rodrigoramosrs commited on
Commit
f95c901
·
verified ·
1 Parent(s): 236f88f

Upload hf_quant_config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. hf_quant_config.json +302 -157
hf_quant_config.json CHANGED
@@ -1,159 +1,304 @@
1
  {
2
- "producer": {
3
- "name": "modelopt",
4
- "version": "0.47.0"
5
- },
6
- "quantization": {
7
- "quant_algo": "NVFP4",
8
- "kv_cache_quant_algo": null,
9
- "group_size": 16,
10
- "exclude_modules": [
11
- "lm_head",
12
- "model.language_model.embed_tokens",
13
- "model.language_model.layers.0.linear_attn.conv1d",
14
- "model.language_model.layers.0.linear_attn.in_proj_a",
15
- "model.language_model.layers.0.linear_attn.in_proj_b",
16
- "model.language_model.layers.1.linear_attn.conv1d",
17
- "model.language_model.layers.1.linear_attn.in_proj_a",
18
- "model.language_model.layers.1.linear_attn.in_proj_b",
19
- "model.language_model.layers.10.linear_attn.conv1d",
20
- "model.language_model.layers.10.linear_attn.in_proj_a",
21
- "model.language_model.layers.10.linear_attn.in_proj_b",
22
- "model.language_model.layers.12.linear_attn.conv1d",
23
- "model.language_model.layers.12.linear_attn.in_proj_a",
24
- "model.language_model.layers.12.linear_attn.in_proj_b",
25
- "model.language_model.layers.13.linear_attn.conv1d",
26
- "model.language_model.layers.13.linear_attn.in_proj_a",
27
- "model.language_model.layers.13.linear_attn.in_proj_b",
28
- "model.language_model.layers.14.linear_attn.conv1d",
29
- "model.language_model.layers.14.linear_attn.in_proj_a",
30
- "model.language_model.layers.14.linear_attn.in_proj_b",
31
- "model.language_model.layers.16.linear_attn.conv1d",
32
- "model.language_model.layers.16.linear_attn.in_proj_a",
33
- "model.language_model.layers.16.linear_attn.in_proj_b",
34
- "model.language_model.layers.17.linear_attn.conv1d",
35
- "model.language_model.layers.17.linear_attn.in_proj_a",
36
- "model.language_model.layers.17.linear_attn.in_proj_b",
37
- "model.language_model.layers.18.linear_attn.conv1d",
38
- "model.language_model.layers.18.linear_attn.in_proj_a",
39
- "model.language_model.layers.18.linear_attn.in_proj_b",
40
- "model.language_model.layers.2.linear_attn.conv1d",
41
- "model.language_model.layers.2.linear_attn.in_proj_a",
42
- "model.language_model.layers.2.linear_attn.in_proj_b",
43
- "model.language_model.layers.20.linear_attn.conv1d",
44
- "model.language_model.layers.20.linear_attn.in_proj_a",
45
- "model.language_model.layers.20.linear_attn.in_proj_b",
46
- "model.language_model.layers.21.linear_attn.conv1d",
47
- "model.language_model.layers.21.linear_attn.in_proj_a",
48
- "model.language_model.layers.21.linear_attn.in_proj_b",
49
- "model.language_model.layers.22.linear_attn.conv1d",
50
- "model.language_model.layers.22.linear_attn.in_proj_a",
51
- "model.language_model.layers.22.linear_attn.in_proj_b",
52
- "model.language_model.layers.24.linear_attn.conv1d",
53
- "model.language_model.layers.24.linear_attn.in_proj_a",
54
- "model.language_model.layers.24.linear_attn.in_proj_b",
55
- "model.language_model.layers.25.linear_attn.conv1d",
56
- "model.language_model.layers.25.linear_attn.in_proj_a",
57
- "model.language_model.layers.25.linear_attn.in_proj_b",
58
- "model.language_model.layers.26.linear_attn.conv1d",
59
- "model.language_model.layers.26.linear_attn.in_proj_a",
60
- "model.language_model.layers.26.linear_attn.in_proj_b",
61
- "model.language_model.layers.28.linear_attn.conv1d",
62
- "model.language_model.layers.28.linear_attn.in_proj_a",
63
- "model.language_model.layers.28.linear_attn.in_proj_b",
64
- "model.language_model.layers.29.linear_attn.conv1d",
65
- "model.language_model.layers.29.linear_attn.in_proj_a",
66
- "model.language_model.layers.29.linear_attn.in_proj_b",
67
- "model.language_model.layers.30.linear_attn.conv1d",
68
- "model.language_model.layers.30.linear_attn.in_proj_a",
69
- "model.language_model.layers.30.linear_attn.in_proj_b",
70
- "model.language_model.layers.32.linear_attn.conv1d",
71
- "model.language_model.layers.32.linear_attn.in_proj_a",
72
- "model.language_model.layers.32.linear_attn.in_proj_b",
73
- "model.language_model.layers.33.linear_attn.conv1d",
74
- "model.language_model.layers.33.linear_attn.in_proj_a",
75
- "model.language_model.layers.33.linear_attn.in_proj_b",
76
- "model.language_model.layers.34.linear_attn.conv1d",
77
- "model.language_model.layers.34.linear_attn.in_proj_a",
78
- "model.language_model.layers.34.linear_attn.in_proj_b",
79
- "model.language_model.layers.36.linear_attn.conv1d",
80
- "model.language_model.layers.36.linear_attn.in_proj_a",
81
- "model.language_model.layers.36.linear_attn.in_proj_b",
82
- "model.language_model.layers.37.linear_attn.conv1d",
83
- "model.language_model.layers.37.linear_attn.in_proj_a",
84
- "model.language_model.layers.37.linear_attn.in_proj_b",
85
- "model.language_model.layers.38.linear_attn.conv1d",
86
- "model.language_model.layers.38.linear_attn.in_proj_a",
87
- "model.language_model.layers.38.linear_attn.in_proj_b",
88
- "model.language_model.layers.4.linear_attn.conv1d",
89
- "model.language_model.layers.4.linear_attn.in_proj_a",
90
- "model.language_model.layers.4.linear_attn.in_proj_b",
91
- "model.language_model.layers.40.linear_attn.conv1d",
92
- "model.language_model.layers.40.linear_attn.in_proj_a",
93
- "model.language_model.layers.40.linear_attn.in_proj_b",
94
- "model.language_model.layers.41.linear_attn.conv1d",
95
- "model.language_model.layers.41.linear_attn.in_proj_a",
96
- "model.language_model.layers.41.linear_attn.in_proj_b",
97
- "model.language_model.layers.42.linear_attn.conv1d",
98
- "model.language_model.layers.42.linear_attn.in_proj_a",
99
- "model.language_model.layers.42.linear_attn.in_proj_b",
100
- "model.language_model.layers.44.linear_attn.conv1d",
101
- "model.language_model.layers.44.linear_attn.in_proj_a",
102
- "model.language_model.layers.44.linear_attn.in_proj_b",
103
- "model.language_model.layers.45.linear_attn.conv1d",
104
- "model.language_model.layers.45.linear_attn.in_proj_a",
105
- "model.language_model.layers.45.linear_attn.in_proj_b",
106
- "model.language_model.layers.46.linear_attn.conv1d",
107
- "model.language_model.layers.46.linear_attn.in_proj_a",
108
- "model.language_model.layers.46.linear_attn.in_proj_b",
109
- "model.language_model.layers.48.linear_attn.conv1d",
110
- "model.language_model.layers.48.linear_attn.in_proj_a",
111
- "model.language_model.layers.48.linear_attn.in_proj_b",
112
- "model.language_model.layers.49.linear_attn.conv1d",
113
- "model.language_model.layers.49.linear_attn.in_proj_a",
114
- "model.language_model.layers.49.linear_attn.in_proj_b",
115
- "model.language_model.layers.5.linear_attn.conv1d",
116
- "model.language_model.layers.5.linear_attn.in_proj_a",
117
- "model.language_model.layers.5.linear_attn.in_proj_b",
118
- "model.language_model.layers.50.linear_attn.conv1d",
119
- "model.language_model.layers.50.linear_attn.in_proj_a",
120
- "model.language_model.layers.50.linear_attn.in_proj_b",
121
- "model.language_model.layers.52.linear_attn.conv1d",
122
- "model.language_model.layers.52.linear_attn.in_proj_a",
123
- "model.language_model.layers.52.linear_attn.in_proj_b",
124
- "model.language_model.layers.53.linear_attn.conv1d",
125
- "model.language_model.layers.53.linear_attn.in_proj_a",
126
- "model.language_model.layers.53.linear_attn.in_proj_b",
127
- "model.language_model.layers.54.linear_attn.conv1d",
128
- "model.language_model.layers.54.linear_attn.in_proj_a",
129
- "model.language_model.layers.54.linear_attn.in_proj_b",
130
- "model.language_model.layers.56.linear_attn.conv1d",
131
- "model.language_model.layers.56.linear_attn.in_proj_a",
132
- "model.language_model.layers.56.linear_attn.in_proj_b",
133
- "model.language_model.layers.57.linear_attn.conv1d",
134
- "model.language_model.layers.57.linear_attn.in_proj_a",
135
- "model.language_model.layers.57.linear_attn.in_proj_b",
136
- "model.language_model.layers.58.linear_attn.conv1d",
137
- "model.language_model.layers.58.linear_attn.in_proj_a",
138
- "model.language_model.layers.58.linear_attn.in_proj_b",
139
- "model.language_model.layers.6.linear_attn.conv1d",
140
- "model.language_model.layers.6.linear_attn.in_proj_a",
141
- "model.language_model.layers.6.linear_attn.in_proj_b",
142
- "model.language_model.layers.60.linear_attn.conv1d",
143
- "model.language_model.layers.60.linear_attn.in_proj_a",
144
- "model.language_model.layers.60.linear_attn.in_proj_b",
145
- "model.language_model.layers.61.linear_attn.conv1d",
146
- "model.language_model.layers.61.linear_attn.in_proj_a",
147
- "model.language_model.layers.61.linear_attn.in_proj_b",
148
- "model.language_model.layers.62.linear_attn.conv1d",
149
- "model.language_model.layers.62.linear_attn.in_proj_a",
150
- "model.language_model.layers.62.linear_attn.in_proj_b",
151
- "model.language_model.layers.8.linear_attn.conv1d",
152
- "model.language_model.layers.8.linear_attn.in_proj_a",
153
- "model.language_model.layers.8.linear_attn.in_proj_b",
154
- "model.language_model.layers.9.linear_attn.conv1d",
155
- "model.language_model.layers.9.linear_attn.in_proj_a",
156
- "model.language_model.layers.9.linear_attn.in_proj_b"
157
- ]
158
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
159
  }
 
1
  {
2
+ "producer": {
3
+ "name": "modelopt",
4
+ "version": "0.47.0"
5
+ },
6
+ "quantization": {
7
+ "quant_algo": "NVFP4",
8
+ "kv_cache_quant_algo": null,
9
+ "group_size": 16,
10
+ "exclude_modules": [
11
+ "lm_head",
12
+ "model.language_model.embed_tokens",
13
+ "model.language_model.layers.0.linear_attn.conv1d",
14
+ "model.language_model.layers.0.linear_attn.in_proj_a",
15
+ "model.language_model.layers.0.linear_attn.in_proj_b",
16
+ "model.language_model.layers.1.linear_attn.conv1d",
17
+ "model.language_model.layers.1.linear_attn.in_proj_a",
18
+ "model.language_model.layers.1.linear_attn.in_proj_b",
19
+ "model.language_model.layers.10.linear_attn.conv1d",
20
+ "model.language_model.layers.10.linear_attn.in_proj_a",
21
+ "model.language_model.layers.10.linear_attn.in_proj_b",
22
+ "model.language_model.layers.12.linear_attn.conv1d",
23
+ "model.language_model.layers.12.linear_attn.in_proj_a",
24
+ "model.language_model.layers.12.linear_attn.in_proj_b",
25
+ "model.language_model.layers.13.linear_attn.conv1d",
26
+ "model.language_model.layers.13.linear_attn.in_proj_a",
27
+ "model.language_model.layers.13.linear_attn.in_proj_b",
28
+ "model.language_model.layers.14.linear_attn.conv1d",
29
+ "model.language_model.layers.14.linear_attn.in_proj_a",
30
+ "model.language_model.layers.14.linear_attn.in_proj_b",
31
+ "model.language_model.layers.16.linear_attn.conv1d",
32
+ "model.language_model.layers.16.linear_attn.in_proj_a",
33
+ "model.language_model.layers.16.linear_attn.in_proj_b",
34
+ "model.language_model.layers.17.linear_attn.conv1d",
35
+ "model.language_model.layers.17.linear_attn.in_proj_a",
36
+ "model.language_model.layers.17.linear_attn.in_proj_b",
37
+ "model.language_model.layers.18.linear_attn.conv1d",
38
+ "model.language_model.layers.18.linear_attn.in_proj_a",
39
+ "model.language_model.layers.18.linear_attn.in_proj_b",
40
+ "model.language_model.layers.2.linear_attn.conv1d",
41
+ "model.language_model.layers.2.linear_attn.in_proj_a",
42
+ "model.language_model.layers.2.linear_attn.in_proj_b",
43
+ "model.language_model.layers.20.linear_attn.conv1d",
44
+ "model.language_model.layers.20.linear_attn.in_proj_a",
45
+ "model.language_model.layers.20.linear_attn.in_proj_b",
46
+ "model.language_model.layers.21.linear_attn.conv1d",
47
+ "model.language_model.layers.21.linear_attn.in_proj_a",
48
+ "model.language_model.layers.21.linear_attn.in_proj_b",
49
+ "model.language_model.layers.22.linear_attn.conv1d",
50
+ "model.language_model.layers.22.linear_attn.in_proj_a",
51
+ "model.language_model.layers.22.linear_attn.in_proj_b",
52
+ "model.language_model.layers.24.linear_attn.conv1d",
53
+ "model.language_model.layers.24.linear_attn.in_proj_a",
54
+ "model.language_model.layers.24.linear_attn.in_proj_b",
55
+ "model.language_model.layers.25.linear_attn.conv1d",
56
+ "model.language_model.layers.25.linear_attn.in_proj_a",
57
+ "model.language_model.layers.25.linear_attn.in_proj_b",
58
+ "model.language_model.layers.26.linear_attn.conv1d",
59
+ "model.language_model.layers.26.linear_attn.in_proj_a",
60
+ "model.language_model.layers.26.linear_attn.in_proj_b",
61
+ "model.language_model.layers.28.linear_attn.conv1d",
62
+ "model.language_model.layers.28.linear_attn.in_proj_a",
63
+ "model.language_model.layers.28.linear_attn.in_proj_b",
64
+ "model.language_model.layers.29.linear_attn.conv1d",
65
+ "model.language_model.layers.29.linear_attn.in_proj_a",
66
+ "model.language_model.layers.29.linear_attn.in_proj_b",
67
+ "model.language_model.layers.30.linear_attn.conv1d",
68
+ "model.language_model.layers.30.linear_attn.in_proj_a",
69
+ "model.language_model.layers.30.linear_attn.in_proj_b",
70
+ "model.language_model.layers.32.linear_attn.conv1d",
71
+ "model.language_model.layers.32.linear_attn.in_proj_a",
72
+ "model.language_model.layers.32.linear_attn.in_proj_b",
73
+ "model.language_model.layers.33.linear_attn.conv1d",
74
+ "model.language_model.layers.33.linear_attn.in_proj_a",
75
+ "model.language_model.layers.33.linear_attn.in_proj_b",
76
+ "model.language_model.layers.34.linear_attn.conv1d",
77
+ "model.language_model.layers.34.linear_attn.in_proj_a",
78
+ "model.language_model.layers.34.linear_attn.in_proj_b",
79
+ "model.language_model.layers.36.linear_attn.conv1d",
80
+ "model.language_model.layers.36.linear_attn.in_proj_a",
81
+ "model.language_model.layers.36.linear_attn.in_proj_b",
82
+ "model.language_model.layers.37.linear_attn.conv1d",
83
+ "model.language_model.layers.37.linear_attn.in_proj_a",
84
+ "model.language_model.layers.37.linear_attn.in_proj_b",
85
+ "model.language_model.layers.38.linear_attn.conv1d",
86
+ "model.language_model.layers.38.linear_attn.in_proj_a",
87
+ "model.language_model.layers.38.linear_attn.in_proj_b",
88
+ "model.language_model.layers.4.linear_attn.conv1d",
89
+ "model.language_model.layers.4.linear_attn.in_proj_a",
90
+ "model.language_model.layers.4.linear_attn.in_proj_b",
91
+ "model.language_model.layers.40.linear_attn.conv1d",
92
+ "model.language_model.layers.40.linear_attn.in_proj_a",
93
+ "model.language_model.layers.40.linear_attn.in_proj_b",
94
+ "model.language_model.layers.41.linear_attn.conv1d",
95
+ "model.language_model.layers.41.linear_attn.in_proj_a",
96
+ "model.language_model.layers.41.linear_attn.in_proj_b",
97
+ "model.language_model.layers.42.linear_attn.conv1d",
98
+ "model.language_model.layers.42.linear_attn.in_proj_a",
99
+ "model.language_model.layers.42.linear_attn.in_proj_b",
100
+ "model.language_model.layers.44.linear_attn.conv1d",
101
+ "model.language_model.layers.44.linear_attn.in_proj_a",
102
+ "model.language_model.layers.44.linear_attn.in_proj_b",
103
+ "model.language_model.layers.45.linear_attn.conv1d",
104
+ "model.language_model.layers.45.linear_attn.in_proj_a",
105
+ "model.language_model.layers.45.linear_attn.in_proj_b",
106
+ "model.language_model.layers.46.linear_attn.conv1d",
107
+ "model.language_model.layers.46.linear_attn.in_proj_a",
108
+ "model.language_model.layers.46.linear_attn.in_proj_b",
109
+ "model.language_model.layers.48.linear_attn.conv1d",
110
+ "model.language_model.layers.48.linear_attn.in_proj_a",
111
+ "model.language_model.layers.48.linear_attn.in_proj_b",
112
+ "model.language_model.layers.49.linear_attn.conv1d",
113
+ "model.language_model.layers.49.linear_attn.in_proj_a",
114
+ "model.language_model.layers.49.linear_attn.in_proj_b",
115
+ "model.language_model.layers.5.linear_attn.conv1d",
116
+ "model.language_model.layers.5.linear_attn.in_proj_a",
117
+ "model.language_model.layers.5.linear_attn.in_proj_b",
118
+ "model.language_model.layers.50.linear_attn.conv1d",
119
+ "model.language_model.layers.50.linear_attn.in_proj_a",
120
+ "model.language_model.layers.50.linear_attn.in_proj_b",
121
+ "model.language_model.layers.52.linear_attn.conv1d",
122
+ "model.language_model.layers.52.linear_attn.in_proj_a",
123
+ "model.language_model.layers.52.linear_attn.in_proj_b",
124
+ "model.language_model.layers.53.linear_attn.conv1d",
125
+ "model.language_model.layers.53.linear_attn.in_proj_a",
126
+ "model.language_model.layers.53.linear_attn.in_proj_b",
127
+ "model.language_model.layers.54.linear_attn.conv1d",
128
+ "model.language_model.layers.54.linear_attn.in_proj_a",
129
+ "model.language_model.layers.54.linear_attn.in_proj_b",
130
+ "model.language_model.layers.56.linear_attn.conv1d",
131
+ "model.language_model.layers.56.linear_attn.in_proj_a",
132
+ "model.language_model.layers.56.linear_attn.in_proj_b",
133
+ "model.language_model.layers.57.linear_attn.conv1d",
134
+ "model.language_model.layers.57.linear_attn.in_proj_a",
135
+ "model.language_model.layers.57.linear_attn.in_proj_b",
136
+ "model.language_model.layers.58.linear_attn.conv1d",
137
+ "model.language_model.layers.58.linear_attn.in_proj_a",
138
+ "model.language_model.layers.58.linear_attn.in_proj_b",
139
+ "model.language_model.layers.6.linear_attn.conv1d",
140
+ "model.language_model.layers.6.linear_attn.in_proj_a",
141
+ "model.language_model.layers.6.linear_attn.in_proj_b",
142
+ "model.language_model.layers.60.linear_attn.conv1d",
143
+ "model.language_model.layers.60.linear_attn.in_proj_a",
144
+ "model.language_model.layers.60.linear_attn.in_proj_b",
145
+ "model.language_model.layers.61.linear_attn.conv1d",
146
+ "model.language_model.layers.61.linear_attn.in_proj_a",
147
+ "model.language_model.layers.61.linear_attn.in_proj_b",
148
+ "model.language_model.layers.62.linear_attn.conv1d",
149
+ "model.language_model.layers.62.linear_attn.in_proj_a",
150
+ "model.language_model.layers.62.linear_attn.in_proj_b",
151
+ "model.language_model.layers.8.linear_attn.conv1d",
152
+ "model.language_model.layers.8.linear_attn.in_proj_a",
153
+ "model.language_model.layers.8.linear_attn.in_proj_b",
154
+ "model.language_model.layers.9.linear_attn.conv1d",
155
+ "model.language_model.layers.9.linear_attn.in_proj_a",
156
+ "model.language_model.layers.9.linear_attn.in_proj_b",
157
+ "model.embed_tokens",
158
+ "model.layers.0.linear_attn.conv1d",
159
+ "model.layers.0.linear_attn.in_proj_a",
160
+ "model.layers.0.linear_attn.in_proj_b",
161
+ "model.layers.1.linear_attn.conv1d",
162
+ "model.layers.1.linear_attn.in_proj_a",
163
+ "model.layers.1.linear_attn.in_proj_b",
164
+ "model.layers.10.linear_attn.conv1d",
165
+ "model.layers.10.linear_attn.in_proj_a",
166
+ "model.layers.10.linear_attn.in_proj_b",
167
+ "model.layers.12.linear_attn.conv1d",
168
+ "model.layers.12.linear_attn.in_proj_a",
169
+ "model.layers.12.linear_attn.in_proj_b",
170
+ "model.layers.13.linear_attn.conv1d",
171
+ "model.layers.13.linear_attn.in_proj_a",
172
+ "model.layers.13.linear_attn.in_proj_b",
173
+ "model.layers.14.linear_attn.conv1d",
174
+ "model.layers.14.linear_attn.in_proj_a",
175
+ "model.layers.14.linear_attn.in_proj_b",
176
+ "model.layers.16.linear_attn.conv1d",
177
+ "model.layers.16.linear_attn.in_proj_a",
178
+ "model.layers.16.linear_attn.in_proj_b",
179
+ "model.layers.17.linear_attn.conv1d",
180
+ "model.layers.17.linear_attn.in_proj_a",
181
+ "model.layers.17.linear_attn.in_proj_b",
182
+ "model.layers.18.linear_attn.conv1d",
183
+ "model.layers.18.linear_attn.in_proj_a",
184
+ "model.layers.18.linear_attn.in_proj_b",
185
+ "model.layers.2.linear_attn.conv1d",
186
+ "model.layers.2.linear_attn.in_proj_a",
187
+ "model.layers.2.linear_attn.in_proj_b",
188
+ "model.layers.20.linear_attn.conv1d",
189
+ "model.layers.20.linear_attn.in_proj_a",
190
+ "model.layers.20.linear_attn.in_proj_b",
191
+ "model.layers.21.linear_attn.conv1d",
192
+ "model.layers.21.linear_attn.in_proj_a",
193
+ "model.layers.21.linear_attn.in_proj_b",
194
+ "model.layers.22.linear_attn.conv1d",
195
+ "model.layers.22.linear_attn.in_proj_a",
196
+ "model.layers.22.linear_attn.in_proj_b",
197
+ "model.layers.24.linear_attn.conv1d",
198
+ "model.layers.24.linear_attn.in_proj_a",
199
+ "model.layers.24.linear_attn.in_proj_b",
200
+ "model.layers.25.linear_attn.conv1d",
201
+ "model.layers.25.linear_attn.in_proj_a",
202
+ "model.layers.25.linear_attn.in_proj_b",
203
+ "model.layers.26.linear_attn.conv1d",
204
+ "model.layers.26.linear_attn.in_proj_a",
205
+ "model.layers.26.linear_attn.in_proj_b",
206
+ "model.layers.28.linear_attn.conv1d",
207
+ "model.layers.28.linear_attn.in_proj_a",
208
+ "model.layers.28.linear_attn.in_proj_b",
209
+ "model.layers.29.linear_attn.conv1d",
210
+ "model.layers.29.linear_attn.in_proj_a",
211
+ "model.layers.29.linear_attn.in_proj_b",
212
+ "model.layers.30.linear_attn.conv1d",
213
+ "model.layers.30.linear_attn.in_proj_a",
214
+ "model.layers.30.linear_attn.in_proj_b",
215
+ "model.layers.32.linear_attn.conv1d",
216
+ "model.layers.32.linear_attn.in_proj_a",
217
+ "model.layers.32.linear_attn.in_proj_b",
218
+ "model.layers.33.linear_attn.conv1d",
219
+ "model.layers.33.linear_attn.in_proj_a",
220
+ "model.layers.33.linear_attn.in_proj_b",
221
+ "model.layers.34.linear_attn.conv1d",
222
+ "model.layers.34.linear_attn.in_proj_a",
223
+ "model.layers.34.linear_attn.in_proj_b",
224
+ "model.layers.36.linear_attn.conv1d",
225
+ "model.layers.36.linear_attn.in_proj_a",
226
+ "model.layers.36.linear_attn.in_proj_b",
227
+ "model.layers.37.linear_attn.conv1d",
228
+ "model.layers.37.linear_attn.in_proj_a",
229
+ "model.layers.37.linear_attn.in_proj_b",
230
+ "model.layers.38.linear_attn.conv1d",
231
+ "model.layers.38.linear_attn.in_proj_a",
232
+ "model.layers.38.linear_attn.in_proj_b",
233
+ "model.layers.4.linear_attn.conv1d",
234
+ "model.layers.4.linear_attn.in_proj_a",
235
+ "model.layers.4.linear_attn.in_proj_b",
236
+ "model.layers.40.linear_attn.conv1d",
237
+ "model.layers.40.linear_attn.in_proj_a",
238
+ "model.layers.40.linear_attn.in_proj_b",
239
+ "model.layers.41.linear_attn.conv1d",
240
+ "model.layers.41.linear_attn.in_proj_a",
241
+ "model.layers.41.linear_attn.in_proj_b",
242
+ "model.layers.42.linear_attn.conv1d",
243
+ "model.layers.42.linear_attn.in_proj_a",
244
+ "model.layers.42.linear_attn.in_proj_b",
245
+ "model.layers.44.linear_attn.conv1d",
246
+ "model.layers.44.linear_attn.in_proj_a",
247
+ "model.layers.44.linear_attn.in_proj_b",
248
+ "model.layers.45.linear_attn.conv1d",
249
+ "model.layers.45.linear_attn.in_proj_a",
250
+ "model.layers.45.linear_attn.in_proj_b",
251
+ "model.layers.46.linear_attn.conv1d",
252
+ "model.layers.46.linear_attn.in_proj_a",
253
+ "model.layers.46.linear_attn.in_proj_b",
254
+ "model.layers.48.linear_attn.conv1d",
255
+ "model.layers.48.linear_attn.in_proj_a",
256
+ "model.layers.48.linear_attn.in_proj_b",
257
+ "model.layers.49.linear_attn.conv1d",
258
+ "model.layers.49.linear_attn.in_proj_a",
259
+ "model.layers.49.linear_attn.in_proj_b",
260
+ "model.layers.5.linear_attn.conv1d",
261
+ "model.layers.5.linear_attn.in_proj_a",
262
+ "model.layers.5.linear_attn.in_proj_b",
263
+ "model.layers.50.linear_attn.conv1d",
264
+ "model.layers.50.linear_attn.in_proj_a",
265
+ "model.layers.50.linear_attn.in_proj_b",
266
+ "model.layers.52.linear_attn.conv1d",
267
+ "model.layers.52.linear_attn.in_proj_a",
268
+ "model.layers.52.linear_attn.in_proj_b",
269
+ "model.layers.53.linear_attn.conv1d",
270
+ "model.layers.53.linear_attn.in_proj_a",
271
+ "model.layers.53.linear_attn.in_proj_b",
272
+ "model.layers.54.linear_attn.conv1d",
273
+ "model.layers.54.linear_attn.in_proj_a",
274
+ "model.layers.54.linear_attn.in_proj_b",
275
+ "model.layers.56.linear_attn.conv1d",
276
+ "model.layers.56.linear_attn.in_proj_a",
277
+ "model.layers.56.linear_attn.in_proj_b",
278
+ "model.layers.57.linear_attn.conv1d",
279
+ "model.layers.57.linear_attn.in_proj_a",
280
+ "model.layers.57.linear_attn.in_proj_b",
281
+ "model.layers.58.linear_attn.conv1d",
282
+ "model.layers.58.linear_attn.in_proj_a",
283
+ "model.layers.58.linear_attn.in_proj_b",
284
+ "model.layers.6.linear_attn.conv1d",
285
+ "model.layers.6.linear_attn.in_proj_a",
286
+ "model.layers.6.linear_attn.in_proj_b",
287
+ "model.layers.60.linear_attn.conv1d",
288
+ "model.layers.60.linear_attn.in_proj_a",
289
+ "model.layers.60.linear_attn.in_proj_b",
290
+ "model.layers.61.linear_attn.conv1d",
291
+ "model.layers.61.linear_attn.in_proj_a",
292
+ "model.layers.61.linear_attn.in_proj_b",
293
+ "model.layers.62.linear_attn.conv1d",
294
+ "model.layers.62.linear_attn.in_proj_a",
295
+ "model.layers.62.linear_attn.in_proj_b",
296
+ "model.layers.8.linear_attn.conv1d",
297
+ "model.layers.8.linear_attn.in_proj_a",
298
+ "model.layers.8.linear_attn.in_proj_b",
299
+ "model.layers.9.linear_attn.conv1d",
300
+ "model.layers.9.linear_attn.in_proj_a",
301
+ "model.layers.9.linear_attn.in_proj_b"
302
+ ]
303
+ }
304
  }