DrNicefellow commited on
Commit
4f8513c
1 Parent(s): bbe8f13

Upload 13 files

Browse files
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MambaForCausalLM"
4
+ ],
5
+ "bos_token_id": 0,
6
+ "conv_kernel": 4,
7
+ "eos_token_id": 0,
8
+ "expand": 2,
9
+ "fused_add_norm": true,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2560,
12
+ "initializer_range": 0.1,
13
+ "intermediate_size": 5120,
14
+ "layer_norm_epsilon": 1e-05,
15
+ "model_type": "mamba",
16
+ "n_layer": 48,
17
+ "num_hidden_layers": 48,
18
+ "pad_token_id": 0,
19
+ "pad_vocab_size_multiple": 8,
20
+ "rescale_prenorm_residual": false,
21
+ "residual_in_fp32": true,
22
+ "rms_norm": true,
23
+ "state_size": 16,
24
+ "time_step_floor": 0.0001,
25
+ "time_step_init_scheme": "random",
26
+ "time_step_max": 0.1,
27
+ "time_step_min": 0.001,
28
+ "time_step_rank": 160,
29
+ "time_step_scale": 1.0,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.41.0",
32
+ "use_bias": false,
33
+ "use_cache": true,
34
+ "use_conv_bias": true,
35
+ "vocab_size": 50280
36
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.41.0"
7
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28aceec4f38f616d2c4ab1075c278738b8ed8786740f296b6efd8d596ee1027c
3
+ size 16867928192
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2d044e62b284b79f170fe6a948c1b789b661b855da817d57a94dc4e69ffd0f0
3
+ size 4969794150
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:617831e2ea9c23548b4bf740f7148daea93c223259068526b16f6ded666f3d6f
3
+ size 3464130832
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,490 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 8433756160
4
+ },
5
+ "weight_map": {
6
+ "backbone.embeddings.weight": "pytorch_model-00001-of-00002.bin",
7
+ "backbone.layers.0.mixer.A_log": "pytorch_model-00001-of-00002.bin",
8
+ "backbone.layers.0.mixer.D": "pytorch_model-00001-of-00002.bin",
9
+ "backbone.layers.0.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
10
+ "backbone.layers.0.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
11
+ "backbone.layers.0.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
12
+ "backbone.layers.0.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
13
+ "backbone.layers.0.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
14
+ "backbone.layers.0.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
15
+ "backbone.layers.0.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
16
+ "backbone.layers.0.norm.weight": "pytorch_model-00001-of-00002.bin",
17
+ "backbone.layers.1.mixer.A_log": "pytorch_model-00001-of-00002.bin",
18
+ "backbone.layers.1.mixer.D": "pytorch_model-00001-of-00002.bin",
19
+ "backbone.layers.1.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
20
+ "backbone.layers.1.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
21
+ "backbone.layers.1.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
22
+ "backbone.layers.1.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
23
+ "backbone.layers.1.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
24
+ "backbone.layers.1.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
25
+ "backbone.layers.1.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
26
+ "backbone.layers.1.norm.weight": "pytorch_model-00001-of-00002.bin",
27
+ "backbone.layers.10.mixer.A_log": "pytorch_model-00001-of-00002.bin",
28
+ "backbone.layers.10.mixer.D": "pytorch_model-00001-of-00002.bin",
29
+ "backbone.layers.10.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
30
+ "backbone.layers.10.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
31
+ "backbone.layers.10.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
32
+ "backbone.layers.10.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
33
+ "backbone.layers.10.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
34
+ "backbone.layers.10.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
35
+ "backbone.layers.10.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
36
+ "backbone.layers.10.norm.weight": "pytorch_model-00001-of-00002.bin",
37
+ "backbone.layers.11.mixer.A_log": "pytorch_model-00001-of-00002.bin",
38
+ "backbone.layers.11.mixer.D": "pytorch_model-00001-of-00002.bin",
39
+ "backbone.layers.11.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
40
+ "backbone.layers.11.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
41
+ "backbone.layers.11.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
42
+ "backbone.layers.11.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
43
+ "backbone.layers.11.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
44
+ "backbone.layers.11.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
45
+ "backbone.layers.11.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
46
+ "backbone.layers.11.norm.weight": "pytorch_model-00001-of-00002.bin",
47
+ "backbone.layers.12.mixer.A_log": "pytorch_model-00001-of-00002.bin",
48
+ "backbone.layers.12.mixer.D": "pytorch_model-00001-of-00002.bin",
49
+ "backbone.layers.12.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
50
+ "backbone.layers.12.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
51
+ "backbone.layers.12.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
52
+ "backbone.layers.12.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
53
+ "backbone.layers.12.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
54
+ "backbone.layers.12.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
55
+ "backbone.layers.12.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
56
+ "backbone.layers.12.norm.weight": "pytorch_model-00001-of-00002.bin",
57
+ "backbone.layers.13.mixer.A_log": "pytorch_model-00001-of-00002.bin",
58
+ "backbone.layers.13.mixer.D": "pytorch_model-00001-of-00002.bin",
59
+ "backbone.layers.13.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
60
+ "backbone.layers.13.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
61
+ "backbone.layers.13.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
62
+ "backbone.layers.13.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
63
+ "backbone.layers.13.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
64
+ "backbone.layers.13.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
65
+ "backbone.layers.13.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
66
+ "backbone.layers.13.norm.weight": "pytorch_model-00001-of-00002.bin",
67
+ "backbone.layers.14.mixer.A_log": "pytorch_model-00001-of-00002.bin",
68
+ "backbone.layers.14.mixer.D": "pytorch_model-00001-of-00002.bin",
69
+ "backbone.layers.14.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
70
+ "backbone.layers.14.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
71
+ "backbone.layers.14.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
72
+ "backbone.layers.14.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
73
+ "backbone.layers.14.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
74
+ "backbone.layers.14.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
75
+ "backbone.layers.14.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
76
+ "backbone.layers.14.norm.weight": "pytorch_model-00001-of-00002.bin",
77
+ "backbone.layers.15.mixer.A_log": "pytorch_model-00001-of-00002.bin",
78
+ "backbone.layers.15.mixer.D": "pytorch_model-00001-of-00002.bin",
79
+ "backbone.layers.15.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
80
+ "backbone.layers.15.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
81
+ "backbone.layers.15.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
82
+ "backbone.layers.15.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
83
+ "backbone.layers.15.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
84
+ "backbone.layers.15.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
85
+ "backbone.layers.15.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
86
+ "backbone.layers.15.norm.weight": "pytorch_model-00001-of-00002.bin",
87
+ "backbone.layers.16.mixer.A_log": "pytorch_model-00001-of-00002.bin",
88
+ "backbone.layers.16.mixer.D": "pytorch_model-00001-of-00002.bin",
89
+ "backbone.layers.16.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
90
+ "backbone.layers.16.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
91
+ "backbone.layers.16.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
92
+ "backbone.layers.16.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
93
+ "backbone.layers.16.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
94
+ "backbone.layers.16.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
95
+ "backbone.layers.16.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
96
+ "backbone.layers.16.norm.weight": "pytorch_model-00001-of-00002.bin",
97
+ "backbone.layers.17.mixer.A_log": "pytorch_model-00001-of-00002.bin",
98
+ "backbone.layers.17.mixer.D": "pytorch_model-00001-of-00002.bin",
99
+ "backbone.layers.17.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
100
+ "backbone.layers.17.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
101
+ "backbone.layers.17.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
102
+ "backbone.layers.17.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
103
+ "backbone.layers.17.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
104
+ "backbone.layers.17.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
105
+ "backbone.layers.17.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
106
+ "backbone.layers.17.norm.weight": "pytorch_model-00001-of-00002.bin",
107
+ "backbone.layers.18.mixer.A_log": "pytorch_model-00001-of-00002.bin",
108
+ "backbone.layers.18.mixer.D": "pytorch_model-00001-of-00002.bin",
109
+ "backbone.layers.18.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
110
+ "backbone.layers.18.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
111
+ "backbone.layers.18.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
112
+ "backbone.layers.18.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
113
+ "backbone.layers.18.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
114
+ "backbone.layers.18.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
115
+ "backbone.layers.18.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
116
+ "backbone.layers.18.norm.weight": "pytorch_model-00001-of-00002.bin",
117
+ "backbone.layers.19.mixer.A_log": "pytorch_model-00001-of-00002.bin",
118
+ "backbone.layers.19.mixer.D": "pytorch_model-00001-of-00002.bin",
119
+ "backbone.layers.19.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
120
+ "backbone.layers.19.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
121
+ "backbone.layers.19.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
122
+ "backbone.layers.19.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
123
+ "backbone.layers.19.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
124
+ "backbone.layers.19.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
125
+ "backbone.layers.19.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
126
+ "backbone.layers.19.norm.weight": "pytorch_model-00001-of-00002.bin",
127
+ "backbone.layers.2.mixer.A_log": "pytorch_model-00001-of-00002.bin",
128
+ "backbone.layers.2.mixer.D": "pytorch_model-00001-of-00002.bin",
129
+ "backbone.layers.2.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
130
+ "backbone.layers.2.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
131
+ "backbone.layers.2.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
132
+ "backbone.layers.2.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
133
+ "backbone.layers.2.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
134
+ "backbone.layers.2.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
135
+ "backbone.layers.2.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
136
+ "backbone.layers.2.norm.weight": "pytorch_model-00001-of-00002.bin",
137
+ "backbone.layers.20.mixer.A_log": "pytorch_model-00001-of-00002.bin",
138
+ "backbone.layers.20.mixer.D": "pytorch_model-00001-of-00002.bin",
139
+ "backbone.layers.20.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
140
+ "backbone.layers.20.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
141
+ "backbone.layers.20.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
142
+ "backbone.layers.20.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
143
+ "backbone.layers.20.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
144
+ "backbone.layers.20.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
145
+ "backbone.layers.20.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
146
+ "backbone.layers.20.norm.weight": "pytorch_model-00001-of-00002.bin",
147
+ "backbone.layers.21.mixer.A_log": "pytorch_model-00001-of-00002.bin",
148
+ "backbone.layers.21.mixer.D": "pytorch_model-00001-of-00002.bin",
149
+ "backbone.layers.21.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
150
+ "backbone.layers.21.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
151
+ "backbone.layers.21.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
152
+ "backbone.layers.21.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
153
+ "backbone.layers.21.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
154
+ "backbone.layers.21.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
155
+ "backbone.layers.21.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
156
+ "backbone.layers.21.norm.weight": "pytorch_model-00001-of-00002.bin",
157
+ "backbone.layers.22.mixer.A_log": "pytorch_model-00001-of-00002.bin",
158
+ "backbone.layers.22.mixer.D": "pytorch_model-00001-of-00002.bin",
159
+ "backbone.layers.22.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
160
+ "backbone.layers.22.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
161
+ "backbone.layers.22.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
162
+ "backbone.layers.22.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
163
+ "backbone.layers.22.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
164
+ "backbone.layers.22.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
165
+ "backbone.layers.22.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
166
+ "backbone.layers.22.norm.weight": "pytorch_model-00001-of-00002.bin",
167
+ "backbone.layers.23.mixer.A_log": "pytorch_model-00001-of-00002.bin",
168
+ "backbone.layers.23.mixer.D": "pytorch_model-00001-of-00002.bin",
169
+ "backbone.layers.23.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
170
+ "backbone.layers.23.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
171
+ "backbone.layers.23.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
172
+ "backbone.layers.23.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
173
+ "backbone.layers.23.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
174
+ "backbone.layers.23.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
175
+ "backbone.layers.23.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
176
+ "backbone.layers.23.norm.weight": "pytorch_model-00001-of-00002.bin",
177
+ "backbone.layers.24.mixer.A_log": "pytorch_model-00001-of-00002.bin",
178
+ "backbone.layers.24.mixer.D": "pytorch_model-00001-of-00002.bin",
179
+ "backbone.layers.24.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
180
+ "backbone.layers.24.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
181
+ "backbone.layers.24.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
182
+ "backbone.layers.24.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
183
+ "backbone.layers.24.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
184
+ "backbone.layers.24.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
185
+ "backbone.layers.24.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
186
+ "backbone.layers.24.norm.weight": "pytorch_model-00001-of-00002.bin",
187
+ "backbone.layers.25.mixer.A_log": "pytorch_model-00001-of-00002.bin",
188
+ "backbone.layers.25.mixer.D": "pytorch_model-00001-of-00002.bin",
189
+ "backbone.layers.25.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
190
+ "backbone.layers.25.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
191
+ "backbone.layers.25.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
192
+ "backbone.layers.25.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
193
+ "backbone.layers.25.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
194
+ "backbone.layers.25.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
195
+ "backbone.layers.25.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
196
+ "backbone.layers.25.norm.weight": "pytorch_model-00001-of-00002.bin",
197
+ "backbone.layers.26.mixer.A_log": "pytorch_model-00001-of-00002.bin",
198
+ "backbone.layers.26.mixer.D": "pytorch_model-00001-of-00002.bin",
199
+ "backbone.layers.26.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
200
+ "backbone.layers.26.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
201
+ "backbone.layers.26.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
202
+ "backbone.layers.26.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
203
+ "backbone.layers.26.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
204
+ "backbone.layers.26.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
205
+ "backbone.layers.26.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
206
+ "backbone.layers.26.norm.weight": "pytorch_model-00001-of-00002.bin",
207
+ "backbone.layers.27.mixer.A_log": "pytorch_model-00001-of-00002.bin",
208
+ "backbone.layers.27.mixer.D": "pytorch_model-00001-of-00002.bin",
209
+ "backbone.layers.27.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
210
+ "backbone.layers.27.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
211
+ "backbone.layers.27.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
212
+ "backbone.layers.27.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
213
+ "backbone.layers.27.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
214
+ "backbone.layers.27.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
215
+ "backbone.layers.27.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
216
+ "backbone.layers.27.norm.weight": "pytorch_model-00001-of-00002.bin",
217
+ "backbone.layers.28.mixer.A_log": "pytorch_model-00002-of-00002.bin",
218
+ "backbone.layers.28.mixer.D": "pytorch_model-00002-of-00002.bin",
219
+ "backbone.layers.28.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
220
+ "backbone.layers.28.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
221
+ "backbone.layers.28.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
222
+ "backbone.layers.28.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
223
+ "backbone.layers.28.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
224
+ "backbone.layers.28.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
225
+ "backbone.layers.28.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
226
+ "backbone.layers.28.norm.weight": "pytorch_model-00002-of-00002.bin",
227
+ "backbone.layers.29.mixer.A_log": "pytorch_model-00002-of-00002.bin",
228
+ "backbone.layers.29.mixer.D": "pytorch_model-00002-of-00002.bin",
229
+ "backbone.layers.29.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
230
+ "backbone.layers.29.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
231
+ "backbone.layers.29.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
232
+ "backbone.layers.29.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
233
+ "backbone.layers.29.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
234
+ "backbone.layers.29.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
235
+ "backbone.layers.29.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
236
+ "backbone.layers.29.norm.weight": "pytorch_model-00002-of-00002.bin",
237
+ "backbone.layers.3.mixer.A_log": "pytorch_model-00001-of-00002.bin",
238
+ "backbone.layers.3.mixer.D": "pytorch_model-00001-of-00002.bin",
239
+ "backbone.layers.3.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
240
+ "backbone.layers.3.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
241
+ "backbone.layers.3.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
242
+ "backbone.layers.3.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
243
+ "backbone.layers.3.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
244
+ "backbone.layers.3.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
245
+ "backbone.layers.3.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
246
+ "backbone.layers.3.norm.weight": "pytorch_model-00001-of-00002.bin",
247
+ "backbone.layers.30.mixer.A_log": "pytorch_model-00002-of-00002.bin",
248
+ "backbone.layers.30.mixer.D": "pytorch_model-00002-of-00002.bin",
249
+ "backbone.layers.30.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
250
+ "backbone.layers.30.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
251
+ "backbone.layers.30.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
252
+ "backbone.layers.30.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
253
+ "backbone.layers.30.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
254
+ "backbone.layers.30.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
255
+ "backbone.layers.30.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
256
+ "backbone.layers.30.norm.weight": "pytorch_model-00002-of-00002.bin",
257
+ "backbone.layers.31.mixer.A_log": "pytorch_model-00002-of-00002.bin",
258
+ "backbone.layers.31.mixer.D": "pytorch_model-00002-of-00002.bin",
259
+ "backbone.layers.31.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
260
+ "backbone.layers.31.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
261
+ "backbone.layers.31.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
262
+ "backbone.layers.31.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
263
+ "backbone.layers.31.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
264
+ "backbone.layers.31.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
265
+ "backbone.layers.31.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
266
+ "backbone.layers.31.norm.weight": "pytorch_model-00002-of-00002.bin",
267
+ "backbone.layers.32.mixer.A_log": "pytorch_model-00002-of-00002.bin",
268
+ "backbone.layers.32.mixer.D": "pytorch_model-00002-of-00002.bin",
269
+ "backbone.layers.32.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
270
+ "backbone.layers.32.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
271
+ "backbone.layers.32.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
272
+ "backbone.layers.32.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
273
+ "backbone.layers.32.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
274
+ "backbone.layers.32.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
275
+ "backbone.layers.32.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
276
+ "backbone.layers.32.norm.weight": "pytorch_model-00002-of-00002.bin",
277
+ "backbone.layers.33.mixer.A_log": "pytorch_model-00002-of-00002.bin",
278
+ "backbone.layers.33.mixer.D": "pytorch_model-00002-of-00002.bin",
279
+ "backbone.layers.33.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
280
+ "backbone.layers.33.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
281
+ "backbone.layers.33.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
282
+ "backbone.layers.33.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
283
+ "backbone.layers.33.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
284
+ "backbone.layers.33.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
285
+ "backbone.layers.33.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
286
+ "backbone.layers.33.norm.weight": "pytorch_model-00002-of-00002.bin",
287
+ "backbone.layers.34.mixer.A_log": "pytorch_model-00002-of-00002.bin",
288
+ "backbone.layers.34.mixer.D": "pytorch_model-00002-of-00002.bin",
289
+ "backbone.layers.34.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
290
+ "backbone.layers.34.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
291
+ "backbone.layers.34.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
292
+ "backbone.layers.34.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
293
+ "backbone.layers.34.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
294
+ "backbone.layers.34.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
295
+ "backbone.layers.34.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
296
+ "backbone.layers.34.norm.weight": "pytorch_model-00002-of-00002.bin",
297
+ "backbone.layers.35.mixer.A_log": "pytorch_model-00002-of-00002.bin",
298
+ "backbone.layers.35.mixer.D": "pytorch_model-00002-of-00002.bin",
299
+ "backbone.layers.35.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
300
+ "backbone.layers.35.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
301
+ "backbone.layers.35.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
302
+ "backbone.layers.35.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
303
+ "backbone.layers.35.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
304
+ "backbone.layers.35.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
305
+ "backbone.layers.35.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
306
+ "backbone.layers.35.norm.weight": "pytorch_model-00002-of-00002.bin",
307
+ "backbone.layers.36.mixer.A_log": "pytorch_model-00002-of-00002.bin",
308
+ "backbone.layers.36.mixer.D": "pytorch_model-00002-of-00002.bin",
309
+ "backbone.layers.36.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
310
+ "backbone.layers.36.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
311
+ "backbone.layers.36.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
312
+ "backbone.layers.36.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
313
+ "backbone.layers.36.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
314
+ "backbone.layers.36.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
315
+ "backbone.layers.36.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
316
+ "backbone.layers.36.norm.weight": "pytorch_model-00002-of-00002.bin",
317
+ "backbone.layers.37.mixer.A_log": "pytorch_model-00002-of-00002.bin",
318
+ "backbone.layers.37.mixer.D": "pytorch_model-00002-of-00002.bin",
319
+ "backbone.layers.37.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
320
+ "backbone.layers.37.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
321
+ "backbone.layers.37.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
322
+ "backbone.layers.37.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
323
+ "backbone.layers.37.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
324
+ "backbone.layers.37.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
325
+ "backbone.layers.37.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
326
+ "backbone.layers.37.norm.weight": "pytorch_model-00002-of-00002.bin",
327
+ "backbone.layers.38.mixer.A_log": "pytorch_model-00002-of-00002.bin",
328
+ "backbone.layers.38.mixer.D": "pytorch_model-00002-of-00002.bin",
329
+ "backbone.layers.38.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
330
+ "backbone.layers.38.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
331
+ "backbone.layers.38.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
332
+ "backbone.layers.38.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
333
+ "backbone.layers.38.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
334
+ "backbone.layers.38.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
335
+ "backbone.layers.38.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
336
+ "backbone.layers.38.norm.weight": "pytorch_model-00002-of-00002.bin",
337
+ "backbone.layers.39.mixer.A_log": "pytorch_model-00002-of-00002.bin",
338
+ "backbone.layers.39.mixer.D": "pytorch_model-00002-of-00002.bin",
339
+ "backbone.layers.39.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
340
+ "backbone.layers.39.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
341
+ "backbone.layers.39.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
342
+ "backbone.layers.39.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
343
+ "backbone.layers.39.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
344
+ "backbone.layers.39.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
345
+ "backbone.layers.39.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
346
+ "backbone.layers.39.norm.weight": "pytorch_model-00002-of-00002.bin",
347
+ "backbone.layers.4.mixer.A_log": "pytorch_model-00001-of-00002.bin",
348
+ "backbone.layers.4.mixer.D": "pytorch_model-00001-of-00002.bin",
349
+ "backbone.layers.4.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
350
+ "backbone.layers.4.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
351
+ "backbone.layers.4.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
352
+ "backbone.layers.4.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
353
+ "backbone.layers.4.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
354
+ "backbone.layers.4.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
355
+ "backbone.layers.4.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
356
+ "backbone.layers.4.norm.weight": "pytorch_model-00001-of-00002.bin",
357
+ "backbone.layers.40.mixer.A_log": "pytorch_model-00002-of-00002.bin",
358
+ "backbone.layers.40.mixer.D": "pytorch_model-00002-of-00002.bin",
359
+ "backbone.layers.40.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
360
+ "backbone.layers.40.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
361
+ "backbone.layers.40.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
362
+ "backbone.layers.40.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
363
+ "backbone.layers.40.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
364
+ "backbone.layers.40.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
365
+ "backbone.layers.40.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
366
+ "backbone.layers.40.norm.weight": "pytorch_model-00002-of-00002.bin",
367
+ "backbone.layers.41.mixer.A_log": "pytorch_model-00002-of-00002.bin",
368
+ "backbone.layers.41.mixer.D": "pytorch_model-00002-of-00002.bin",
369
+ "backbone.layers.41.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
370
+ "backbone.layers.41.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
371
+ "backbone.layers.41.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
372
+ "backbone.layers.41.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
373
+ "backbone.layers.41.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
374
+ "backbone.layers.41.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
375
+ "backbone.layers.41.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
376
+ "backbone.layers.41.norm.weight": "pytorch_model-00002-of-00002.bin",
377
+ "backbone.layers.42.mixer.A_log": "pytorch_model-00002-of-00002.bin",
378
+ "backbone.layers.42.mixer.D": "pytorch_model-00002-of-00002.bin",
379
+ "backbone.layers.42.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
380
+ "backbone.layers.42.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
381
+ "backbone.layers.42.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
382
+ "backbone.layers.42.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
383
+ "backbone.layers.42.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
384
+ "backbone.layers.42.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
385
+ "backbone.layers.42.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
386
+ "backbone.layers.42.norm.weight": "pytorch_model-00002-of-00002.bin",
387
+ "backbone.layers.43.mixer.A_log": "pytorch_model-00002-of-00002.bin",
388
+ "backbone.layers.43.mixer.D": "pytorch_model-00002-of-00002.bin",
389
+ "backbone.layers.43.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
390
+ "backbone.layers.43.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
391
+ "backbone.layers.43.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
392
+ "backbone.layers.43.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
393
+ "backbone.layers.43.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
394
+ "backbone.layers.43.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
395
+ "backbone.layers.43.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
396
+ "backbone.layers.43.norm.weight": "pytorch_model-00002-of-00002.bin",
397
+ "backbone.layers.44.mixer.A_log": "pytorch_model-00002-of-00002.bin",
398
+ "backbone.layers.44.mixer.D": "pytorch_model-00002-of-00002.bin",
399
+ "backbone.layers.44.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
400
+ "backbone.layers.44.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
401
+ "backbone.layers.44.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
402
+ "backbone.layers.44.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
403
+ "backbone.layers.44.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
404
+ "backbone.layers.44.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
405
+ "backbone.layers.44.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
406
+ "backbone.layers.44.norm.weight": "pytorch_model-00002-of-00002.bin",
407
+ "backbone.layers.45.mixer.A_log": "pytorch_model-00002-of-00002.bin",
408
+ "backbone.layers.45.mixer.D": "pytorch_model-00002-of-00002.bin",
409
+ "backbone.layers.45.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
410
+ "backbone.layers.45.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
411
+ "backbone.layers.45.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
412
+ "backbone.layers.45.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
413
+ "backbone.layers.45.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
414
+ "backbone.layers.45.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
415
+ "backbone.layers.45.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
416
+ "backbone.layers.45.norm.weight": "pytorch_model-00002-of-00002.bin",
417
+ "backbone.layers.46.mixer.A_log": "pytorch_model-00002-of-00002.bin",
418
+ "backbone.layers.46.mixer.D": "pytorch_model-00002-of-00002.bin",
419
+ "backbone.layers.46.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
420
+ "backbone.layers.46.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
421
+ "backbone.layers.46.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
422
+ "backbone.layers.46.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
423
+ "backbone.layers.46.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
424
+ "backbone.layers.46.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
425
+ "backbone.layers.46.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
426
+ "backbone.layers.46.norm.weight": "pytorch_model-00002-of-00002.bin",
427
+ "backbone.layers.47.mixer.A_log": "pytorch_model-00002-of-00002.bin",
428
+ "backbone.layers.47.mixer.D": "pytorch_model-00002-of-00002.bin",
429
+ "backbone.layers.47.mixer.conv1d.bias": "pytorch_model-00002-of-00002.bin",
430
+ "backbone.layers.47.mixer.conv1d.weight": "pytorch_model-00002-of-00002.bin",
431
+ "backbone.layers.47.mixer.dt_proj.bias": "pytorch_model-00002-of-00002.bin",
432
+ "backbone.layers.47.mixer.dt_proj.weight": "pytorch_model-00002-of-00002.bin",
433
+ "backbone.layers.47.mixer.in_proj.weight": "pytorch_model-00002-of-00002.bin",
434
+ "backbone.layers.47.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
435
+ "backbone.layers.47.mixer.x_proj.weight": "pytorch_model-00002-of-00002.bin",
436
+ "backbone.layers.47.norm.weight": "pytorch_model-00002-of-00002.bin",
437
+ "backbone.layers.5.mixer.A_log": "pytorch_model-00001-of-00002.bin",
438
+ "backbone.layers.5.mixer.D": "pytorch_model-00001-of-00002.bin",
439
+ "backbone.layers.5.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
440
+ "backbone.layers.5.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
441
+ "backbone.layers.5.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
442
+ "backbone.layers.5.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
443
+ "backbone.layers.5.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
444
+ "backbone.layers.5.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
445
+ "backbone.layers.5.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
446
+ "backbone.layers.5.norm.weight": "pytorch_model-00001-of-00002.bin",
447
+ "backbone.layers.6.mixer.A_log": "pytorch_model-00001-of-00002.bin",
448
+ "backbone.layers.6.mixer.D": "pytorch_model-00001-of-00002.bin",
449
+ "backbone.layers.6.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
450
+ "backbone.layers.6.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
451
+ "backbone.layers.6.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
452
+ "backbone.layers.6.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
453
+ "backbone.layers.6.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
454
+ "backbone.layers.6.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
455
+ "backbone.layers.6.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
456
+ "backbone.layers.6.norm.weight": "pytorch_model-00001-of-00002.bin",
457
+ "backbone.layers.7.mixer.A_log": "pytorch_model-00001-of-00002.bin",
458
+ "backbone.layers.7.mixer.D": "pytorch_model-00001-of-00002.bin",
459
+ "backbone.layers.7.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
460
+ "backbone.layers.7.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
461
+ "backbone.layers.7.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
462
+ "backbone.layers.7.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
463
+ "backbone.layers.7.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
464
+ "backbone.layers.7.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
465
+ "backbone.layers.7.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
466
+ "backbone.layers.7.norm.weight": "pytorch_model-00001-of-00002.bin",
467
+ "backbone.layers.8.mixer.A_log": "pytorch_model-00001-of-00002.bin",
468
+ "backbone.layers.8.mixer.D": "pytorch_model-00001-of-00002.bin",
469
+ "backbone.layers.8.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
470
+ "backbone.layers.8.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
471
+ "backbone.layers.8.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
472
+ "backbone.layers.8.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
473
+ "backbone.layers.8.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
474
+ "backbone.layers.8.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
475
+ "backbone.layers.8.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
476
+ "backbone.layers.8.norm.weight": "pytorch_model-00001-of-00002.bin",
477
+ "backbone.layers.9.mixer.A_log": "pytorch_model-00001-of-00002.bin",
478
+ "backbone.layers.9.mixer.D": "pytorch_model-00001-of-00002.bin",
479
+ "backbone.layers.9.mixer.conv1d.bias": "pytorch_model-00001-of-00002.bin",
480
+ "backbone.layers.9.mixer.conv1d.weight": "pytorch_model-00001-of-00002.bin",
481
+ "backbone.layers.9.mixer.dt_proj.bias": "pytorch_model-00001-of-00002.bin",
482
+ "backbone.layers.9.mixer.dt_proj.weight": "pytorch_model-00001-of-00002.bin",
483
+ "backbone.layers.9.mixer.in_proj.weight": "pytorch_model-00001-of-00002.bin",
484
+ "backbone.layers.9.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
485
+ "backbone.layers.9.mixer.x_proj.weight": "pytorch_model-00001-of-00002.bin",
486
+ "backbone.layers.9.norm.weight": "pytorch_model-00001-of-00002.bin",
487
+ "backbone.norm_f.weight": "pytorch_model-00002-of-00002.bin",
488
+ "lm_head.weight": "pytorch_model-00001-of-00002.bin"
489
+ }
490
+ }
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41cd6a88d2d7f809d13bb42dda010de83344837fa38fb584b22d32f177162581
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,214 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|padding|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "50254": {
23
+ "content": " ",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "50255": {
31
+ "content": " ",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "50256": {
39
+ "content": " ",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "50257": {
47
+ "content": " ",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "50258": {
55
+ "content": " ",
56
+ "lstrip": false,
57
+ "normalized": true,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "50259": {
63
+ "content": " ",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "50260": {
71
+ "content": " ",
72
+ "lstrip": false,
73
+ "normalized": true,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "50261": {
79
+ "content": " ",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "50262": {
87
+ "content": " ",
88
+ "lstrip": false,
89
+ "normalized": true,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "50263": {
95
+ "content": " ",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "50264": {
103
+ "content": " ",
104
+ "lstrip": false,
105
+ "normalized": true,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "50265": {
111
+ "content": " ",
112
+ "lstrip": false,
113
+ "normalized": true,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "50266": {
119
+ "content": " ",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "50267": {
127
+ "content": " ",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "50268": {
135
+ "content": " ",
136
+ "lstrip": false,
137
+ "normalized": true,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "50269": {
143
+ "content": " ",
144
+ "lstrip": false,
145
+ "normalized": true,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "50270": {
151
+ "content": " ",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "50271": {
159
+ "content": " ",
160
+ "lstrip": false,
161
+ "normalized": true,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "50272": {
167
+ "content": " ",
168
+ "lstrip": false,
169
+ "normalized": true,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "50273": {
175
+ "content": " ",
176
+ "lstrip": false,
177
+ "normalized": true,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "50274": {
183
+ "content": " ",
184
+ "lstrip": false,
185
+ "normalized": true,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "50275": {
191
+ "content": " ",
192
+ "lstrip": false,
193
+ "normalized": true,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "50276": {
199
+ "content": " ",
200
+ "lstrip": false,
201
+ "normalized": true,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ }
206
+ },
207
+ "bos_token": "<|endoftext|>",
208
+ "clean_up_tokenization_spaces": true,
209
+ "eos_token": "<|endoftext|>",
210
+ "model_max_length": 1000000000000000019884624838656,
211
+ "pad_token": "<|endoftext|>",
212
+ "tokenizer_class": "GPTNeoXTokenizer",
213
+ "unk_token": "<|endoftext|>"
214
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47947ad77b77f97c177fd9d7f8b1faa1906cfe44ebce02481444a2f0faa2fa96
3
+ size 5112