Upload folder using huggingface_hub

#1
README.md ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - mlx
5
+ base_model: state-spaces/mamba-1.4b-hf
6
+ ---
7
+
8
+ # mlx-community/mamba-1.4b-hf-f32
9
+
10
+ The Model [mlx-community/mamba-1.4b-hf-f32](https://huggingface.co/mlx-community/mamba-1.4b-hf-f32) was converted to MLX format from [state-spaces/mamba-1.4b-hf](https://huggingface.co/state-spaces/mamba-1.4b-hf) using mlx-lm version **0.18.1**.
11
+
12
+ ## Use with mlx
13
+
14
+ ```bash
15
+ pip install mlx-lm
16
+ ```
17
+
18
+ ```python
19
+ from mlx_lm import load, generate
20
+
21
+ model, tokenizer = load("mlx-community/mamba-1.4b-hf-f32")
22
+ response = generate(model, tokenizer, prompt="hello", verbose=True)
23
+ ```
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MambaForCausalLM"
4
+ ],
5
+ "bos_token_id": 0,
6
+ "conv_kernel": 4,
7
+ "d_model": 2048,
8
+ "eos_token_id": 0,
9
+ "expand": 2,
10
+ "fused_add_norm": true,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.1,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_epsilon": 1e-05,
16
+ "model_type": "mamba",
17
+ "n_layer": 48,
18
+ "num_hidden_layers": 48,
19
+ "pad_token_id": 0,
20
+ "pad_vocab_size_multiple": 8,
21
+ "rescale_prenorm_residual": false,
22
+ "residual_in_fp32": true,
23
+ "rms_norm": true,
24
+ "ssm_cfg": {},
25
+ "state_size": 16,
26
+ "time_step_floor": 0.0001,
27
+ "time_step_init_scheme": "random",
28
+ "time_step_max": 0.1,
29
+ "time_step_min": 0.001,
30
+ "time_step_rank": 128,
31
+ "time_step_scale": 1.0,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.39.0.dev0",
34
+ "use_bias": false,
35
+ "use_cache": true,
36
+ "use_conv_bias": true,
37
+ "vocab_size": 50280
38
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23357f32a269e9238df22bbd624681e904bc48697eedc8f5d2a5f7c30e5a6c46
3
+ size 5349427668
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af9d9540c4629ac11cda8d7a72c017715834392bc16dc1e2ce62214f696b674e
3
+ size 139339131
model.safetensors.index.json ADDED
@@ -0,0 +1,489 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5488713728
4
+ },
5
+ "weight_map": {
6
+ "backbone.embeddings.weight": "model-00001-of-00002.safetensors",
7
+ "backbone.layers.0.mixer.A_log": "model-00001-of-00002.safetensors",
8
+ "backbone.layers.0.mixer.D": "model-00001-of-00002.safetensors",
9
+ "backbone.layers.0.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
10
+ "backbone.layers.0.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
11
+ "backbone.layers.0.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
12
+ "backbone.layers.0.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
13
+ "backbone.layers.0.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
14
+ "backbone.layers.0.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
15
+ "backbone.layers.0.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
16
+ "backbone.layers.0.norm.weight": "model-00001-of-00002.safetensors",
17
+ "backbone.layers.1.mixer.A_log": "model-00001-of-00002.safetensors",
18
+ "backbone.layers.1.mixer.D": "model-00001-of-00002.safetensors",
19
+ "backbone.layers.1.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
20
+ "backbone.layers.1.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
21
+ "backbone.layers.1.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
22
+ "backbone.layers.1.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
23
+ "backbone.layers.1.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
24
+ "backbone.layers.1.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
25
+ "backbone.layers.1.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
26
+ "backbone.layers.1.norm.weight": "model-00001-of-00002.safetensors",
27
+ "backbone.layers.10.mixer.A_log": "model-00001-of-00002.safetensors",
28
+ "backbone.layers.10.mixer.D": "model-00001-of-00002.safetensors",
29
+ "backbone.layers.10.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
30
+ "backbone.layers.10.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
31
+ "backbone.layers.10.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
32
+ "backbone.layers.10.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
33
+ "backbone.layers.10.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
34
+ "backbone.layers.10.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
35
+ "backbone.layers.10.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
36
+ "backbone.layers.10.norm.weight": "model-00001-of-00002.safetensors",
37
+ "backbone.layers.11.mixer.A_log": "model-00001-of-00002.safetensors",
38
+ "backbone.layers.11.mixer.D": "model-00001-of-00002.safetensors",
39
+ "backbone.layers.11.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
40
+ "backbone.layers.11.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
41
+ "backbone.layers.11.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
42
+ "backbone.layers.11.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
43
+ "backbone.layers.11.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
44
+ "backbone.layers.11.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
45
+ "backbone.layers.11.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
46
+ "backbone.layers.11.norm.weight": "model-00001-of-00002.safetensors",
47
+ "backbone.layers.12.mixer.A_log": "model-00001-of-00002.safetensors",
48
+ "backbone.layers.12.mixer.D": "model-00001-of-00002.safetensors",
49
+ "backbone.layers.12.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
50
+ "backbone.layers.12.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
51
+ "backbone.layers.12.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
52
+ "backbone.layers.12.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
53
+ "backbone.layers.12.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
54
+ "backbone.layers.12.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
55
+ "backbone.layers.12.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
56
+ "backbone.layers.12.norm.weight": "model-00001-of-00002.safetensors",
57
+ "backbone.layers.13.mixer.A_log": "model-00001-of-00002.safetensors",
58
+ "backbone.layers.13.mixer.D": "model-00001-of-00002.safetensors",
59
+ "backbone.layers.13.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
60
+ "backbone.layers.13.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
61
+ "backbone.layers.13.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
62
+ "backbone.layers.13.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
63
+ "backbone.layers.13.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
64
+ "backbone.layers.13.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
65
+ "backbone.layers.13.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
66
+ "backbone.layers.13.norm.weight": "model-00001-of-00002.safetensors",
67
+ "backbone.layers.14.mixer.A_log": "model-00001-of-00002.safetensors",
68
+ "backbone.layers.14.mixer.D": "model-00001-of-00002.safetensors",
69
+ "backbone.layers.14.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
70
+ "backbone.layers.14.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
71
+ "backbone.layers.14.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
72
+ "backbone.layers.14.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
73
+ "backbone.layers.14.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
74
+ "backbone.layers.14.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
75
+ "backbone.layers.14.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
76
+ "backbone.layers.14.norm.weight": "model-00001-of-00002.safetensors",
77
+ "backbone.layers.15.mixer.A_log": "model-00001-of-00002.safetensors",
78
+ "backbone.layers.15.mixer.D": "model-00001-of-00002.safetensors",
79
+ "backbone.layers.15.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
80
+ "backbone.layers.15.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
81
+ "backbone.layers.15.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
82
+ "backbone.layers.15.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
83
+ "backbone.layers.15.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
84
+ "backbone.layers.15.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
85
+ "backbone.layers.15.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
86
+ "backbone.layers.15.norm.weight": "model-00001-of-00002.safetensors",
87
+ "backbone.layers.16.mixer.A_log": "model-00001-of-00002.safetensors",
88
+ "backbone.layers.16.mixer.D": "model-00001-of-00002.safetensors",
89
+ "backbone.layers.16.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
90
+ "backbone.layers.16.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
91
+ "backbone.layers.16.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
92
+ "backbone.layers.16.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
93
+ "backbone.layers.16.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
94
+ "backbone.layers.16.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
95
+ "backbone.layers.16.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
96
+ "backbone.layers.16.norm.weight": "model-00001-of-00002.safetensors",
97
+ "backbone.layers.17.mixer.A_log": "model-00001-of-00002.safetensors",
98
+ "backbone.layers.17.mixer.D": "model-00001-of-00002.safetensors",
99
+ "backbone.layers.17.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
100
+ "backbone.layers.17.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
101
+ "backbone.layers.17.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
102
+ "backbone.layers.17.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
103
+ "backbone.layers.17.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
104
+ "backbone.layers.17.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
105
+ "backbone.layers.17.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
106
+ "backbone.layers.17.norm.weight": "model-00001-of-00002.safetensors",
107
+ "backbone.layers.18.mixer.A_log": "model-00001-of-00002.safetensors",
108
+ "backbone.layers.18.mixer.D": "model-00001-of-00002.safetensors",
109
+ "backbone.layers.18.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
110
+ "backbone.layers.18.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
111
+ "backbone.layers.18.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
112
+ "backbone.layers.18.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
113
+ "backbone.layers.18.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
114
+ "backbone.layers.18.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
115
+ "backbone.layers.18.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
116
+ "backbone.layers.18.norm.weight": "model-00001-of-00002.safetensors",
117
+ "backbone.layers.19.mixer.A_log": "model-00001-of-00002.safetensors",
118
+ "backbone.layers.19.mixer.D": "model-00001-of-00002.safetensors",
119
+ "backbone.layers.19.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
120
+ "backbone.layers.19.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
121
+ "backbone.layers.19.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
122
+ "backbone.layers.19.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
123
+ "backbone.layers.19.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
124
+ "backbone.layers.19.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
125
+ "backbone.layers.19.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
126
+ "backbone.layers.19.norm.weight": "model-00001-of-00002.safetensors",
127
+ "backbone.layers.2.mixer.A_log": "model-00001-of-00002.safetensors",
128
+ "backbone.layers.2.mixer.D": "model-00001-of-00002.safetensors",
129
+ "backbone.layers.2.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
130
+ "backbone.layers.2.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
131
+ "backbone.layers.2.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
132
+ "backbone.layers.2.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
133
+ "backbone.layers.2.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
134
+ "backbone.layers.2.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
135
+ "backbone.layers.2.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
136
+ "backbone.layers.2.norm.weight": "model-00001-of-00002.safetensors",
137
+ "backbone.layers.20.mixer.A_log": "model-00001-of-00002.safetensors",
138
+ "backbone.layers.20.mixer.D": "model-00001-of-00002.safetensors",
139
+ "backbone.layers.20.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
140
+ "backbone.layers.20.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
141
+ "backbone.layers.20.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
142
+ "backbone.layers.20.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
143
+ "backbone.layers.20.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
144
+ "backbone.layers.20.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
145
+ "backbone.layers.20.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
146
+ "backbone.layers.20.norm.weight": "model-00001-of-00002.safetensors",
147
+ "backbone.layers.21.mixer.A_log": "model-00001-of-00002.safetensors",
148
+ "backbone.layers.21.mixer.D": "model-00001-of-00002.safetensors",
149
+ "backbone.layers.21.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
150
+ "backbone.layers.21.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
151
+ "backbone.layers.21.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
152
+ "backbone.layers.21.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
153
+ "backbone.layers.21.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
154
+ "backbone.layers.21.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
155
+ "backbone.layers.21.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
156
+ "backbone.layers.21.norm.weight": "model-00001-of-00002.safetensors",
157
+ "backbone.layers.22.mixer.A_log": "model-00001-of-00002.safetensors",
158
+ "backbone.layers.22.mixer.D": "model-00001-of-00002.safetensors",
159
+ "backbone.layers.22.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
160
+ "backbone.layers.22.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
161
+ "backbone.layers.22.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
162
+ "backbone.layers.22.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
163
+ "backbone.layers.22.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
164
+ "backbone.layers.22.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
165
+ "backbone.layers.22.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
166
+ "backbone.layers.22.norm.weight": "model-00001-of-00002.safetensors",
167
+ "backbone.layers.23.mixer.A_log": "model-00001-of-00002.safetensors",
168
+ "backbone.layers.23.mixer.D": "model-00001-of-00002.safetensors",
169
+ "backbone.layers.23.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
170
+ "backbone.layers.23.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
171
+ "backbone.layers.23.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
172
+ "backbone.layers.23.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
173
+ "backbone.layers.23.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
174
+ "backbone.layers.23.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
175
+ "backbone.layers.23.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
176
+ "backbone.layers.23.norm.weight": "model-00001-of-00002.safetensors",
177
+ "backbone.layers.24.mixer.A_log": "model-00001-of-00002.safetensors",
178
+ "backbone.layers.24.mixer.D": "model-00001-of-00002.safetensors",
179
+ "backbone.layers.24.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
180
+ "backbone.layers.24.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
181
+ "backbone.layers.24.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
182
+ "backbone.layers.24.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
183
+ "backbone.layers.24.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
184
+ "backbone.layers.24.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
185
+ "backbone.layers.24.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
186
+ "backbone.layers.24.norm.weight": "model-00001-of-00002.safetensors",
187
+ "backbone.layers.25.mixer.A_log": "model-00001-of-00002.safetensors",
188
+ "backbone.layers.25.mixer.D": "model-00001-of-00002.safetensors",
189
+ "backbone.layers.25.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
190
+ "backbone.layers.25.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
191
+ "backbone.layers.25.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
192
+ "backbone.layers.25.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
193
+ "backbone.layers.25.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
194
+ "backbone.layers.25.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
195
+ "backbone.layers.25.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
196
+ "backbone.layers.25.norm.weight": "model-00001-of-00002.safetensors",
197
+ "backbone.layers.26.mixer.A_log": "model-00001-of-00002.safetensors",
198
+ "backbone.layers.26.mixer.D": "model-00001-of-00002.safetensors",
199
+ "backbone.layers.26.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
200
+ "backbone.layers.26.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
201
+ "backbone.layers.26.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
202
+ "backbone.layers.26.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
203
+ "backbone.layers.26.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
204
+ "backbone.layers.26.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
205
+ "backbone.layers.26.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
206
+ "backbone.layers.26.norm.weight": "model-00001-of-00002.safetensors",
207
+ "backbone.layers.27.mixer.A_log": "model-00001-of-00002.safetensors",
208
+ "backbone.layers.27.mixer.D": "model-00001-of-00002.safetensors",
209
+ "backbone.layers.27.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
210
+ "backbone.layers.27.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
211
+ "backbone.layers.27.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
212
+ "backbone.layers.27.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
213
+ "backbone.layers.27.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
214
+ "backbone.layers.27.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
215
+ "backbone.layers.27.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
216
+ "backbone.layers.27.norm.weight": "model-00001-of-00002.safetensors",
217
+ "backbone.layers.28.mixer.A_log": "model-00001-of-00002.safetensors",
218
+ "backbone.layers.28.mixer.D": "model-00001-of-00002.safetensors",
219
+ "backbone.layers.28.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
220
+ "backbone.layers.28.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
221
+ "backbone.layers.28.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
222
+ "backbone.layers.28.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
223
+ "backbone.layers.28.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
224
+ "backbone.layers.28.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
225
+ "backbone.layers.28.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
226
+ "backbone.layers.28.norm.weight": "model-00001-of-00002.safetensors",
227
+ "backbone.layers.29.mixer.A_log": "model-00001-of-00002.safetensors",
228
+ "backbone.layers.29.mixer.D": "model-00001-of-00002.safetensors",
229
+ "backbone.layers.29.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
230
+ "backbone.layers.29.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
231
+ "backbone.layers.29.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
232
+ "backbone.layers.29.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
233
+ "backbone.layers.29.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
234
+ "backbone.layers.29.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
235
+ "backbone.layers.29.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
236
+ "backbone.layers.29.norm.weight": "model-00001-of-00002.safetensors",
237
+ "backbone.layers.3.mixer.A_log": "model-00001-of-00002.safetensors",
238
+ "backbone.layers.3.mixer.D": "model-00001-of-00002.safetensors",
239
+ "backbone.layers.3.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
240
+ "backbone.layers.3.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
241
+ "backbone.layers.3.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
242
+ "backbone.layers.3.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
243
+ "backbone.layers.3.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
244
+ "backbone.layers.3.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
245
+ "backbone.layers.3.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
246
+ "backbone.layers.3.norm.weight": "model-00001-of-00002.safetensors",
247
+ "backbone.layers.30.mixer.A_log": "model-00001-of-00002.safetensors",
248
+ "backbone.layers.30.mixer.D": "model-00001-of-00002.safetensors",
249
+ "backbone.layers.30.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
250
+ "backbone.layers.30.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
251
+ "backbone.layers.30.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
252
+ "backbone.layers.30.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
253
+ "backbone.layers.30.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
254
+ "backbone.layers.30.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
255
+ "backbone.layers.30.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
256
+ "backbone.layers.30.norm.weight": "model-00001-of-00002.safetensors",
257
+ "backbone.layers.31.mixer.A_log": "model-00001-of-00002.safetensors",
258
+ "backbone.layers.31.mixer.D": "model-00001-of-00002.safetensors",
259
+ "backbone.layers.31.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
260
+ "backbone.layers.31.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
261
+ "backbone.layers.31.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
262
+ "backbone.layers.31.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
263
+ "backbone.layers.31.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
264
+ "backbone.layers.31.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
265
+ "backbone.layers.31.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
266
+ "backbone.layers.31.norm.weight": "model-00001-of-00002.safetensors",
267
+ "backbone.layers.32.mixer.A_log": "model-00001-of-00002.safetensors",
268
+ "backbone.layers.32.mixer.D": "model-00001-of-00002.safetensors",
269
+ "backbone.layers.32.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
270
+ "backbone.layers.32.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
271
+ "backbone.layers.32.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
272
+ "backbone.layers.32.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
273
+ "backbone.layers.32.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
274
+ "backbone.layers.32.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
275
+ "backbone.layers.32.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
276
+ "backbone.layers.32.norm.weight": "model-00001-of-00002.safetensors",
277
+ "backbone.layers.33.mixer.A_log": "model-00001-of-00002.safetensors",
278
+ "backbone.layers.33.mixer.D": "model-00001-of-00002.safetensors",
279
+ "backbone.layers.33.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
280
+ "backbone.layers.33.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
281
+ "backbone.layers.33.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
282
+ "backbone.layers.33.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
283
+ "backbone.layers.33.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
284
+ "backbone.layers.33.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
285
+ "backbone.layers.33.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
286
+ "backbone.layers.33.norm.weight": "model-00001-of-00002.safetensors",
287
+ "backbone.layers.34.mixer.A_log": "model-00001-of-00002.safetensors",
288
+ "backbone.layers.34.mixer.D": "model-00001-of-00002.safetensors",
289
+ "backbone.layers.34.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
290
+ "backbone.layers.34.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
291
+ "backbone.layers.34.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
292
+ "backbone.layers.34.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
293
+ "backbone.layers.34.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
294
+ "backbone.layers.34.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
295
+ "backbone.layers.34.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
296
+ "backbone.layers.34.norm.weight": "model-00001-of-00002.safetensors",
297
+ "backbone.layers.35.mixer.A_log": "model-00001-of-00002.safetensors",
298
+ "backbone.layers.35.mixer.D": "model-00001-of-00002.safetensors",
299
+ "backbone.layers.35.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
300
+ "backbone.layers.35.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
301
+ "backbone.layers.35.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
302
+ "backbone.layers.35.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
303
+ "backbone.layers.35.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
304
+ "backbone.layers.35.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
305
+ "backbone.layers.35.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
306
+ "backbone.layers.35.norm.weight": "model-00001-of-00002.safetensors",
307
+ "backbone.layers.36.mixer.A_log": "model-00001-of-00002.safetensors",
308
+ "backbone.layers.36.mixer.D": "model-00001-of-00002.safetensors",
309
+ "backbone.layers.36.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
310
+ "backbone.layers.36.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
311
+ "backbone.layers.36.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
312
+ "backbone.layers.36.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
313
+ "backbone.layers.36.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
314
+ "backbone.layers.36.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
315
+ "backbone.layers.36.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
316
+ "backbone.layers.36.norm.weight": "model-00001-of-00002.safetensors",
317
+ "backbone.layers.37.mixer.A_log": "model-00001-of-00002.safetensors",
318
+ "backbone.layers.37.mixer.D": "model-00001-of-00002.safetensors",
319
+ "backbone.layers.37.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
320
+ "backbone.layers.37.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
321
+ "backbone.layers.37.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
322
+ "backbone.layers.37.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
323
+ "backbone.layers.37.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
324
+ "backbone.layers.37.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
325
+ "backbone.layers.37.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
326
+ "backbone.layers.37.norm.weight": "model-00001-of-00002.safetensors",
327
+ "backbone.layers.38.mixer.A_log": "model-00001-of-00002.safetensors",
328
+ "backbone.layers.38.mixer.D": "model-00001-of-00002.safetensors",
329
+ "backbone.layers.38.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
330
+ "backbone.layers.38.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
331
+ "backbone.layers.38.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
332
+ "backbone.layers.38.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
333
+ "backbone.layers.38.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
334
+ "backbone.layers.38.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
335
+ "backbone.layers.38.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
336
+ "backbone.layers.38.norm.weight": "model-00001-of-00002.safetensors",
337
+ "backbone.layers.39.mixer.A_log": "model-00001-of-00002.safetensors",
338
+ "backbone.layers.39.mixer.D": "model-00001-of-00002.safetensors",
339
+ "backbone.layers.39.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
340
+ "backbone.layers.39.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
341
+ "backbone.layers.39.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
342
+ "backbone.layers.39.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
343
+ "backbone.layers.39.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
344
+ "backbone.layers.39.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
345
+ "backbone.layers.39.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
346
+ "backbone.layers.39.norm.weight": "model-00001-of-00002.safetensors",
347
+ "backbone.layers.4.mixer.A_log": "model-00001-of-00002.safetensors",
348
+ "backbone.layers.4.mixer.D": "model-00001-of-00002.safetensors",
349
+ "backbone.layers.4.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
350
+ "backbone.layers.4.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
351
+ "backbone.layers.4.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
352
+ "backbone.layers.4.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
353
+ "backbone.layers.4.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
354
+ "backbone.layers.4.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
355
+ "backbone.layers.4.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
356
+ "backbone.layers.4.norm.weight": "model-00001-of-00002.safetensors",
357
+ "backbone.layers.40.mixer.A_log": "model-00001-of-00002.safetensors",
358
+ "backbone.layers.40.mixer.D": "model-00001-of-00002.safetensors",
359
+ "backbone.layers.40.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
360
+ "backbone.layers.40.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
361
+ "backbone.layers.40.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
362
+ "backbone.layers.40.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
363
+ "backbone.layers.40.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
364
+ "backbone.layers.40.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
365
+ "backbone.layers.40.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
366
+ "backbone.layers.40.norm.weight": "model-00001-of-00002.safetensors",
367
+ "backbone.layers.41.mixer.A_log": "model-00001-of-00002.safetensors",
368
+ "backbone.layers.41.mixer.D": "model-00001-of-00002.safetensors",
369
+ "backbone.layers.41.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
370
+ "backbone.layers.41.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
371
+ "backbone.layers.41.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
372
+ "backbone.layers.41.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
373
+ "backbone.layers.41.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
374
+ "backbone.layers.41.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
375
+ "backbone.layers.41.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
376
+ "backbone.layers.41.norm.weight": "model-00001-of-00002.safetensors",
377
+ "backbone.layers.42.mixer.A_log": "model-00001-of-00002.safetensors",
378
+ "backbone.layers.42.mixer.D": "model-00001-of-00002.safetensors",
379
+ "backbone.layers.42.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
380
+ "backbone.layers.42.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
381
+ "backbone.layers.42.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
382
+ "backbone.layers.42.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
383
+ "backbone.layers.42.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
384
+ "backbone.layers.42.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
385
+ "backbone.layers.42.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
386
+ "backbone.layers.42.norm.weight": "model-00001-of-00002.safetensors",
387
+ "backbone.layers.43.mixer.A_log": "model-00001-of-00002.safetensors",
388
+ "backbone.layers.43.mixer.D": "model-00001-of-00002.safetensors",
389
+ "backbone.layers.43.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
390
+ "backbone.layers.43.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
391
+ "backbone.layers.43.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
392
+ "backbone.layers.43.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
393
+ "backbone.layers.43.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
394
+ "backbone.layers.43.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
395
+ "backbone.layers.43.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
396
+ "backbone.layers.43.norm.weight": "model-00001-of-00002.safetensors",
397
+ "backbone.layers.44.mixer.A_log": "model-00001-of-00002.safetensors",
398
+ "backbone.layers.44.mixer.D": "model-00001-of-00002.safetensors",
399
+ "backbone.layers.44.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
400
+ "backbone.layers.44.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
401
+ "backbone.layers.44.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
402
+ "backbone.layers.44.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
403
+ "backbone.layers.44.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
404
+ "backbone.layers.44.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
405
+ "backbone.layers.44.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
406
+ "backbone.layers.44.norm.weight": "model-00001-of-00002.safetensors",
407
+ "backbone.layers.45.mixer.A_log": "model-00001-of-00002.safetensors",
408
+ "backbone.layers.45.mixer.D": "model-00001-of-00002.safetensors",
409
+ "backbone.layers.45.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
410
+ "backbone.layers.45.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
411
+ "backbone.layers.45.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
412
+ "backbone.layers.45.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
413
+ "backbone.layers.45.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
414
+ "backbone.layers.45.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
415
+ "backbone.layers.45.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
416
+ "backbone.layers.45.norm.weight": "model-00001-of-00002.safetensors",
417
+ "backbone.layers.46.mixer.A_log": "model-00001-of-00002.safetensors",
418
+ "backbone.layers.46.mixer.D": "model-00001-of-00002.safetensors",
419
+ "backbone.layers.46.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
420
+ "backbone.layers.46.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
421
+ "backbone.layers.46.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
422
+ "backbone.layers.46.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
423
+ "backbone.layers.46.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
424
+ "backbone.layers.46.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
425
+ "backbone.layers.46.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
426
+ "backbone.layers.46.norm.weight": "model-00002-of-00002.safetensors",
427
+ "backbone.layers.47.mixer.A_log": "model-00002-of-00002.safetensors",
428
+ "backbone.layers.47.mixer.D": "model-00002-of-00002.safetensors",
429
+ "backbone.layers.47.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
430
+ "backbone.layers.47.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
431
+ "backbone.layers.47.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
432
+ "backbone.layers.47.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
433
+ "backbone.layers.47.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
434
+ "backbone.layers.47.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
435
+ "backbone.layers.47.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
436
+ "backbone.layers.47.norm.weight": "model-00002-of-00002.safetensors",
437
+ "backbone.layers.5.mixer.A_log": "model-00001-of-00002.safetensors",
438
+ "backbone.layers.5.mixer.D": "model-00001-of-00002.safetensors",
439
+ "backbone.layers.5.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
440
+ "backbone.layers.5.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
441
+ "backbone.layers.5.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
442
+ "backbone.layers.5.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
443
+ "backbone.layers.5.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
444
+ "backbone.layers.5.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
445
+ "backbone.layers.5.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
446
+ "backbone.layers.5.norm.weight": "model-00001-of-00002.safetensors",
447
+ "backbone.layers.6.mixer.A_log": "model-00001-of-00002.safetensors",
448
+ "backbone.layers.6.mixer.D": "model-00001-of-00002.safetensors",
449
+ "backbone.layers.6.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
450
+ "backbone.layers.6.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
451
+ "backbone.layers.6.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
452
+ "backbone.layers.6.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
453
+ "backbone.layers.6.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
454
+ "backbone.layers.6.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
455
+ "backbone.layers.6.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
456
+ "backbone.layers.6.norm.weight": "model-00001-of-00002.safetensors",
457
+ "backbone.layers.7.mixer.A_log": "model-00001-of-00002.safetensors",
458
+ "backbone.layers.7.mixer.D": "model-00001-of-00002.safetensors",
459
+ "backbone.layers.7.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
460
+ "backbone.layers.7.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
461
+ "backbone.layers.7.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
462
+ "backbone.layers.7.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
463
+ "backbone.layers.7.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
464
+ "backbone.layers.7.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
465
+ "backbone.layers.7.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
466
+ "backbone.layers.7.norm.weight": "model-00001-of-00002.safetensors",
467
+ "backbone.layers.8.mixer.A_log": "model-00001-of-00002.safetensors",
468
+ "backbone.layers.8.mixer.D": "model-00001-of-00002.safetensors",
469
+ "backbone.layers.8.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
470
+ "backbone.layers.8.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
471
+ "backbone.layers.8.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
472
+ "backbone.layers.8.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
473
+ "backbone.layers.8.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
474
+ "backbone.layers.8.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
475
+ "backbone.layers.8.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
476
+ "backbone.layers.8.norm.weight": "model-00001-of-00002.safetensors",
477
+ "backbone.layers.9.mixer.A_log": "model-00001-of-00002.safetensors",
478
+ "backbone.layers.9.mixer.D": "model-00001-of-00002.safetensors",
479
+ "backbone.layers.9.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
480
+ "backbone.layers.9.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
481
+ "backbone.layers.9.mixer.dt_proj.bias": "model-00001-of-00002.safetensors",
482
+ "backbone.layers.9.mixer.dt_proj.weight": "model-00001-of-00002.safetensors",
483
+ "backbone.layers.9.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
484
+ "backbone.layers.9.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
485
+ "backbone.layers.9.mixer.x_proj.weight": "model-00001-of-00002.safetensors",
486
+ "backbone.layers.9.norm.weight": "model-00001-of-00002.safetensors",
487
+ "backbone.norm_f.weight": "model-00002-of-00002.safetensors"
488
+ }
489
+ }
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
+ }