w-ahmad commited on
Commit
453da1f
·
verified ·
1 Parent(s): 00c03df

Upload MoQ-Tensor-Configs/MoQ_model_tensors_3.8.txt with huggingface_hub

Browse files
MoQ-Tensor-Configs/MoQ_model_tensors_3.8.txt ADDED
@@ -0,0 +1,250 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ output.weight=IQ4_XS
2
+ token_embd.weight=IQ4_XS
3
+ blk.14.ffn_down.weight=IQ3_S
4
+ blk.14.ffn_gate.weight=IQ3_S
5
+ blk.14.ffn_up.weight=IQ3_S
6
+ blk.15.ffn_down.weight=IQ3_S
7
+ blk.15.ffn_gate.weight=IQ3_S
8
+ blk.15.ffn_up.weight=IQ3_S
9
+ blk.25.ffn_down.weight=IQ3_S
10
+ blk.26.ffn_down.weight=IQ3_S
11
+ blk.26.ffn_gate.weight=IQ3_S
12
+ blk.26.ffn_up.weight=IQ3_S
13
+ blk.27.ffn_down.weight=IQ3_S
14
+ blk.27.ffn_gate.weight=IQ3_S
15
+ blk.0.ffn_down.weight=IQ3_S
16
+ blk.0.ffn_gate.weight=IQ3_S
17
+ blk.0.ffn_up.weight=IQ3_S
18
+ blk.1.ffn_down.weight=IQ3_S
19
+ blk.1.ffn_gate.weight=IQ3_S
20
+ blk.1.ffn_up.weight=IQ3_S
21
+ blk.10.ffn_down.weight=IQ3_S
22
+ blk.10.ffn_gate.weight=IQ3_S
23
+ blk.10.ffn_up.weight=IQ3_S
24
+ blk.11.ffn_down.weight=IQ3_S
25
+ blk.11.ffn_gate.weight=IQ3_S
26
+ blk.11.ffn_up.weight=IQ3_S
27
+ blk.16.ffn_down.weight=IQ3_S
28
+ blk.16.ffn_gate.weight=IQ3_S
29
+ blk.16.ffn_up.weight=IQ3_S
30
+ blk.17.ffn_down.weight=IQ3_S
31
+ blk.17.ffn_gate.weight=IQ3_S
32
+ blk.17.ffn_up.weight=IQ3_S
33
+ blk.18.ffn_down.weight=IQ3_S
34
+ blk.18.ffn_gate.weight=IQ3_S
35
+ blk.18.ffn_up.weight=IQ3_S
36
+ blk.19.ffn_down.weight=IQ3_S
37
+ blk.21.ffn_down.weight=IQ3_S
38
+ blk.21.ffn_gate.weight=IQ3_S
39
+ blk.21.ffn_up.weight=IQ3_S
40
+ blk.22.ffn_down.weight=IQ3_S
41
+ blk.22.ffn_gate.weight=IQ3_S
42
+ blk.22.ffn_up.weight=IQ3_S
43
+ blk.23.ffn_down.weight=IQ3_S
44
+ blk.23.ffn_gate.weight=IQ3_S
45
+ blk.23.ffn_up.weight=IQ3_S
46
+ blk.27.ffn_up.weight=IQ3_S
47
+ blk.3.ffn_down.weight=IQ3_S
48
+ blk.3.ffn_gate.weight=IQ3_S
49
+ blk.3.ffn_up.weight=IQ3_S
50
+ blk.30.ffn_down.weight=IQ3_S
51
+ blk.30.ffn_gate.weight=IQ3_S
52
+ blk.30.ffn_up.weight=IQ3_S
53
+ blk.31.ffn_down.weight=IQ3_S
54
+ blk.31.ffn_gate.weight=IQ3_S
55
+ blk.31.ffn_up.weight=IQ3_S
56
+ blk.4.ffn_down.weight=IQ3_S
57
+ blk.4.ffn_gate.weight=IQ3_S
58
+ blk.4.ffn_up.weight=IQ3_S
59
+ blk.8.ffn_down.weight=IQ3_S
60
+ blk.8.ffn_gate.weight=IQ3_S
61
+ blk.8.ffn_up.weight=IQ3_S
62
+ blk.9.ffn_down.weight=IQ3_S
63
+ blk.9.ffn_gate.weight=IQ3_S
64
+ blk.9.ffn_up.weight=IQ3_S
65
+ blk.0.attn_qkv.weight=IQ3_S
66
+ blk.1.attn_qkv.weight=IQ3_S
67
+ blk.10.attn_qkv.weight=IQ3_S
68
+ blk.11.attn_q.weight=IQ4_XS
69
+ blk.12.ffn_down.weight=IQ3_S
70
+ blk.12.ffn_gate.weight=IQ3_S
71
+ blk.12.ffn_up.weight=IQ3_S
72
+ blk.13.ffn_down.weight=IQ3_S
73
+ blk.13.ffn_gate.weight=IQ3_S
74
+ blk.13.ffn_up.weight=IQ3_S
75
+ blk.14.attn_qkv.weight=IQ3_S
76
+ blk.15.attn_q.weight=IQ4_XS
77
+ blk.16.attn_qkv.weight=IQ3_S
78
+ blk.17.attn_qkv.weight=IQ3_S
79
+ blk.18.attn_qkv.weight=IQ3_S
80
+ blk.19.ffn_gate.weight=IQ3_S
81
+ blk.19.ffn_up.weight=IQ3_S
82
+ blk.19.attn_q.weight=IQ4_XS
83
+ blk.2.attn_qkv.weight=IQ3_S
84
+ blk.2.ffn_down.weight=IQ3_S
85
+ blk.2.ffn_gate.weight=IQ3_S
86
+ blk.2.ffn_up.weight=IQ3_S
87
+ blk.20.attn_qkv.weight=IQ3_S
88
+ blk.20.ffn_down.weight=IQ3_S
89
+ blk.20.ffn_gate.weight=IQ3_S
90
+ blk.20.ffn_up.weight=IQ3_S
91
+ blk.22.attn_qkv.weight=IQ3_S
92
+ blk.23.attn_q.weight=IQ4_XS
93
+ blk.24.attn_qkv.weight=IQ3_S
94
+ blk.24.ffn_down.weight=IQ3_S
95
+ blk.24.ffn_gate.weight=IQ3_S
96
+ blk.24.ffn_up.weight=IQ3_S
97
+ blk.25.attn_qkv.weight=IQ3_S
98
+ blk.25.ffn_gate.weight=IQ3_S
99
+ blk.25.ffn_up.weight=IQ3_S
100
+ blk.26.attn_qkv.weight=IQ3_S
101
+ blk.27.attn_q.weight=IQ4_XS
102
+ blk.28.ffn_down.weight=IQ3_S
103
+ blk.28.ffn_gate.weight=IQ3_S
104
+ blk.28.ffn_up.weight=IQ3_S
105
+ blk.29.ffn_down.weight=IQ3_S
106
+ blk.29.ffn_gate.weight=IQ3_S
107
+ blk.29.ffn_up.weight=IQ3_S
108
+ blk.3.attn_q.weight=IQ4_XS
109
+ blk.30.attn_qkv.weight=IQ3_S
110
+ blk.31.attn_q.weight=IQ4_XS
111
+ blk.4.attn_qkv.weight=IQ3_S
112
+ blk.5.attn_qkv.weight=IQ3_S
113
+ blk.5.ffn_down.weight=IQ3_S
114
+ blk.5.ffn_gate.weight=IQ3_S
115
+ blk.5.ffn_up.weight=IQ3_S
116
+ blk.6.attn_qkv.weight=IQ3_S
117
+ blk.6.ffn_down.weight=IQ3_S
118
+ blk.6.ffn_gate.weight=IQ3_S
119
+ blk.6.ffn_up.weight=IQ3_S
120
+ blk.7.ffn_down.weight=IQ3_S
121
+ blk.7.ffn_gate.weight=IQ3_S
122
+ blk.7.ffn_up.weight=IQ3_S
123
+ blk.7.attn_q.weight=IQ4_XS
124
+ blk.8.attn_qkv.weight=IQ3_S
125
+ blk.9.attn_qkv.weight=IQ3_S
126
+ blk.0.ssm_alpha.weight=bf16
127
+ blk.0.ssm_beta.weight=bf16
128
+ blk.0.attn_gate.weight=IQ4_XS
129
+ blk.0.ssm_out.weight=IQ4_XS
130
+ blk.1.ssm_alpha.weight=bf16
131
+ blk.1.ssm_beta.weight=bf16
132
+ blk.1.attn_gate.weight=IQ4_XS
133
+ blk.1.ssm_out.weight=IQ4_XS
134
+ blk.10.ssm_alpha.weight=bf16
135
+ blk.10.ssm_beta.weight=bf16
136
+ blk.10.attn_gate.weight=IQ4_XS
137
+ blk.10.ssm_out.weight=IQ4_XS
138
+ blk.11.attn_k.weight=bf16
139
+ blk.11.attn_output.weight=Q4_K
140
+ blk.11.attn_v.weight=Q5_K
141
+ blk.12.ssm_alpha.weight=bf16
142
+ blk.12.ssm_beta.weight=bf16
143
+ blk.12.attn_qkv.weight=IQ3_S
144
+ blk.12.attn_gate.weight=IQ4_XS
145
+ blk.12.ssm_out.weight=IQ4_XS
146
+ blk.13.ssm_alpha.weight=bf16
147
+ blk.13.ssm_beta.weight=bf16
148
+ blk.13.attn_qkv.weight=IQ3_S
149
+ blk.13.attn_gate.weight=IQ4_XS
150
+ blk.13.ssm_out.weight=IQ4_XS
151
+ blk.14.ssm_alpha.weight=bf16
152
+ blk.14.ssm_beta.weight=bf16
153
+ blk.14.attn_gate.weight=IQ4_XS
154
+ blk.14.ssm_out.weight=IQ4_XS
155
+ blk.15.attn_k.weight=bf16
156
+ blk.15.attn_output.weight=Q4_K
157
+ blk.15.attn_v.weight=Q5_K
158
+ blk.16.ssm_alpha.weight=bf16
159
+ blk.16.ssm_beta.weight=bf16
160
+ blk.16.attn_gate.weight=IQ4_XS
161
+ blk.16.ssm_out.weight=IQ4_XS
162
+ blk.17.ssm_alpha.weight=bf16
163
+ blk.17.ssm_beta.weight=bf16
164
+ blk.17.attn_gate.weight=IQ4_XS
165
+ blk.17.ssm_out.weight=IQ4_XS
166
+ blk.18.ssm_alpha.weight=bf16
167
+ blk.18.ssm_beta.weight=bf16
168
+ blk.18.attn_gate.weight=IQ4_XS
169
+ blk.18.ssm_out.weight=IQ4_XS
170
+ blk.19.attn_k.weight=bf16
171
+ blk.19.attn_output.weight=Q4_K
172
+ blk.19.attn_v.weight=Q5_K
173
+ blk.2.ssm_alpha.weight=bf16
174
+ blk.2.ssm_beta.weight=bf16
175
+ blk.2.attn_gate.weight=IQ4_XS
176
+ blk.2.ssm_out.weight=IQ4_XS
177
+ blk.20.ssm_alpha.weight=bf16
178
+ blk.20.ssm_beta.weight=bf16
179
+ blk.20.attn_gate.weight=IQ4_XS
180
+ blk.20.ssm_out.weight=IQ4_XS
181
+ blk.21.ssm_alpha.weight=bf16
182
+ blk.21.ssm_beta.weight=bf16
183
+ blk.21.attn_qkv.weight=IQ3_S
184
+ blk.21.attn_gate.weight=IQ4_XS
185
+ blk.21.ssm_out.weight=IQ4_XS
186
+ blk.22.ssm_alpha.weight=bf16
187
+ blk.22.ssm_beta.weight=bf16
188
+ blk.22.attn_gate.weight=IQ4_XS
189
+ blk.22.ssm_out.weight=IQ4_XS
190
+ blk.23.attn_k.weight=bf16
191
+ blk.23.attn_output.weight=Q4_K
192
+ blk.23.attn_v.weight=Q5_K
193
+ blk.24.ssm_alpha.weight=bf16
194
+ blk.24.ssm_beta.weight=bf16
195
+ blk.24.attn_gate.weight=IQ4_XS
196
+ blk.24.ssm_out.weight=IQ4_XS
197
+ blk.25.ssm_alpha.weight=bf16
198
+ blk.25.ssm_beta.weight=bf16
199
+ blk.25.attn_gate.weight=IQ4_XS
200
+ blk.25.ssm_out.weight=IQ4_XS
201
+ blk.26.ssm_alpha.weight=bf16
202
+ blk.26.ssm_beta.weight=bf16
203
+ blk.26.attn_gate.weight=IQ4_XS
204
+ blk.26.ssm_out.weight=IQ4_XS
205
+ blk.27.attn_k.weight=bf16
206
+ blk.27.attn_output.weight=Q4_K
207
+ blk.27.attn_v.weight=Q5_K
208
+ blk.28.ssm_alpha.weight=bf16
209
+ blk.28.ssm_beta.weight=bf16
210
+ blk.28.attn_qkv.weight=IQ3_S
211
+ blk.28.attn_gate.weight=IQ4_XS
212
+ blk.28.ssm_out.weight=IQ4_XS
213
+ blk.29.ssm_alpha.weight=bf16
214
+ blk.29.ssm_beta.weight=bf16
215
+ blk.29.attn_qkv.weight=IQ3_S
216
+ blk.29.attn_gate.weight=IQ4_XS
217
+ blk.29.ssm_out.weight=IQ4_XS
218
+ blk.3.attn_k.weight=bf16
219
+ blk.3.attn_output.weight=Q4_K
220
+ blk.3.attn_v.weight=Q5_K
221
+ blk.30.ssm_alpha.weight=bf16
222
+ blk.30.ssm_beta.weight=bf16
223
+ blk.30.attn_gate.weight=IQ4_XS
224
+ blk.30.ssm_out.weight=IQ4_XS
225
+ blk.31.attn_k.weight=bf16
226
+ blk.31.attn_output.weight=Q4_K
227
+ blk.31.attn_v.weight=Q5_K
228
+ blk.4.ssm_alpha.weight=bf16
229
+ blk.4.ssm_beta.weight=bf16
230
+ blk.4.attn_gate.weight=IQ4_XS
231
+ blk.4.ssm_out.weight=IQ4_XS
232
+ blk.5.ssm_alpha.weight=bf16
233
+ blk.5.ssm_beta.weight=bf16
234
+ blk.5.attn_gate.weight=IQ4_XS
235
+ blk.5.ssm_out.weight=IQ4_XS
236
+ blk.6.ssm_alpha.weight=bf16
237
+ blk.6.ssm_beta.weight=bf16
238
+ blk.6.attn_gate.weight=IQ4_XS
239
+ blk.6.ssm_out.weight=IQ4_XS
240
+ blk.7.attn_k.weight=bf16
241
+ blk.7.attn_output.weight=Q4_K
242
+ blk.7.attn_v.weight=Q5_K
243
+ blk.8.ssm_alpha.weight=bf16
244
+ blk.8.ssm_beta.weight=bf16
245
+ blk.8.attn_gate.weight=IQ4_XS
246
+ blk.8.ssm_out.weight=IQ4_XS
247
+ blk.9.ssm_alpha.weight=bf16
248
+ blk.9.ssm_beta.weight=bf16
249
+ blk.9.attn_gate.weight=IQ4_XS
250
+ blk.9.ssm_out.weight=IQ4_XS