w-ahmad commited on
Commit
9e0c93c
·
verified ·
1 Parent(s): 6741d0b

Upload MoQ-Tensor-Configs/MoQ_gemma4_12b_it_tensors_4.0.txt with huggingface_hub

Browse files
MoQ-Tensor-Configs/MoQ_gemma4_12b_it_tensors_4.0.txt ADDED
@@ -0,0 +1,329 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ token_embd.weight=IQ4_NL
2
+ blk.0.ffn_down.weight=Q4_K
3
+ blk.0.ffn_gate.weight=IQ4_XS
4
+ blk.0.ffn_up.weight=IQ4_NL
5
+ blk.0.attn_k.weight=IQ3_XXS
6
+ blk.0.attn_output.weight=IQ3_S
7
+ blk.0.attn_q.weight=IQ4_XS
8
+ blk.0.attn_v.weight=IQ3_S
9
+ blk.1.ffn_down.weight=Q4_K
10
+ blk.1.ffn_gate.weight=IQ4_XS
11
+ blk.1.ffn_up.weight=IQ4_NL
12
+ blk.1.attn_k.weight=IQ3_XXS
13
+ blk.1.attn_output.weight=IQ3_S
14
+ blk.1.attn_q.weight=IQ4_XS
15
+ blk.1.attn_v.weight=IQ3_S
16
+ blk.10.ffn_down.weight=Q4_K
17
+ blk.10.ffn_gate.weight=IQ4_XS
18
+ blk.10.ffn_up.weight=IQ4_NL
19
+ blk.10.attn_k.weight=IQ3_XXS
20
+ blk.10.attn_output.weight=IQ3_S
21
+ blk.10.attn_q.weight=IQ4_XS
22
+ blk.10.attn_v.weight=IQ3_S
23
+ blk.11.ffn_down.weight=Q4_K
24
+ blk.11.ffn_gate.weight=IQ4_XS
25
+ blk.11.ffn_up.weight=IQ4_NL
26
+ blk.11.attn_k.weight=IQ3_XXS
27
+ blk.11.attn_output.weight=IQ3_S
28
+ blk.11.attn_q.weight=IQ4_XS
29
+ blk.12.ffn_down.weight=Q4_K
30
+ blk.12.ffn_gate.weight=IQ4_XS
31
+ blk.12.ffn_up.weight=IQ4_NL
32
+ blk.12.attn_k.weight=IQ3_XXS
33
+ blk.12.attn_output.weight=IQ3_S
34
+ blk.12.attn_q.weight=IQ4_XS
35
+ blk.12.attn_v.weight=IQ3_S
36
+ blk.13.ffn_down.weight=Q4_K
37
+ blk.13.ffn_gate.weight=IQ4_XS
38
+ blk.13.ffn_up.weight=IQ4_NL
39
+ blk.13.attn_k.weight=IQ3_XXS
40
+ blk.13.attn_output.weight=IQ3_S
41
+ blk.13.attn_q.weight=IQ4_XS
42
+ blk.13.attn_v.weight=IQ3_S
43
+ blk.14.ffn_down.weight=Q4_K
44
+ blk.14.ffn_gate.weight=IQ4_XS
45
+ blk.14.ffn_up.weight=IQ4_NL
46
+ blk.14.attn_k.weight=IQ3_XXS
47
+ blk.14.attn_output.weight=IQ3_S
48
+ blk.14.attn_q.weight=IQ4_XS
49
+ blk.14.attn_v.weight=IQ3_S
50
+ blk.15.ffn_down.weight=Q4_K
51
+ blk.15.ffn_gate.weight=IQ4_XS
52
+ blk.15.ffn_up.weight=IQ4_NL
53
+ blk.15.attn_k.weight=IQ3_XXS
54
+ blk.15.attn_output.weight=IQ3_S
55
+ blk.15.attn_q.weight=IQ4_XS
56
+ blk.15.attn_v.weight=IQ3_S
57
+ blk.16.ffn_down.weight=Q4_K
58
+ blk.16.ffn_gate.weight=IQ4_XS
59
+ blk.16.ffn_up.weight=IQ4_NL
60
+ blk.16.attn_k.weight=IQ3_XXS
61
+ blk.16.attn_output.weight=IQ3_S
62
+ blk.16.attn_q.weight=IQ4_XS
63
+ blk.16.attn_v.weight=IQ3_S
64
+ blk.17.ffn_down.weight=Q4_K
65
+ blk.17.ffn_gate.weight=IQ4_XS
66
+ blk.17.ffn_up.weight=IQ4_NL
67
+ blk.17.attn_k.weight=IQ3_XXS
68
+ blk.17.attn_output.weight=IQ3_S
69
+ blk.17.attn_q.weight=IQ4_XS
70
+ blk.18.ffn_down.weight=Q4_K
71
+ blk.18.ffn_gate.weight=IQ4_XS
72
+ blk.18.ffn_up.weight=IQ4_NL
73
+ blk.18.attn_k.weight=IQ3_XXS
74
+ blk.18.attn_output.weight=IQ3_S
75
+ blk.18.attn_q.weight=IQ4_XS
76
+ blk.18.attn_v.weight=IQ3_S
77
+ blk.19.ffn_down.weight=Q4_K
78
+ blk.19.ffn_gate.weight=IQ4_XS
79
+ blk.19.ffn_up.weight=IQ4_NL
80
+ blk.19.attn_k.weight=IQ3_XXS
81
+ blk.19.attn_output.weight=IQ3_S
82
+ blk.19.attn_q.weight=IQ4_XS
83
+ blk.19.attn_v.weight=IQ3_S
84
+ blk.2.ffn_down.weight=Q4_K
85
+ blk.2.ffn_gate.weight=IQ4_XS
86
+ blk.2.ffn_up.weight=IQ4_NL
87
+ blk.2.attn_k.weight=IQ3_XXS
88
+ blk.2.attn_output.weight=IQ3_S
89
+ blk.2.attn_q.weight=IQ4_XS
90
+ blk.2.attn_v.weight=IQ3_S
91
+ blk.20.ffn_down.weight=Q4_K
92
+ blk.20.ffn_gate.weight=IQ4_XS
93
+ blk.20.ffn_up.weight=IQ4_NL
94
+ blk.20.attn_k.weight=IQ3_XXS
95
+ blk.20.attn_output.weight=IQ3_S
96
+ blk.20.attn_q.weight=IQ4_XS
97
+ blk.20.attn_v.weight=IQ3_S
98
+ blk.21.ffn_down.weight=Q4_K
99
+ blk.21.ffn_gate.weight=IQ4_XS
100
+ blk.21.ffn_up.weight=IQ4_NL
101
+ blk.21.attn_k.weight=IQ3_XXS
102
+ blk.21.attn_output.weight=IQ3_S
103
+ blk.21.attn_q.weight=IQ4_XS
104
+ blk.21.attn_v.weight=IQ3_S
105
+ blk.22.ffn_down.weight=Q4_K
106
+ blk.22.ffn_gate.weight=IQ4_XS
107
+ blk.22.ffn_up.weight=IQ4_NL
108
+ blk.22.attn_k.weight=IQ3_XXS
109
+ blk.22.attn_output.weight=IQ3_S
110
+ blk.22.attn_q.weight=IQ4_XS
111
+ blk.22.attn_v.weight=IQ3_S
112
+ blk.23.ffn_down.weight=Q4_K
113
+ blk.23.ffn_gate.weight=IQ4_XS
114
+ blk.23.ffn_up.weight=IQ4_NL
115
+ blk.23.attn_k.weight=IQ3_XXS
116
+ blk.23.attn_output.weight=IQ3_S
117
+ blk.23.attn_q.weight=IQ4_XS
118
+ blk.24.ffn_down.weight=Q4_K
119
+ blk.24.ffn_gate.weight=IQ4_XS
120
+ blk.24.ffn_up.weight=IQ4_NL
121
+ blk.24.attn_k.weight=IQ3_XXS
122
+ blk.24.attn_output.weight=IQ3_S
123
+ blk.24.attn_q.weight=IQ4_XS
124
+ blk.24.attn_v.weight=IQ3_S
125
+ blk.25.ffn_down.weight=Q4_K
126
+ blk.25.ffn_gate.weight=IQ4_XS
127
+ blk.25.ffn_up.weight=IQ4_NL
128
+ blk.25.attn_k.weight=IQ3_XXS
129
+ blk.25.attn_output.weight=IQ3_S
130
+ blk.25.attn_q.weight=IQ4_XS
131
+ blk.25.attn_v.weight=IQ3_S
132
+ blk.26.ffn_down.weight=Q4_K
133
+ blk.26.ffn_gate.weight=IQ4_XS
134
+ blk.26.ffn_up.weight=IQ4_NL
135
+ blk.26.attn_k.weight=IQ3_XXS
136
+ blk.26.attn_output.weight=IQ3_S
137
+ blk.26.attn_q.weight=IQ4_XS
138
+ blk.26.attn_v.weight=IQ3_S
139
+ blk.27.ffn_down.weight=Q4_K
140
+ blk.27.ffn_gate.weight=IQ4_XS
141
+ blk.27.ffn_up.weight=IQ4_NL
142
+ blk.27.attn_k.weight=IQ3_XXS
143
+ blk.27.attn_output.weight=IQ3_S
144
+ blk.27.attn_q.weight=IQ4_XS
145
+ blk.27.attn_v.weight=IQ3_S
146
+ blk.28.ffn_down.weight=Q4_K
147
+ blk.28.ffn_gate.weight=IQ4_XS
148
+ blk.28.ffn_up.weight=IQ4_NL
149
+ blk.28.attn_k.weight=IQ3_XXS
150
+ blk.28.attn_output.weight=IQ3_S
151
+ blk.28.attn_q.weight=IQ4_XS
152
+ blk.28.attn_v.weight=IQ3_S
153
+ blk.29.ffn_down.weight=Q4_K
154
+ blk.29.ffn_gate.weight=IQ4_XS
155
+ blk.29.ffn_up.weight=IQ4_NL
156
+ blk.29.attn_k.weight=IQ3_XXS
157
+ blk.29.attn_output.weight=IQ3_S
158
+ blk.29.attn_q.weight=IQ4_XS
159
+ blk.3.ffn_down.weight=Q4_K
160
+ blk.3.ffn_gate.weight=IQ4_XS
161
+ blk.3.ffn_up.weight=IQ4_NL
162
+ blk.3.attn_k.weight=IQ3_XXS
163
+ blk.3.attn_output.weight=IQ3_S
164
+ blk.3.attn_q.weight=IQ4_XS
165
+ blk.3.attn_v.weight=IQ3_S
166
+ blk.30.ffn_down.weight=Q4_K
167
+ blk.30.ffn_gate.weight=IQ4_XS
168
+ blk.30.ffn_up.weight=IQ4_NL
169
+ blk.30.attn_k.weight=IQ3_XXS
170
+ blk.30.attn_output.weight=IQ3_S
171
+ blk.30.attn_q.weight=IQ4_XS
172
+ blk.30.attn_v.weight=IQ3_S
173
+ blk.31.ffn_down.weight=Q4_K
174
+ blk.31.ffn_gate.weight=IQ4_XS
175
+ blk.31.ffn_up.weight=IQ4_NL
176
+ blk.31.attn_k.weight=IQ3_XXS
177
+ blk.31.attn_output.weight=IQ3_S
178
+ blk.31.attn_q.weight=IQ4_XS
179
+ blk.31.attn_v.weight=IQ3_S
180
+ blk.32.ffn_down.weight=Q4_K
181
+ blk.32.ffn_gate.weight=IQ4_XS
182
+ blk.32.ffn_up.weight=IQ4_NL
183
+ blk.32.attn_k.weight=IQ3_XXS
184
+ blk.32.attn_output.weight=IQ3_S
185
+ blk.32.attn_q.weight=IQ4_XS
186
+ blk.32.attn_v.weight=IQ3_S
187
+ blk.33.ffn_down.weight=Q4_K
188
+ blk.33.ffn_gate.weight=IQ4_XS
189
+ blk.33.ffn_up.weight=IQ4_NL
190
+ blk.33.attn_k.weight=IQ3_XXS
191
+ blk.33.attn_output.weight=IQ3_S
192
+ blk.33.attn_q.weight=IQ4_XS
193
+ blk.33.attn_v.weight=IQ3_S
194
+ blk.34.ffn_down.weight=Q4_K
195
+ blk.34.ffn_gate.weight=IQ4_XS
196
+ blk.34.ffn_up.weight=IQ4_NL
197
+ blk.34.attn_k.weight=IQ3_XXS
198
+ blk.34.attn_output.weight=IQ3_S
199
+ blk.34.attn_q.weight=IQ4_XS
200
+ blk.34.attn_v.weight=IQ3_S
201
+ blk.35.ffn_down.weight=Q4_K
202
+ blk.35.ffn_gate.weight=IQ4_XS
203
+ blk.35.ffn_up.weight=IQ4_NL
204
+ blk.35.attn_k.weight=IQ3_XXS
205
+ blk.35.attn_output.weight=IQ3_S
206
+ blk.35.attn_q.weight=IQ4_XS
207
+ blk.36.ffn_down.weight=Q4_K
208
+ blk.36.ffn_gate.weight=IQ4_XS
209
+ blk.36.ffn_up.weight=IQ4_NL
210
+ blk.36.attn_k.weight=IQ3_XXS
211
+ blk.36.attn_output.weight=IQ3_S
212
+ blk.36.attn_q.weight=IQ4_XS
213
+ blk.36.attn_v.weight=IQ3_S
214
+ blk.37.ffn_down.weight=Q4_K
215
+ blk.37.ffn_gate.weight=IQ4_XS
216
+ blk.37.ffn_up.weight=IQ4_NL
217
+ blk.37.attn_k.weight=IQ3_XXS
218
+ blk.37.attn_output.weight=IQ3_S
219
+ blk.37.attn_q.weight=IQ4_XS
220
+ blk.37.attn_v.weight=IQ3_S
221
+ blk.38.ffn_down.weight=Q4_K
222
+ blk.38.ffn_gate.weight=IQ4_XS
223
+ blk.38.ffn_up.weight=IQ4_NL
224
+ blk.38.attn_k.weight=IQ3_XXS
225
+ blk.38.attn_output.weight=IQ3_S
226
+ blk.38.attn_q.weight=IQ4_XS
227
+ blk.38.attn_v.weight=IQ3_S
228
+ blk.39.ffn_down.weight=Q4_K
229
+ blk.39.ffn_gate.weight=IQ4_XS
230
+ blk.39.ffn_up.weight=IQ4_NL
231
+ blk.39.attn_k.weight=IQ3_XXS
232
+ blk.39.attn_output.weight=IQ3_S
233
+ blk.39.attn_q.weight=IQ4_XS
234
+ blk.39.attn_v.weight=IQ3_S
235
+ blk.4.ffn_down.weight=Q4_K
236
+ blk.4.ffn_gate.weight=IQ4_XS
237
+ blk.4.ffn_up.weight=IQ4_NL
238
+ blk.4.attn_k.weight=IQ3_XXS
239
+ blk.4.attn_output.weight=IQ3_S
240
+ blk.4.attn_q.weight=IQ4_XS
241
+ blk.4.attn_v.weight=IQ3_S
242
+ blk.40.ffn_down.weight=Q4_K
243
+ blk.40.ffn_gate.weight=IQ4_XS
244
+ blk.40.ffn_up.weight=IQ4_NL
245
+ blk.40.attn_k.weight=IQ3_XXS
246
+ blk.40.attn_output.weight=IQ3_S
247
+ blk.40.attn_q.weight=IQ4_XS
248
+ blk.40.attn_v.weight=IQ3_S
249
+ blk.41.ffn_down.weight=Q4_K
250
+ blk.41.ffn_gate.weight=IQ4_XS
251
+ blk.41.ffn_up.weight=IQ4_NL
252
+ blk.41.attn_k.weight=IQ3_XXS
253
+ blk.41.attn_output.weight=IQ3_S
254
+ blk.41.attn_q.weight=IQ4_XS
255
+ blk.42.ffn_down.weight=Q4_K
256
+ blk.42.ffn_gate.weight=IQ4_XS
257
+ blk.42.ffn_up.weight=IQ4_NL
258
+ blk.42.attn_k.weight=IQ3_XXS
259
+ blk.42.attn_output.weight=IQ3_S
260
+ blk.42.attn_q.weight=IQ4_XS
261
+ blk.42.attn_v.weight=IQ3_S
262
+ blk.43.ffn_down.weight=Q4_K
263
+ blk.43.ffn_gate.weight=IQ4_XS
264
+ blk.43.ffn_up.weight=IQ4_NL
265
+ blk.43.attn_k.weight=IQ3_XXS
266
+ blk.43.attn_output.weight=IQ3_S
267
+ blk.43.attn_q.weight=IQ4_XS
268
+ blk.43.attn_v.weight=IQ3_S
269
+ blk.44.ffn_down.weight=Q4_K
270
+ blk.44.ffn_gate.weight=IQ4_XS
271
+ blk.44.ffn_up.weight=IQ4_NL
272
+ blk.44.attn_k.weight=IQ3_XXS
273
+ blk.44.attn_output.weight=IQ3_S
274
+ blk.44.attn_q.weight=IQ4_XS
275
+ blk.44.attn_v.weight=IQ3_S
276
+ blk.45.ffn_down.weight=Q4_K
277
+ blk.45.ffn_gate.weight=IQ4_XS
278
+ blk.45.ffn_up.weight=IQ4_NL
279
+ blk.45.attn_k.weight=IQ3_XXS
280
+ blk.45.attn_output.weight=IQ3_S
281
+ blk.45.attn_q.weight=IQ4_XS
282
+ blk.45.attn_v.weight=IQ3_S
283
+ blk.46.ffn_down.weight=Q4_K
284
+ blk.46.ffn_gate.weight=IQ4_XS
285
+ blk.46.ffn_up.weight=IQ4_NL
286
+ blk.46.attn_k.weight=IQ3_XXS
287
+ blk.46.attn_output.weight=IQ3_S
288
+ blk.46.attn_q.weight=IQ4_XS
289
+ blk.46.attn_v.weight=IQ3_S
290
+ blk.47.ffn_down.weight=Q4_K
291
+ blk.47.ffn_gate.weight=IQ4_XS
292
+ blk.47.ffn_up.weight=IQ4_NL
293
+ blk.47.attn_k.weight=IQ3_XXS
294
+ blk.47.attn_output.weight=IQ3_S
295
+ blk.47.attn_q.weight=IQ4_XS
296
+ blk.5.ffn_down.weight=Q4_K
297
+ blk.5.ffn_gate.weight=IQ4_XS
298
+ blk.5.ffn_up.weight=IQ4_NL
299
+ blk.5.attn_k.weight=IQ3_XXS
300
+ blk.5.attn_output.weight=IQ3_S
301
+ blk.5.attn_q.weight=IQ4_XS
302
+ blk.6.ffn_down.weight=Q4_K
303
+ blk.6.ffn_gate.weight=IQ4_XS
304
+ blk.6.ffn_up.weight=IQ4_NL
305
+ blk.6.attn_k.weight=IQ3_XXS
306
+ blk.6.attn_output.weight=IQ3_S
307
+ blk.6.attn_q.weight=IQ4_XS
308
+ blk.6.attn_v.weight=IQ3_S
309
+ blk.7.ffn_down.weight=Q4_K
310
+ blk.7.ffn_gate.weight=IQ4_XS
311
+ blk.7.ffn_up.weight=IQ4_NL
312
+ blk.7.attn_k.weight=IQ3_XXS
313
+ blk.7.attn_output.weight=IQ3_S
314
+ blk.7.attn_q.weight=IQ4_XS
315
+ blk.7.attn_v.weight=IQ3_S
316
+ blk.8.ffn_down.weight=Q4_K
317
+ blk.8.ffn_gate.weight=IQ4_XS
318
+ blk.8.ffn_up.weight=IQ4_NL
319
+ blk.8.attn_k.weight=IQ3_XXS
320
+ blk.8.attn_output.weight=IQ3_S
321
+ blk.8.attn_q.weight=IQ4_XS
322
+ blk.8.attn_v.weight=IQ3_S
323
+ blk.9.ffn_down.weight=Q4_K
324
+ blk.9.ffn_gate.weight=IQ4_XS
325
+ blk.9.ffn_up.weight=IQ4_NL
326
+ blk.9.attn_k.weight=IQ3_XXS
327
+ blk.9.attn_output.weight=IQ3_S
328
+ blk.9.attn_q.weight=IQ4_XS
329
+ blk.9.attn_v.weight=IQ3_S