bits": 4,
1753
+ "group_size": 64
1754
+ },
1755
+ "model.layers.23.mlp.up_proj": {
1756
+ "bits": 4,
1757
+ "group_size": 64
1758
+ },
1759
+ "model.layers.24.self_attn.q_proj": {
1760
+ "bits": 4,
1761
+ "group_size": 64
1762
+ },
1763
+ "model.layers.24.self_attn.k_proj": {
1764
+ "bits": 4,
1765
+ "group_size": 64
1766
+ },
1767
+ "model.layers.24.self_attn.v_proj": {
1768
+ "bits": 4,
1769
+ "group_size": 64
1770
+ },
1771
+ "model.layers.24.self_attn.o_proj": {
1772
+ "bits": 4,
1773
+ "group_size": 64
1774
+ },
1775
+ "model.layers.24.mlp.gate_proj": {
1776
+ "bits": 4,
1777
+ "group_size": 64
1778
+ },
1779
+ "model.layers.24.mlp.down_proj": {
1780
+ "bits": 4,
1781
+ "group_size": 64
1782
+ },
1783
+ "model.layers.24.mlp.up_proj": {
1784
+ "bits": 4,
1785
+ "group_size": 64
1786
+ },
1787
+ "model.layers.25.self_attn.q_proj": {
1788
+ "bits": 4,
1789
+ "group_size": 64
1790
+ },
1791
+ "model.layers.25.self_attn.k_proj": {
1792
+ "bits": 4,
1793
+ "group_size": 64
1794
+ },
1795
+ "model.layers.25.self_attn.v_proj": {
1796
+ "bits": 4,
1797
+ "group_size": 64
1798
+ },
1799
+ "model.layers.25.self_attn.o_proj": {
1800
+ "bits": 4,
1801
+ "group_size": 64
1802
+ },
1803
+ "model.layers.25.mlp.gate_proj": {
1804
+ "bits": 4,
1805
+ "group_size": 64
1806
+ },
1807
+ "model.layers.25.mlp.down_proj": {
1808
+ "bits": 4,
1809
+ "group_size": 64
1810
+ },
1811
+ "model.layers.25.mlp.up_proj": {
1812
+ "bits": 4,
1813
+ "group_size": 64
1814
+ },
1815
+ "model.layers.26.self_attn.q_proj": {
1816
+ "bits": 4,
1817
+ "group_size": 64
1818
+ },
1819
+ "model.layers.26.self_attn.k_proj": {
1820
+ "bits": 4,
1821
+ "group_size": 64
1822
+ },
1823
+ "model.layers.26.self_attn.v_proj": {
1824
+ "bits": 4,
1825
+ "group_size": 64
1826
+ },
1827
+ "model.layers.26.self_attn.o_proj": {
1828
+ "bits": 4,
1829
+ "group_size": 64
1830
+ },
1831
+ "model.layers.26.mlp.gate_proj": {
1832
+ "bits": 4,
1833
+ "group_size": 64
1834
+ },
1835
+ "model.layers.26.mlp.down_proj": {
1836
+ "bits": 4,
1837
+ "group_size": 64
1838
+ },
1839
+ "model.layers.26.mlp.up_proj": {
1840
+ "bits": 4,
1841
+ "group_size": 64
1842
+ },
1843
+ "model.layers.27.self_attn.q_proj": {
1844
+ "bits": 4,
1845
+ "group_size": 64
1846
+ },
1847
+ "model.layers.27.self_attn.k_proj": {
1848
+ "bits": 4,
1849
+ "group_size": 64
1850
+ },
1851
+ "model.layers.27.self_attn.v_proj": {
1852
+ "bits": 4,
1853
+ "group_size": 64
1854
+ },
1855
+ "model.layers.27.self_attn.o_proj": {
1856
+ "bits": 4,
1857
+ "group_size": 64
1858
+ },
1859
+ "model.layers.27.mlp.gate_proj": {
1860
+ "bits": 4,
1861
+ "group_size": 64
1862
+ },
1863
+ "model.layers.27.mlp.down_proj": {
1864
+ "bits": 4,
1865
+ "group_size": 64
1866
+ },
1867
+ "model.layers.27.mlp.up_proj": {
1868
+ "bits": 4,
1869
+ "group_size": 64
1870
+ },
1871
+ "model.layers.28.self_attn.q_proj": {
1872
+ "bits": 4,
1873
+ "group_size": 64
1874
+ },
1875
+ "model.layers.28.self_attn.k_proj": {
1876
+ "bits": 4,
1877
+ "group_size": 64
1878
+ },
1879
+ "model.layers.28.self_attn.v_proj": {
1880
+ "bits": 4,
1881
+ "group_size": 64
1882
+ },
1883
+ "model.layers.28.self_attn.o_proj": {
1884
+ "bits": 4,
1885
+ "group_size": 64
1886
+ },
1887
+ "model.layers.28.mlp.gate_proj": {
1888
+ "bits": 4,
1889
+ "group_size": 64
1890
+ },
1891
+ "model.layers.28.mlp.down_proj": {
1892
+ "bits": 4,
1893
+ "group_size": 64
1894
+ },
1895
+ "model.layers.28.mlp.up_proj": {
1896
+ "bits": 4,
1897
+ "group_size": 64
1898
+ },
1899
+ "model.layers.29.self_attn.q_proj": {
1900
+ "bits": 4,
1901
+ "group_size": 64
1902
+ },
1903
+ "model.layers.29.self_attn.k_proj": {
1904
+ "bits": 4,
1905
+ "group_size": 64
1906
+ },
1907
+ "model.layers.29.self_attn.v_proj": {
1908
+ "bits": 4,
1909
+ "group_size": 64
1910
+ },
1911
+ "model.layers.29.self_attn.o_proj": {
1912
+ "bits": 4,
1913
+ "group_size": 64
1914
+ },
1915
+ "model.layers.29.mlp.gate_proj": {
1916
+ "bits": 4,
1917
+ "group_size": 64
1918
+ },
1919
+ "model.layers.29.mlp.down_proj": {
1920
+ "bits": 4,
1921
+ "group_size": 64
1922
+ },
1923
+ "model.layers.29.mlp.up_proj": {
1924
+ "bits": 4,
1925
+ "group_size": 64
1926
+ },
1927
+ "model.layers.30.self_attn.q_proj": {
1928
+ "bits": 4,
1929
+ "group_size": 64
1930
+ },
1931
+ "model.layers.30.self_attn.k_proj": {
1932
+ "bits": 4,
1933
+ "group_size": 64
1934
+ },
1935
+ "model.layers.30.self_attn.v_proj": {
1936
+ "bits": 4,
1937
+ "group_size": 64
1938
+ },
1939
+ "model.layers.30.self_attn.o_proj": {
1940
+ "bits": 4,
1941
+ "group_size": 64
1942
+ },
1943
+ "model.layers.30.mlp.gate_proj": {
1944
+ "bits": 4,
1945
+ "group_size": 64
1946
+ },
1947
+ "model.layers.30.mlp.down_proj": {
1948
+ "bits": 4,
1949
+ "group_size": 64
1950
+ },
1951
+ "model.layers.30.mlp.up_proj": {
1952
+ "bits": 4,
1953
+ "group_size": 64
1954
+ },
1955
+ "model.layers.31.self_attn.q_proj": {
1956
+ "bits": 4,
1957
+ "group_size": 64
1958
+ },
1959
+ "model.layers.31.self_attn.k_proj": {
1960
+ "bits": 4,
1961
+ "group_size": 64
1962
+ },
1963
+ "model.layers.31.self_attn.v_proj": {
1964
+ "bits": 4,
1965
+ "group_size": 64
1966
+ },
1967
+ "model.layers.31.self_attn.o_proj": {
1968
+ "bits": 4,
1969
+ "group_size": 64
1970
+ },
1971
+ "model.layers.31.mlp.gate_proj": {
1972
+ "bits": 4,
1973
+ "group_size": 64
1974
+ },
1975
+ "model.layers.31.mlp.down_proj": {
1976
+ "bits": 4,
1977
+ "group_size": 64
1978
+ },
1979
+ "model.layers.31.mlp.up_proj": {
1980
+ "bits": 4,
1981
+ "group_size": 64
1982
+ },
1983
+ "model.layers.32.self_attn.q_proj": {
1984
+ "bits": 4,
1985
+ "group_size": 64
1986
+ },
1987
+ "model.layers.32.self_attn.k_proj": {
1988
+ "bits": 4,
1989
+ "group_size": 64
1990
+ },
1991
+ "model.layers.32.self_attn.v_proj": {
1992
+ "bits": 4,
1993
+ "group_size": 64
1994
+ },
1995
+ "model.layers.32.self_attn.o_proj": {
1996
+ "bits": 4,
1997
+ "group_size": 64
1998
+ },
1999
+ "model.layers.32.mlp.gate_proj": {
2000
+ "bits": 4,
2001
+ "group_size": 64
2002
+ },
2003
+ "model.layers.32.mlp.down_proj": {
2004
+ "bits": 4,
2005
+ "group_size": 64
2006
+ },
2007
+ "model.layers.32.mlp.up_proj": {
2008
+ "bits": 4,
2009
+ "group_size": 64
2010
+ },
2011
+ "model.layers.33.self_attn.q_proj": {
2012
+ "bits": 4,
2013
+ "group_size": 64
2014
+ },
2015
+ "model.layers.33.self_attn.k_proj": {
2016
+ "bits": 4,
2017
+ "group_size": 64
2018
+ },
2019
+ "model.layers.33.self_attn.v_proj": {
2020
+ "bits": 4,
2021
+ "group_size": 64
2022
+ },
2023
+ "model.layers.33.self_attn.o_proj": {
2024
+ "bits": 4,
2025
+ "group_size": 64
2026
+ },
2027
+ "model.layers.33.mlp.gate_proj": {
2028
+ "bits": 4,
2029
+ "group_size": 64
2030
+ },
2031
+ "model.layers.33.mlp.down_proj": {
2032
+ "bits": 4,
2033
+ "group_size": 64
2034
+ },
2035
+ "model.layers.33.mlp.up_proj": {
2036
+ "bits": 4,
2037
+ "group_size": 64
2038
+ },
2039
+ "model.layers.34.self_attn.q_proj": {
2040
+ "bits": 4,
2041
+ "group_size": 64
2042
+ },
2043
+ "model.layers.34.self_attn.k_proj": {
2044
+ "bits": 4,
2045
+ "group_size": 64
2046
+ },
2047
+ "model.layers.34.self_attn.v_proj": {
2048
+ "bits": 4,
2049
+ "group_size": 64
2050
+ },
2051
+ "model.layers.34.self_attn.o_proj": {
2052
+ "bits": 4,
2053
+ "group_size": 64
2054
+ },
2055
+ "model.layers.34.mlp.gate_proj": {
2056
+ "bits": 4,
2057
+ "group_size": 64
2058
+ },
2059
+ "model.layers.34.mlp.down_proj": {
2060
+ "bits": 4,
2061
+ "group_size": 64
2062
+ },
2063
+ "model.layers.34.mlp.up_proj": {
2064
+ "bits": 4,
2065
+ "group_size": 64
2066
+ },
2067
+ "model.layers.35.self_attn.q_proj": {
2068
+ "bits": 4,
2069
+ "group_size": 64
2070
+ },
2071
+ "model.layers.35.self_attn.k_proj": {
2072
+ "bits": 4,
2073
+ "group_size": 64
2074
+ },
2075
+ "model.layers.35.self_attn.v_proj": {
2076
+ "bits": 4,
2077
+ "group_size": 64
2078
+ },
2079
+ "model.layers.35.self_attn.o_proj": {
2080
+ "bits": 4,
2081
+ "group_size": 64
2082
+ },
2083
+ "model.layers.35.mlp.gate_proj": {
2084
+ "bits": 4,
2085
+ "group_size": 64
2086
+ },
2087
+ "model.layers.35.mlp.down_proj": {
2088
+ "bits": 4,
2089
+ "group_size": 64
2090
+ },
2091
+ "model.layers.35.mlp.up_proj": {
2092
+ "bits": 4,
2093
+ "group_size": 64
2094
+ },
2095
+ "lm_head": {
2096
+ "bits": 6,
2097
+ "group_size": 64
2098
+ }
2099
+ },
2100
+ "rms_norm_eps": 1e-06,
2101
+ "rope_scaling": null,
2102
+ "rope_theta": 1000000,
2103
+ "sliding_window": null,
2104
+ "tie_word_embeddings": false,
2105
+ "torch_dtype": "float16",
2106
+ "transformers_version": "4.53.3",
2107
+ "unsloth_fixed": true,
2108
+ "unsloth_version": "2025.11.4",
2109
+ "use_cache": true,
2110
+ "use_sliding_window": false,
2111
+ "vocab_size": 151936
2112
+ }