Text Generation
Transformers
Safetensors
PyTorch
nvidia
conversational
8-bit precision
suhara commited on
Commit
b580bef
·
verified ·
1 Parent(s): 30fa227

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "NemotronHForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "nvidia/NVIDIA-Nemotron-Nano-9B-v2--configuration_nemotron_h.NemotronHConfig",
9
+ "AutoModelForCausalLM": "nvidia/NVIDIA-Nemotron-Nano-9B-v2--modeling_nemotron_h.NemotronHForCausalLM"
10
+ },
11
+ "bos_token_id": 1,
12
+ "chunk_size": 128,
13
+ "conv_kernel": 4,
14
+ "eos_token_id": 12,
15
+ "expand": 2,
16
+ "head_dim": 128,
17
+ "hidden_dropout": 0.0,
18
+ "hidden_size": 4480,
19
+ "hybrid_override_pattern": "M-M-M-MM-M-M-M*-M-M-M*-M-M-M-M*-M-M-M-M*-M-MM-M-M-M-M-M-",
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 15680,
22
+ "layer_norm_epsilon": 1e-05,
23
+ "mamba_head_dim": 80,
24
+ "mamba_hidden_act": "silu",
25
+ "mamba_num_groups": 8,
26
+ "mamba_num_heads": 128,
27
+ "mamba_proj_bias": false,
28
+ "mamba_state_dim": 128,
29
+ "max_position_embeddings": 131072,
30
+ "mlp_bias": false,
31
+ "mlp_hidden_act": "relu2",
32
+ "model_type": "nemotron_h",
33
+ "n_groups": 8,
34
+ "num_attention_heads": 40,
35
+ "num_hidden_layers": 56,
36
+ "num_key_value_heads": 8,
37
+ "num_logits_to_keep": 1,
38
+ "num_query_groups": 8,
39
+ "pad_token_id": 0,
40
+ "rescale_prenorm_residual": true,
41
+ "residual_in_fp32": false,
42
+ "rms_norm_eps": 1e-05,
43
+ "sliding_window": null,
44
+ "ssm_state_size": 128,
45
+ "tie_word_embeddings": false,
46
+ "time_step_floor": 0.0001,
47
+ "time_step_limit": [
48
+ 0.0,
49
+ Infinity
50
+ ],
51
+ "time_step_max": 0.1,
52
+ "time_step_min": 0.001,
53
+ "time_step_rank": 256,
54
+ "torch_dtype": "bfloat16",
55
+ "transformers_version": "4.51.3",
56
+ "use_bias": false,
57
+ "use_cache": true,
58
+ "use_conv_bias": true,
59
+ "use_mamba_kernels": true,
60
+ "vocab_size": 131072
61
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 2,
6
+ 11,
7
+ 12
8
+ ],
9
+ "pad_token_id": 0,
10
+ "transformers_version": "4.51.3"
11
+ }
hf_quant_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "producer": {
3
+ "name": "modelopt",
4
+ "version": "0.34.1.dev141+g5db6ea47c"
5
+ },
6
+ "quantization": {
7
+ "quant_algo": "NVFP4",
8
+ "kv_cache_quant_algo": null,
9
+ "group_size": 16,
10
+ "exclude_modules": [
11
+ "lm_head",
12
+ "backbone.layers.0.mixer.in_proj",
13
+ "backbone.layers.0.mixer.out_proj",
14
+ "backbone.layers.1.mixer.up_proj",
15
+ "backbone.layers.1.mixer.down_proj",
16
+ "backbone.layers.54.mixer.in_proj",
17
+ "backbone.layers.54.mixer.out_proj",
18
+ "backbone.layers.55.mixer.up_proj",
19
+ "backbone.layers.55.mixer.down_proj",
20
+ "backbone.layers.0.mixer.conv1d",
21
+ "backbone.layers.2.mixer.conv1d",
22
+ "backbone.layers.4.mixer.conv1d",
23
+ "backbone.layers.6.mixer.conv1d",
24
+ "backbone.layers.7.mixer.conv1d",
25
+ "backbone.layers.9.mixer.conv1d",
26
+ "backbone.layers.11.mixer.conv1d",
27
+ "backbone.layers.13.mixer.conv1d",
28
+ "backbone.layers.14.mixer.q_proj",
29
+ "backbone.layers.14.mixer.k_proj",
30
+ "backbone.layers.14.mixer.v_proj",
31
+ "backbone.layers.14.mixer.o_proj",
32
+ "backbone.layers.16.mixer.conv1d",
33
+ "backbone.layers.18.mixer.conv1d",
34
+ "backbone.layers.20.mixer.conv1d",
35
+ "backbone.layers.21.mixer.q_proj",
36
+ "backbone.layers.21.mixer.k_proj",
37
+ "backbone.layers.21.mixer.v_proj",
38
+ "backbone.layers.21.mixer.o_proj",
39
+ "backbone.layers.23.mixer.conv1d",
40
+ "backbone.layers.25.mixer.conv1d",
41
+ "backbone.layers.27.mixer.conv1d",
42
+ "backbone.layers.29.mixer.conv1d",
43
+ "backbone.layers.30.mixer.q_proj",
44
+ "backbone.layers.30.mixer.k_proj",
45
+ "backbone.layers.30.mixer.v_proj",
46
+ "backbone.layers.30.mixer.o_proj",
47
+ "backbone.layers.32.mixer.conv1d",
48
+ "backbone.layers.34.mixer.conv1d",
49
+ "backbone.layers.36.mixer.conv1d",
50
+ "backbone.layers.38.mixer.conv1d",
51
+ "backbone.layers.39.mixer.q_proj",
52
+ "backbone.layers.39.mixer.k_proj",
53
+ "backbone.layers.39.mixer.v_proj",
54
+ "backbone.layers.39.mixer.o_proj",
55
+ "backbone.layers.41.mixer.conv1d",
56
+ "backbone.layers.43.mixer.conv1d",
57
+ "backbone.layers.44.mixer.conv1d",
58
+ "backbone.layers.46.mixer.conv1d",
59
+ "backbone.layers.48.mixer.conv1d",
60
+ "backbone.layers.50.mixer.conv1d",
61
+ "backbone.layers.52.mixer.conv1d",
62
+ "backbone.layers.54.mixer.conv1d"
63
+ ]
64
+ }
65
+ }
model-00001-of-00010.json ADDED
@@ -0,0 +1,176 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 3965487296
4
+ },
5
+ "weight_map": {
6
+ "backbone.embeddings.weight": "model-00001-of-00010.safetensors",
7
+ "backbone.norm_f.weight": "model-00001-of-00010.safetensors",
8
+ "lm_head.weight": "model-00001-of-00010.safetensors",
9
+ "backbone.layers.0.norm.weight": "model-00001-of-00010.safetensors",
10
+ "backbone.layers.0.mixer.norm.weight": "model-00001-of-00010.safetensors",
11
+ "backbone.layers.0.mixer.A_log": "model-00001-of-00010.safetensors",
12
+ "backbone.layers.0.mixer.D": "model-00001-of-00010.safetensors",
13
+ "backbone.layers.0.mixer.dt_bias": "model-00001-of-00010.safetensors",
14
+ "backbone.layers.0.mixer.conv1d.weight": "model-00001-of-00010.safetensors",
15
+ "backbone.layers.0.mixer.conv1d.bias": "model-00001-of-00010.safetensors",
16
+ "backbone.layers.0.mixer.in_proj.weight": "model-00001-of-00010.safetensors",
17
+ "backbone.layers.0.mixer.out_proj.weight": "model-00001-of-00010.safetensors",
18
+ "backbone.layers.1.norm.weight": "model-00001-of-00010.safetensors",
19
+ "backbone.layers.1.mixer.up_proj.weight": "model-00001-of-00010.safetensors",
20
+ "backbone.layers.1.mixer.down_proj.weight": "model-00001-of-00010.safetensors",
21
+ "backbone.layers.2.norm.weight": "model-00001-of-00010.safetensors",
22
+ "backbone.layers.2.mixer.norm.weight": "model-00001-of-00010.safetensors",
23
+ "backbone.layers.2.mixer.A_log": "model-00001-of-00010.safetensors",
24
+ "backbone.layers.2.mixer.D": "model-00001-of-00010.safetensors",
25
+ "backbone.layers.2.mixer.dt_bias": "model-00001-of-00010.safetensors",
26
+ "backbone.layers.2.mixer.conv1d.weight": "model-00001-of-00010.safetensors",
27
+ "backbone.layers.2.mixer.conv1d.bias": "model-00001-of-00010.safetensors",
28
+ "backbone.layers.2.mixer.in_proj.weight": "model-00001-of-00010.safetensors",
29
+ "backbone.layers.2.mixer.in_proj.weight_scale": "model-00001-of-00010.safetensors",
30
+ "backbone.layers.2.mixer.in_proj.weight_scale_2": "model-00001-of-00010.safetensors",
31
+ "backbone.layers.2.mixer.in_proj.input_scale": "model-00001-of-00010.safetensors",
32
+ "backbone.layers.2.mixer.out_proj.weight": "model-00001-of-00010.safetensors",
33
+ "backbone.layers.2.mixer.out_proj.weight_scale": "model-00001-of-00010.safetensors",
34
+ "backbone.layers.2.mixer.out_proj.weight_scale_2": "model-00001-of-00010.safetensors",
35
+ "backbone.layers.2.mixer.out_proj.input_scale": "model-00001-of-00010.safetensors",
36
+ "backbone.layers.3.norm.weight": "model-00001-of-00010.safetensors",
37
+ "backbone.layers.3.mixer.up_proj.weight": "model-00001-of-00010.safetensors",
38
+ "backbone.layers.3.mixer.up_proj.weight_scale": "model-00001-of-00010.safetensors",
39
+ "backbone.layers.3.mixer.up_proj.weight_scale_2": "model-00001-of-00010.safetensors",
40
+ "backbone.layers.3.mixer.up_proj.input_scale": "model-00001-of-00010.safetensors",
41
+ "backbone.layers.3.mixer.down_proj.weight": "model-00001-of-00010.safetensors",
42
+ "backbone.layers.3.mixer.down_proj.weight_scale": "model-00001-of-00010.safetensors",
43
+ "backbone.layers.3.mixer.down_proj.weight_scale_2": "model-00001-of-00010.safetensors",
44
+ "backbone.layers.3.mixer.down_proj.input_scale": "model-00001-of-00010.safetensors",
45
+ "backbone.layers.4.norm.weight": "model-00001-of-00010.safetensors",
46
+ "backbone.layers.4.mixer.norm.weight": "model-00001-of-00010.safetensors",
47
+ "backbone.layers.4.mixer.A_log": "model-00001-of-00010.safetensors",
48
+ "backbone.layers.4.mixer.D": "model-00001-of-00010.safetensors",
49
+ "backbone.layers.4.mixer.dt_bias": "model-00001-of-00010.safetensors",
50
+ "backbone.layers.4.mixer.conv1d.weight": "model-00001-of-00010.safetensors",
51
+ "backbone.layers.4.mixer.conv1d.bias": "model-00001-of-00010.safetensors",
52
+ "backbone.layers.4.mixer.in_proj.weight": "model-00001-of-00010.safetensors",
53
+ "backbone.layers.4.mixer.in_proj.weight_scale": "model-00001-of-00010.safetensors",
54
+ "backbone.layers.4.mixer.in_proj.weight_scale_2": "model-00001-of-00010.safetensors",
55
+ "backbone.layers.4.mixer.in_proj.input_scale": "model-00001-of-00010.safetensors",
56
+ "backbone.layers.4.mixer.out_proj.weight": "model-00001-of-00010.safetensors",
57
+ "backbone.layers.4.mixer.out_proj.weight_scale": "model-00001-of-00010.safetensors",
58
+ "backbone.layers.4.mixer.out_proj.weight_scale_2": "model-00001-of-00010.safetensors",
59
+ "backbone.layers.4.mixer.out_proj.input_scale": "model-00001-of-00010.safetensors",
60
+ "backbone.layers.5.norm.weight": "model-00001-of-00010.safetensors",
61
+ "backbone.layers.5.mixer.up_proj.weight": "model-00001-of-00010.safetensors",
62
+ "backbone.layers.5.mixer.up_proj.weight_scale": "model-00001-of-00010.safetensors",
63
+ "backbone.layers.5.mixer.up_proj.weight_scale_2": "model-00001-of-00010.safetensors",
64
+ "backbone.layers.5.mixer.up_proj.input_scale": "model-00001-of-00010.safetensors",
65
+ "backbone.layers.5.mixer.down_proj.weight": "model-00001-of-00010.safetensors",
66
+ "backbone.layers.5.mixer.down_proj.weight_scale": "model-00001-of-00010.safetensors",
67
+ "backbone.layers.5.mixer.down_proj.weight_scale_2": "model-00001-of-00010.safetensors",
68
+ "backbone.layers.5.mixer.down_proj.input_scale": "model-00001-of-00010.safetensors",
69
+ "backbone.layers.6.norm.weight": "model-00001-of-00010.safetensors",
70
+ "backbone.layers.6.mixer.norm.weight": "model-00001-of-00010.safetensors",
71
+ "backbone.layers.6.mixer.A_log": "model-00001-of-00010.safetensors",
72
+ "backbone.layers.6.mixer.D": "model-00001-of-00010.safetensors",
73
+ "backbone.layers.6.mixer.dt_bias": "model-00001-of-00010.safetensors",
74
+ "backbone.layers.6.mixer.conv1d.weight": "model-00001-of-00010.safetensors",
75
+ "backbone.layers.6.mixer.conv1d.bias": "model-00001-of-00010.safetensors",
76
+ "backbone.layers.6.mixer.in_proj.weight": "model-00001-of-00010.safetensors",
77
+ "backbone.layers.6.mixer.in_proj.weight_scale": "model-00001-of-00010.safetensors",
78
+ "backbone.layers.6.mixer.in_proj.weight_scale_2": "model-00001-of-00010.safetensors",
79
+ "backbone.layers.6.mixer.in_proj.input_scale": "model-00001-of-00010.safetensors",
80
+ "backbone.layers.6.mixer.out_proj.weight": "model-00001-of-00010.safetensors",
81
+ "backbone.layers.6.mixer.out_proj.weight_scale": "model-00001-of-00010.safetensors",
82
+ "backbone.layers.6.mixer.out_proj.weight_scale_2": "model-00001-of-00010.safetensors",
83
+ "backbone.layers.6.mixer.out_proj.input_scale": "model-00001-of-00010.safetensors",
84
+ "backbone.layers.7.norm.weight": "model-00001-of-00010.safetensors",
85
+ "backbone.layers.7.mixer.norm.weight": "model-00001-of-00010.safetensors",
86
+ "backbone.layers.7.mixer.A_log": "model-00001-of-00010.safetensors",
87
+ "backbone.layers.7.mixer.D": "model-00001-of-00010.safetensors",
88
+ "backbone.layers.7.mixer.dt_bias": "model-00001-of-00010.safetensors",
89
+ "backbone.layers.7.mixer.conv1d.weight": "model-00001-of-00010.safetensors",
90
+ "backbone.layers.7.mixer.conv1d.bias": "model-00001-of-00010.safetensors",
91
+ "backbone.layers.7.mixer.in_proj.weight": "model-00001-of-00010.safetensors",
92
+ "backbone.layers.7.mixer.in_proj.weight_scale": "model-00001-of-00010.safetensors",
93
+ "backbone.layers.7.mixer.in_proj.weight_scale_2": "model-00001-of-00010.safetensors",
94
+ "backbone.layers.7.mixer.in_proj.input_scale": "model-00001-of-00010.safetensors",
95
+ "backbone.layers.7.mixer.out_proj.weight": "model-00001-of-00010.safetensors",
96
+ "backbone.layers.7.mixer.out_proj.weight_scale": "model-00001-of-00010.safetensors",
97
+ "backbone.layers.7.mixer.out_proj.weight_scale_2": "model-00001-of-00010.safetensors",
98
+ "backbone.layers.7.mixer.out_proj.input_scale": "model-00001-of-00010.safetensors",
99
+ "backbone.layers.8.norm.weight": "model-00001-of-00010.safetensors",
100
+ "backbone.layers.8.mixer.up_proj.weight": "model-00001-of-00010.safetensors",
101
+ "backbone.layers.8.mixer.up_proj.weight_scale": "model-00001-of-00010.safetensors",
102
+ "backbone.layers.8.mixer.up_proj.weight_scale_2": "model-00001-of-00010.safetensors",
103
+ "backbone.layers.8.mixer.up_proj.input_scale": "model-00001-of-00010.safetensors",
104
+ "backbone.layers.8.mixer.down_proj.weight": "model-00001-of-00010.safetensors",
105
+ "backbone.layers.8.mixer.down_proj.weight_scale": "model-00001-of-00010.safetensors",
106
+ "backbone.layers.8.mixer.down_proj.weight_scale_2": "model-00001-of-00010.safetensors",
107
+ "backbone.layers.8.mixer.down_proj.input_scale": "model-00001-of-00010.safetensors",
108
+ "backbone.layers.9.norm.weight": "model-00001-of-00010.safetensors",
109
+ "backbone.layers.9.mixer.norm.weight": "model-00001-of-00010.safetensors",
110
+ "backbone.layers.9.mixer.A_log": "model-00001-of-00010.safetensors",
111
+ "backbone.layers.9.mixer.D": "model-00001-of-00010.safetensors",
112
+ "backbone.layers.9.mixer.dt_bias": "model-00001-of-00010.safetensors",
113
+ "backbone.layers.9.mixer.conv1d.weight": "model-00001-of-00010.safetensors",
114
+ "backbone.layers.9.mixer.conv1d.bias": "model-00001-of-00010.safetensors",
115
+ "backbone.layers.9.mixer.in_proj.weight": "model-00001-of-00010.safetensors",
116
+ "backbone.layers.9.mixer.in_proj.weight_scale": "model-00001-of-00010.safetensors",
117
+ "backbone.layers.9.mixer.in_proj.weight_scale_2": "model-00001-of-00010.safetensors",
118
+ "backbone.layers.9.mixer.in_proj.input_scale": "model-00001-of-00010.safetensors",
119
+ "backbone.layers.9.mixer.out_proj.weight": "model-00001-of-00010.safetensors",
120
+ "backbone.layers.9.mixer.out_proj.weight_scale": "model-00001-of-00010.safetensors",
121
+ "backbone.layers.9.mixer.out_proj.weight_scale_2": "model-00001-of-00010.safetensors",
122
+ "backbone.layers.9.mixer.out_proj.input_scale": "model-00001-of-00010.safetensors",
123
+ "backbone.layers.10.norm.weight": "model-00001-of-00010.safetensors",
124
+ "backbone.layers.10.mixer.up_proj.weight": "model-00001-of-00010.safetensors",
125
+ "backbone.layers.10.mixer.up_proj.weight_scale": "model-00001-of-00010.safetensors",
126
+ "backbone.layers.10.mixer.up_proj.weight_scale_2": "model-00001-of-00010.safetensors",
127
+ "backbone.layers.10.mixer.up_proj.input_scale": "model-00001-of-00010.safetensors",
128
+ "backbone.layers.10.mixer.down_proj.weight": "model-00001-of-00010.safetensors",
129
+ "backbone.layers.10.mixer.down_proj.weight_scale": "model-00001-of-00010.safetensors",
130
+ "backbone.layers.10.mixer.down_proj.weight_scale_2": "model-00001-of-00010.safetensors",
131
+ "backbone.layers.10.mixer.down_proj.input_scale": "model-00001-of-00010.safetensors",
132
+ "backbone.layers.11.norm.weight": "model-00001-of-00010.safetensors",
133
+ "backbone.layers.11.mixer.norm.weight": "model-00001-of-00010.safetensors",
134
+ "backbone.layers.11.mixer.A_log": "model-00001-of-00010.safetensors",
135
+ "backbone.layers.11.mixer.D": "model-00001-of-00010.safetensors",
136
+ "backbone.layers.11.mixer.dt_bias": "model-00001-of-00010.safetensors",
137
+ "backbone.layers.11.mixer.conv1d.weight": "model-00001-of-00010.safetensors",
138
+ "backbone.layers.11.mixer.conv1d.bias": "model-00001-of-00010.safetensors",
139
+ "backbone.layers.11.mixer.in_proj.weight": "model-00001-of-00010.safetensors",
140
+ "backbone.layers.11.mixer.in_proj.weight_scale": "model-00001-of-00010.safetensors",
141
+ "backbone.layers.11.mixer.in_proj.weight_scale_2": "model-00001-of-00010.safetensors",
142
+ "backbone.layers.11.mixer.in_proj.input_scale": "model-00001-of-00010.safetensors",
143
+ "backbone.layers.11.mixer.out_proj.weight": "model-00001-of-00010.safetensors",
144
+ "backbone.layers.11.mixer.out_proj.weight_scale": "model-00001-of-00010.safetensors",
145
+ "backbone.layers.11.mixer.out_proj.weight_scale_2": "model-00001-of-00010.safetensors",
146
+ "backbone.layers.11.mixer.out_proj.input_scale": "model-00001-of-00010.safetensors",
147
+ "backbone.layers.12.norm.weight": "model-00001-of-00010.safetensors",
148
+ "backbone.layers.12.mixer.up_proj.weight": "model-00001-of-00010.safetensors",
149
+ "backbone.layers.12.mixer.up_proj.weight_scale": "model-00001-of-00010.safetensors",
150
+ "backbone.layers.12.mixer.up_proj.weight_scale_2": "model-00001-of-00010.safetensors",
151
+ "backbone.layers.12.mixer.up_proj.input_scale": "model-00001-of-00010.safetensors",
152
+ "backbone.layers.12.mixer.down_proj.weight": "model-00001-of-00010.safetensors",
153
+ "backbone.layers.12.mixer.down_proj.weight_scale": "model-00001-of-00010.safetensors",
154
+ "backbone.layers.12.mixer.down_proj.weight_scale_2": "model-00001-of-00010.safetensors",
155
+ "backbone.layers.12.mixer.down_proj.input_scale": "model-00001-of-00010.safetensors",
156
+ "backbone.layers.13.norm.weight": "model-00001-of-00010.safetensors",
157
+ "backbone.layers.13.mixer.norm.weight": "model-00001-of-00010.safetensors",
158
+ "backbone.layers.13.mixer.A_log": "model-00001-of-00010.safetensors",
159
+ "backbone.layers.13.mixer.D": "model-00001-of-00010.safetensors",
160
+ "backbone.layers.13.mixer.dt_bias": "model-00001-of-00010.safetensors",
161
+ "backbone.layers.13.mixer.conv1d.weight": "model-00001-of-00010.safetensors",
162
+ "backbone.layers.13.mixer.conv1d.bias": "model-00001-of-00010.safetensors",
163
+ "backbone.layers.13.mixer.in_proj.weight": "model-00001-of-00010.safetensors",
164
+ "backbone.layers.13.mixer.in_proj.weight_scale": "model-00001-of-00010.safetensors",
165
+ "backbone.layers.13.mixer.in_proj.weight_scale_2": "model-00001-of-00010.safetensors",
166
+ "backbone.layers.13.mixer.in_proj.input_scale": "model-00001-of-00010.safetensors",
167
+ "backbone.layers.13.mixer.out_proj.weight": "model-00001-of-00010.safetensors",
168
+ "backbone.layers.13.mixer.out_proj.weight_scale": "model-00001-of-00010.safetensors",
169
+ "backbone.layers.13.mixer.out_proj.weight_scale_2": "model-00001-of-00010.safetensors",
170
+ "backbone.layers.13.mixer.out_proj.input_scale": "model-00001-of-00010.safetensors",
171
+ "backbone.layers.14.norm.weight": "model-00001-of-00010.safetensors",
172
+ "backbone.layers.14.mixer.q_proj.weight": "model-00001-of-00010.safetensors",
173
+ "backbone.layers.14.mixer.k_proj.weight": "model-00001-of-00010.safetensors",
174
+ "backbone.layers.14.mixer.v_proj.weight": "model-00001-of-00010.safetensors"
175
+ }
176
+ }
model-00001-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cedcf7e808ded1eec3f9fd50fb67d9aedcc1972af959820d4845cf3411c2455e
3
+ size 3965505744
model-00002-of-00010.json ADDED
@@ -0,0 +1,467 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 3869668928
4
+ },
5
+ "weight_map": {
6
+ "backbone.layers.14.mixer.o_proj.weight": "model-00002-of-00010.safetensors",
7
+ "backbone.layers.15.norm.weight": "model-00002-of-00010.safetensors",
8
+ "backbone.layers.15.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
9
+ "backbone.layers.15.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
10
+ "backbone.layers.15.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
11
+ "backbone.layers.15.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
12
+ "backbone.layers.15.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
13
+ "backbone.layers.15.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
14
+ "backbone.layers.15.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
15
+ "backbone.layers.15.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
16
+ "backbone.layers.16.norm.weight": "model-00002-of-00010.safetensors",
17
+ "backbone.layers.16.mixer.norm.weight": "model-00002-of-00010.safetensors",
18
+ "backbone.layers.16.mixer.A_log": "model-00002-of-00010.safetensors",
19
+ "backbone.layers.16.mixer.D": "model-00002-of-00010.safetensors",
20
+ "backbone.layers.16.mixer.dt_bias": "model-00002-of-00010.safetensors",
21
+ "backbone.layers.16.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
22
+ "backbone.layers.16.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
23
+ "backbone.layers.16.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
24
+ "backbone.layers.16.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
25
+ "backbone.layers.16.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
26
+ "backbone.layers.16.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
27
+ "backbone.layers.16.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
28
+ "backbone.layers.16.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
29
+ "backbone.layers.16.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
30
+ "backbone.layers.16.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
31
+ "backbone.layers.17.norm.weight": "model-00002-of-00010.safetensors",
32
+ "backbone.layers.17.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
33
+ "backbone.layers.17.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
34
+ "backbone.layers.17.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
35
+ "backbone.layers.17.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
36
+ "backbone.layers.17.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
37
+ "backbone.layers.17.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
38
+ "backbone.layers.17.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
39
+ "backbone.layers.17.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
40
+ "backbone.layers.18.norm.weight": "model-00002-of-00010.safetensors",
41
+ "backbone.layers.18.mixer.norm.weight": "model-00002-of-00010.safetensors",
42
+ "backbone.layers.18.mixer.A_log": "model-00002-of-00010.safetensors",
43
+ "backbone.layers.18.mixer.D": "model-00002-of-00010.safetensors",
44
+ "backbone.layers.18.mixer.dt_bias": "model-00002-of-00010.safetensors",
45
+ "backbone.layers.18.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
46
+ "backbone.layers.18.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
47
+ "backbone.layers.18.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
48
+ "backbone.layers.18.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
49
+ "backbone.layers.18.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
50
+ "backbone.layers.18.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
51
+ "backbone.layers.18.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
52
+ "backbone.layers.18.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
53
+ "backbone.layers.18.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
54
+ "backbone.layers.18.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
55
+ "backbone.layers.19.norm.weight": "model-00002-of-00010.safetensors",
56
+ "backbone.layers.19.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
57
+ "backbone.layers.19.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
58
+ "backbone.layers.19.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
59
+ "backbone.layers.19.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
60
+ "backbone.layers.19.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
61
+ "backbone.layers.19.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
62
+ "backbone.layers.19.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
63
+ "backbone.layers.19.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
64
+ "backbone.layers.20.norm.weight": "model-00002-of-00010.safetensors",
65
+ "backbone.layers.20.mixer.norm.weight": "model-00002-of-00010.safetensors",
66
+ "backbone.layers.20.mixer.A_log": "model-00002-of-00010.safetensors",
67
+ "backbone.layers.20.mixer.D": "model-00002-of-00010.safetensors",
68
+ "backbone.layers.20.mixer.dt_bias": "model-00002-of-00010.safetensors",
69
+ "backbone.layers.20.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
70
+ "backbone.layers.20.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
71
+ "backbone.layers.20.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
72
+ "backbone.layers.20.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
73
+ "backbone.layers.20.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
74
+ "backbone.layers.20.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
75
+ "backbone.layers.20.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
76
+ "backbone.layers.20.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
77
+ "backbone.layers.20.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
78
+ "backbone.layers.20.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
79
+ "backbone.layers.21.norm.weight": "model-00002-of-00010.safetensors",
80
+ "backbone.layers.21.mixer.q_proj.weight": "model-00002-of-00010.safetensors",
81
+ "backbone.layers.21.mixer.k_proj.weight": "model-00002-of-00010.safetensors",
82
+ "backbone.layers.21.mixer.v_proj.weight": "model-00002-of-00010.safetensors",
83
+ "backbone.layers.21.mixer.o_proj.weight": "model-00002-of-00010.safetensors",
84
+ "backbone.layers.22.norm.weight": "model-00002-of-00010.safetensors",
85
+ "backbone.layers.22.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
86
+ "backbone.layers.22.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
87
+ "backbone.layers.22.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
88
+ "backbone.layers.22.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
89
+ "backbone.layers.22.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
90
+ "backbone.layers.22.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
91
+ "backbone.layers.22.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
92
+ "backbone.layers.22.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
93
+ "backbone.layers.23.norm.weight": "model-00002-of-00010.safetensors",
94
+ "backbone.layers.23.mixer.norm.weight": "model-00002-of-00010.safetensors",
95
+ "backbone.layers.23.mixer.A_log": "model-00002-of-00010.safetensors",
96
+ "backbone.layers.23.mixer.D": "model-00002-of-00010.safetensors",
97
+ "backbone.layers.23.mixer.dt_bias": "model-00002-of-00010.safetensors",
98
+ "backbone.layers.23.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
99
+ "backbone.layers.23.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
100
+ "backbone.layers.23.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
101
+ "backbone.layers.23.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
102
+ "backbone.layers.23.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
103
+ "backbone.layers.23.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
104
+ "backbone.layers.23.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
105
+ "backbone.layers.23.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
106
+ "backbone.layers.23.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
107
+ "backbone.layers.23.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
108
+ "backbone.layers.24.norm.weight": "model-00002-of-00010.safetensors",
109
+ "backbone.layers.24.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
110
+ "backbone.layers.24.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
111
+ "backbone.layers.24.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
112
+ "backbone.layers.24.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
113
+ "backbone.layers.24.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
114
+ "backbone.layers.24.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
115
+ "backbone.layers.24.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
116
+ "backbone.layers.24.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
117
+ "backbone.layers.25.norm.weight": "model-00002-of-00010.safetensors",
118
+ "backbone.layers.25.mixer.norm.weight": "model-00002-of-00010.safetensors",
119
+ "backbone.layers.25.mixer.A_log": "model-00002-of-00010.safetensors",
120
+ "backbone.layers.25.mixer.D": "model-00002-of-00010.safetensors",
121
+ "backbone.layers.25.mixer.dt_bias": "model-00002-of-00010.safetensors",
122
+ "backbone.layers.25.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
123
+ "backbone.layers.25.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
124
+ "backbone.layers.25.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
125
+ "backbone.layers.25.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
126
+ "backbone.layers.25.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
127
+ "backbone.layers.25.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
128
+ "backbone.layers.25.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
129
+ "backbone.layers.25.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
130
+ "backbone.layers.25.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
131
+ "backbone.layers.25.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
132
+ "backbone.layers.26.norm.weight": "model-00002-of-00010.safetensors",
133
+ "backbone.layers.26.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
134
+ "backbone.layers.26.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
135
+ "backbone.layers.26.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
136
+ "backbone.layers.26.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
137
+ "backbone.layers.26.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
138
+ "backbone.layers.26.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
139
+ "backbone.layers.26.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
140
+ "backbone.layers.26.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
141
+ "backbone.layers.27.norm.weight": "model-00002-of-00010.safetensors",
142
+ "backbone.layers.27.mixer.norm.weight": "model-00002-of-00010.safetensors",
143
+ "backbone.layers.27.mixer.A_log": "model-00002-of-00010.safetensors",
144
+ "backbone.layers.27.mixer.D": "model-00002-of-00010.safetensors",
145
+ "backbone.layers.27.mixer.dt_bias": "model-00002-of-00010.safetensors",
146
+ "backbone.layers.27.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
147
+ "backbone.layers.27.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
148
+ "backbone.layers.27.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
149
+ "backbone.layers.27.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
150
+ "backbone.layers.27.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
151
+ "backbone.layers.27.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
152
+ "backbone.layers.27.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
153
+ "backbone.layers.27.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
154
+ "backbone.layers.27.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
155
+ "backbone.layers.27.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
156
+ "backbone.layers.28.norm.weight": "model-00002-of-00010.safetensors",
157
+ "backbone.layers.28.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
158
+ "backbone.layers.28.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
159
+ "backbone.layers.28.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
160
+ "backbone.layers.28.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
161
+ "backbone.layers.28.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
162
+ "backbone.layers.28.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
163
+ "backbone.layers.28.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
164
+ "backbone.layers.28.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
165
+ "backbone.layers.29.norm.weight": "model-00002-of-00010.safetensors",
166
+ "backbone.layers.29.mixer.norm.weight": "model-00002-of-00010.safetensors",
167
+ "backbone.layers.29.mixer.A_log": "model-00002-of-00010.safetensors",
168
+ "backbone.layers.29.mixer.D": "model-00002-of-00010.safetensors",
169
+ "backbone.layers.29.mixer.dt_bias": "model-00002-of-00010.safetensors",
170
+ "backbone.layers.29.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
171
+ "backbone.layers.29.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
172
+ "backbone.layers.29.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
173
+ "backbone.layers.29.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
174
+ "backbone.layers.29.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
175
+ "backbone.layers.29.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
176
+ "backbone.layers.29.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
177
+ "backbone.layers.29.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
178
+ "backbone.layers.29.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
179
+ "backbone.layers.29.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
180
+ "backbone.layers.30.norm.weight": "model-00002-of-00010.safetensors",
181
+ "backbone.layers.30.mixer.q_proj.weight": "model-00002-of-00010.safetensors",
182
+ "backbone.layers.30.mixer.k_proj.weight": "model-00002-of-00010.safetensors",
183
+ "backbone.layers.30.mixer.v_proj.weight": "model-00002-of-00010.safetensors",
184
+ "backbone.layers.30.mixer.o_proj.weight": "model-00002-of-00010.safetensors",
185
+ "backbone.layers.31.norm.weight": "model-00002-of-00010.safetensors",
186
+ "backbone.layers.31.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
187
+ "backbone.layers.31.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
188
+ "backbone.layers.31.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
189
+ "backbone.layers.31.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
190
+ "backbone.layers.31.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
191
+ "backbone.layers.31.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
192
+ "backbone.layers.31.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
193
+ "backbone.layers.31.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
194
+ "backbone.layers.32.norm.weight": "model-00002-of-00010.safetensors",
195
+ "backbone.layers.32.mixer.norm.weight": "model-00002-of-00010.safetensors",
196
+ "backbone.layers.32.mixer.A_log": "model-00002-of-00010.safetensors",
197
+ "backbone.layers.32.mixer.D": "model-00002-of-00010.safetensors",
198
+ "backbone.layers.32.mixer.dt_bias": "model-00002-of-00010.safetensors",
199
+ "backbone.layers.32.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
200
+ "backbone.layers.32.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
201
+ "backbone.layers.32.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
202
+ "backbone.layers.32.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
203
+ "backbone.layers.32.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
204
+ "backbone.layers.32.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
205
+ "backbone.layers.32.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
206
+ "backbone.layers.32.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
207
+ "backbone.layers.32.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
208
+ "backbone.layers.32.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
209
+ "backbone.layers.33.norm.weight": "model-00002-of-00010.safetensors",
210
+ "backbone.layers.33.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
211
+ "backbone.layers.33.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
212
+ "backbone.layers.33.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
213
+ "backbone.layers.33.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
214
+ "backbone.layers.33.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
215
+ "backbone.layers.33.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
216
+ "backbone.layers.33.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
217
+ "backbone.layers.33.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
218
+ "backbone.layers.34.norm.weight": "model-00002-of-00010.safetensors",
219
+ "backbone.layers.34.mixer.norm.weight": "model-00002-of-00010.safetensors",
220
+ "backbone.layers.34.mixer.A_log": "model-00002-of-00010.safetensors",
221
+ "backbone.layers.34.mixer.D": "model-00002-of-00010.safetensors",
222
+ "backbone.layers.34.mixer.dt_bias": "model-00002-of-00010.safetensors",
223
+ "backbone.layers.34.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
224
+ "backbone.layers.34.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
225
+ "backbone.layers.34.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
226
+ "backbone.layers.34.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
227
+ "backbone.layers.34.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
228
+ "backbone.layers.34.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
229
+ "backbone.layers.34.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
230
+ "backbone.layers.34.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
231
+ "backbone.layers.34.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
232
+ "backbone.layers.34.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
233
+ "backbone.layers.35.norm.weight": "model-00002-of-00010.safetensors",
234
+ "backbone.layers.35.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
235
+ "backbone.layers.35.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
236
+ "backbone.layers.35.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
237
+ "backbone.layers.35.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
238
+ "backbone.layers.35.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
239
+ "backbone.layers.35.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
240
+ "backbone.layers.35.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
241
+ "backbone.layers.35.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
242
+ "backbone.layers.36.norm.weight": "model-00002-of-00010.safetensors",
243
+ "backbone.layers.36.mixer.norm.weight": "model-00002-of-00010.safetensors",
244
+ "backbone.layers.36.mixer.A_log": "model-00002-of-00010.safetensors",
245
+ "backbone.layers.36.mixer.D": "model-00002-of-00010.safetensors",
246
+ "backbone.layers.36.mixer.dt_bias": "model-00002-of-00010.safetensors",
247
+ "backbone.layers.36.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
248
+ "backbone.layers.36.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
249
+ "backbone.layers.36.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
250
+ "backbone.layers.36.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
251
+ "backbone.layers.36.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
252
+ "backbone.layers.36.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
253
+ "backbone.layers.36.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
254
+ "backbone.layers.36.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
255
+ "backbone.layers.36.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
256
+ "backbone.layers.36.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
257
+ "backbone.layers.37.norm.weight": "model-00002-of-00010.safetensors",
258
+ "backbone.layers.37.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
259
+ "backbone.layers.37.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
260
+ "backbone.layers.37.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
261
+ "backbone.layers.37.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
262
+ "backbone.layers.37.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
263
+ "backbone.layers.37.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
264
+ "backbone.layers.37.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
265
+ "backbone.layers.37.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
266
+ "backbone.layers.38.norm.weight": "model-00002-of-00010.safetensors",
267
+ "backbone.layers.38.mixer.norm.weight": "model-00002-of-00010.safetensors",
268
+ "backbone.layers.38.mixer.A_log": "model-00002-of-00010.safetensors",
269
+ "backbone.layers.38.mixer.D": "model-00002-of-00010.safetensors",
270
+ "backbone.layers.38.mixer.dt_bias": "model-00002-of-00010.safetensors",
271
+ "backbone.layers.38.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
272
+ "backbone.layers.38.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
273
+ "backbone.layers.38.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
274
+ "backbone.layers.38.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
275
+ "backbone.layers.38.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
276
+ "backbone.layers.38.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
277
+ "backbone.layers.38.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
278
+ "backbone.layers.38.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
279
+ "backbone.layers.38.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
280
+ "backbone.layers.38.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
281
+ "backbone.layers.39.norm.weight": "model-00002-of-00010.safetensors",
282
+ "backbone.layers.39.mixer.q_proj.weight": "model-00002-of-00010.safetensors",
283
+ "backbone.layers.39.mixer.k_proj.weight": "model-00002-of-00010.safetensors",
284
+ "backbone.layers.39.mixer.v_proj.weight": "model-00002-of-00010.safetensors",
285
+ "backbone.layers.39.mixer.o_proj.weight": "model-00002-of-00010.safetensors",
286
+ "backbone.layers.40.norm.weight": "model-00002-of-00010.safetensors",
287
+ "backbone.layers.40.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
288
+ "backbone.layers.40.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
289
+ "backbone.layers.40.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
290
+ "backbone.layers.40.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
291
+ "backbone.layers.40.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
292
+ "backbone.layers.40.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
293
+ "backbone.layers.40.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
294
+ "backbone.layers.40.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
295
+ "backbone.layers.41.norm.weight": "model-00002-of-00010.safetensors",
296
+ "backbone.layers.41.mixer.norm.weight": "model-00002-of-00010.safetensors",
297
+ "backbone.layers.41.mixer.A_log": "model-00002-of-00010.safetensors",
298
+ "backbone.layers.41.mixer.D": "model-00002-of-00010.safetensors",
299
+ "backbone.layers.41.mixer.dt_bias": "model-00002-of-00010.safetensors",
300
+ "backbone.layers.41.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
301
+ "backbone.layers.41.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
302
+ "backbone.layers.41.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
303
+ "backbone.layers.41.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
304
+ "backbone.layers.41.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
305
+ "backbone.layers.41.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
306
+ "backbone.layers.41.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
307
+ "backbone.layers.41.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
308
+ "backbone.layers.41.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
309
+ "backbone.layers.41.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
310
+ "backbone.layers.42.norm.weight": "model-00002-of-00010.safetensors",
311
+ "backbone.layers.42.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
312
+ "backbone.layers.42.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
313
+ "backbone.layers.42.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
314
+ "backbone.layers.42.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
315
+ "backbone.layers.42.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
316
+ "backbone.layers.42.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
317
+ "backbone.layers.42.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
318
+ "backbone.layers.42.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
319
+ "backbone.layers.43.norm.weight": "model-00002-of-00010.safetensors",
320
+ "backbone.layers.43.mixer.norm.weight": "model-00002-of-00010.safetensors",
321
+ "backbone.layers.43.mixer.A_log": "model-00002-of-00010.safetensors",
322
+ "backbone.layers.43.mixer.D": "model-00002-of-00010.safetensors",
323
+ "backbone.layers.43.mixer.dt_bias": "model-00002-of-00010.safetensors",
324
+ "backbone.layers.43.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
325
+ "backbone.layers.43.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
326
+ "backbone.layers.43.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
327
+ "backbone.layers.43.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
328
+ "backbone.layers.43.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
329
+ "backbone.layers.43.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
330
+ "backbone.layers.43.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
331
+ "backbone.layers.43.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
332
+ "backbone.layers.43.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
333
+ "backbone.layers.43.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
334
+ "backbone.layers.44.norm.weight": "model-00002-of-00010.safetensors",
335
+ "backbone.layers.44.mixer.norm.weight": "model-00002-of-00010.safetensors",
336
+ "backbone.layers.44.mixer.A_log": "model-00002-of-00010.safetensors",
337
+ "backbone.layers.44.mixer.D": "model-00002-of-00010.safetensors",
338
+ "backbone.layers.44.mixer.dt_bias": "model-00002-of-00010.safetensors",
339
+ "backbone.layers.44.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
340
+ "backbone.layers.44.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
341
+ "backbone.layers.44.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
342
+ "backbone.layers.44.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
343
+ "backbone.layers.44.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
344
+ "backbone.layers.44.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
345
+ "backbone.layers.44.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
346
+ "backbone.layers.44.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
347
+ "backbone.layers.44.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
348
+ "backbone.layers.44.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
349
+ "backbone.layers.45.norm.weight": "model-00002-of-00010.safetensors",
350
+ "backbone.layers.45.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
351
+ "backbone.layers.45.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
352
+ "backbone.layers.45.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
353
+ "backbone.layers.45.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
354
+ "backbone.layers.45.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
355
+ "backbone.layers.45.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
356
+ "backbone.layers.45.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
357
+ "backbone.layers.45.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
358
+ "backbone.layers.46.norm.weight": "model-00002-of-00010.safetensors",
359
+ "backbone.layers.46.mixer.norm.weight": "model-00002-of-00010.safetensors",
360
+ "backbone.layers.46.mixer.A_log": "model-00002-of-00010.safetensors",
361
+ "backbone.layers.46.mixer.D": "model-00002-of-00010.safetensors",
362
+ "backbone.layers.46.mixer.dt_bias": "model-00002-of-00010.safetensors",
363
+ "backbone.layers.46.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
364
+ "backbone.layers.46.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
365
+ "backbone.layers.46.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
366
+ "backbone.layers.46.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
367
+ "backbone.layers.46.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
368
+ "backbone.layers.46.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
369
+ "backbone.layers.46.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
370
+ "backbone.layers.46.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
371
+ "backbone.layers.46.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
372
+ "backbone.layers.46.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
373
+ "backbone.layers.47.norm.weight": "model-00002-of-00010.safetensors",
374
+ "backbone.layers.47.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
375
+ "backbone.layers.47.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
376
+ "backbone.layers.47.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
377
+ "backbone.layers.47.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
378
+ "backbone.layers.47.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
379
+ "backbone.layers.47.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
380
+ "backbone.layers.47.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
381
+ "backbone.layers.47.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
382
+ "backbone.layers.48.norm.weight": "model-00002-of-00010.safetensors",
383
+ "backbone.layers.48.mixer.norm.weight": "model-00002-of-00010.safetensors",
384
+ "backbone.layers.48.mixer.A_log": "model-00002-of-00010.safetensors",
385
+ "backbone.layers.48.mixer.D": "model-00002-of-00010.safetensors",
386
+ "backbone.layers.48.mixer.dt_bias": "model-00002-of-00010.safetensors",
387
+ "backbone.layers.48.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
388
+ "backbone.layers.48.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
389
+ "backbone.layers.48.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
390
+ "backbone.layers.48.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
391
+ "backbone.layers.48.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
392
+ "backbone.layers.48.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
393
+ "backbone.layers.48.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
394
+ "backbone.layers.48.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
395
+ "backbone.layers.48.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
396
+ "backbone.layers.48.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
397
+ "backbone.layers.49.norm.weight": "model-00002-of-00010.safetensors",
398
+ "backbone.layers.49.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
399
+ "backbone.layers.49.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
400
+ "backbone.layers.49.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
401
+ "backbone.layers.49.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
402
+ "backbone.layers.49.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
403
+ "backbone.layers.49.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
404
+ "backbone.layers.49.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
405
+ "backbone.layers.49.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
406
+ "backbone.layers.50.norm.weight": "model-00002-of-00010.safetensors",
407
+ "backbone.layers.50.mixer.norm.weight": "model-00002-of-00010.safetensors",
408
+ "backbone.layers.50.mixer.A_log": "model-00002-of-00010.safetensors",
409
+ "backbone.layers.50.mixer.D": "model-00002-of-00010.safetensors",
410
+ "backbone.layers.50.mixer.dt_bias": "model-00002-of-00010.safetensors",
411
+ "backbone.layers.50.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
412
+ "backbone.layers.50.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
413
+ "backbone.layers.50.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
414
+ "backbone.layers.50.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
415
+ "backbone.layers.50.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
416
+ "backbone.layers.50.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
417
+ "backbone.layers.50.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
418
+ "backbone.layers.50.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
419
+ "backbone.layers.50.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
420
+ "backbone.layers.50.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
421
+ "backbone.layers.51.norm.weight": "model-00002-of-00010.safetensors",
422
+ "backbone.layers.51.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
423
+ "backbone.layers.51.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
424
+ "backbone.layers.51.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
425
+ "backbone.layers.51.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
426
+ "backbone.layers.51.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
427
+ "backbone.layers.51.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
428
+ "backbone.layers.51.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
429
+ "backbone.layers.51.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
430
+ "backbone.layers.52.norm.weight": "model-00002-of-00010.safetensors",
431
+ "backbone.layers.52.mixer.norm.weight": "model-00002-of-00010.safetensors",
432
+ "backbone.layers.52.mixer.A_log": "model-00002-of-00010.safetensors",
433
+ "backbone.layers.52.mixer.D": "model-00002-of-00010.safetensors",
434
+ "backbone.layers.52.mixer.dt_bias": "model-00002-of-00010.safetensors",
435
+ "backbone.layers.52.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
436
+ "backbone.layers.52.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
437
+ "backbone.layers.52.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
438
+ "backbone.layers.52.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
439
+ "backbone.layers.52.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
440
+ "backbone.layers.52.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
441
+ "backbone.layers.52.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
442
+ "backbone.layers.52.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
443
+ "backbone.layers.52.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
444
+ "backbone.layers.52.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
445
+ "backbone.layers.53.norm.weight": "model-00002-of-00010.safetensors",
446
+ "backbone.layers.53.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
447
+ "backbone.layers.53.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
448
+ "backbone.layers.53.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
449
+ "backbone.layers.53.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
450
+ "backbone.layers.53.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
451
+ "backbone.layers.53.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
452
+ "backbone.layers.53.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
453
+ "backbone.layers.53.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
454
+ "backbone.layers.54.norm.weight": "model-00002-of-00010.safetensors",
455
+ "backbone.layers.54.mixer.norm.weight": "model-00002-of-00010.safetensors",
456
+ "backbone.layers.54.mixer.A_log": "model-00002-of-00010.safetensors",
457
+ "backbone.layers.54.mixer.D": "model-00002-of-00010.safetensors",
458
+ "backbone.layers.54.mixer.dt_bias": "model-00002-of-00010.safetensors",
459
+ "backbone.layers.54.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
460
+ "backbone.layers.54.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
461
+ "backbone.layers.54.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
462
+ "backbone.layers.54.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
463
+ "backbone.layers.55.norm.weight": "model-00002-of-00010.safetensors",
464
+ "backbone.layers.55.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
465
+ "backbone.layers.55.mixer.down_proj.weight": "model-00002-of-00010.safetensors"
466
+ }
467
+ }
model-00002-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0cc38d146c52334878086254b8cdc0183533f23f1d41fac0f0a7aff0b14da04
3
+ size 3869719216
model-00003-of-00010.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 0
4
+ },
5
+ "weight_map": {}
6
+ }
model-00003-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60d95b10b6e140a9626a7058d5038528f2ff80148dc4569b881db56052046509
3
+ size 40
model-00004-of-00010.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 0
4
+ },
5
+ "weight_map": {}
6
+ }
model-00004-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60d95b10b6e140a9626a7058d5038528f2ff80148dc4569b881db56052046509
3
+ size 40
model-00005-of-00010.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 0
4
+ },
5
+ "weight_map": {}
6
+ }
model-00005-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60d95b10b6e140a9626a7058d5038528f2ff80148dc4569b881db56052046509
3
+ size 40
model-00006-of-00010.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 0
4
+ },
5
+ "weight_map": {}
6
+ }
model-00006-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60d95b10b6e140a9626a7058d5038528f2ff80148dc4569b881db56052046509
3
+ size 40
model-00007-of-00010.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 0
4
+ },
5
+ "weight_map": {}
6
+ }
model-00007-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60d95b10b6e140a9626a7058d5038528f2ff80148dc4569b881db56052046509
3
+ size 40
model-00008-of-00010.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 0
4
+ },
5
+ "weight_map": {}
6
+ }
model-00008-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60d95b10b6e140a9626a7058d5038528f2ff80148dc4569b881db56052046509
3
+ size 40
model-00009-of-00010.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 0
4
+ },
5
+ "weight_map": {}
6
+ }
model-00009-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60d95b10b6e140a9626a7058d5038528f2ff80148dc4569b881db56052046509
3
+ size 40
model-00010-of-00010.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 0
4
+ },
5
+ "weight_map": {}
6
+ }
model-00010-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60d95b10b6e140a9626a7058d5038528f2ff80148dc4569b881db56052046509
3
+ size 40
model.safetensors.index.json ADDED
@@ -0,0 +1,636 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 7835156224
4
+ },
5
+ "weight_map": {
6
+ "backbone.embeddings.weight": "model-00001-of-00010.safetensors",
7
+ "backbone.norm_f.weight": "model-00001-of-00010.safetensors",
8
+ "lm_head.weight": "model-00001-of-00010.safetensors",
9
+ "backbone.layers.0.norm.weight": "model-00001-of-00010.safetensors",
10
+ "backbone.layers.0.mixer.norm.weight": "model-00001-of-00010.safetensors",
11
+ "backbone.layers.0.mixer.A_log": "model-00001-of-00010.safetensors",
12
+ "backbone.layers.0.mixer.D": "model-00001-of-00010.safetensors",
13
+ "backbone.layers.0.mixer.dt_bias": "model-00001-of-00010.safetensors",
14
+ "backbone.layers.0.mixer.conv1d.weight": "model-00001-of-00010.safetensors",
15
+ "backbone.layers.0.mixer.conv1d.bias": "model-00001-of-00010.safetensors",
16
+ "backbone.layers.0.mixer.in_proj.weight": "model-00001-of-00010.safetensors",
17
+ "backbone.layers.0.mixer.out_proj.weight": "model-00001-of-00010.safetensors",
18
+ "backbone.layers.1.norm.weight": "model-00001-of-00010.safetensors",
19
+ "backbone.layers.1.mixer.up_proj.weight": "model-00001-of-00010.safetensors",
20
+ "backbone.layers.1.mixer.down_proj.weight": "model-00001-of-00010.safetensors",
21
+ "backbone.layers.2.norm.weight": "model-00001-of-00010.safetensors",
22
+ "backbone.layers.2.mixer.norm.weight": "model-00001-of-00010.safetensors",
23
+ "backbone.layers.2.mixer.A_log": "model-00001-of-00010.safetensors",
24
+ "backbone.layers.2.mixer.D": "model-00001-of-00010.safetensors",
25
+ "backbone.layers.2.mixer.dt_bias": "model-00001-of-00010.safetensors",
26
+ "backbone.layers.2.mixer.conv1d.weight": "model-00001-of-00010.safetensors",
27
+ "backbone.layers.2.mixer.conv1d.bias": "model-00001-of-00010.safetensors",
28
+ "backbone.layers.2.mixer.in_proj.weight": "model-00001-of-00010.safetensors",
29
+ "backbone.layers.2.mixer.in_proj.weight_scale": "model-00001-of-00010.safetensors",
30
+ "backbone.layers.2.mixer.in_proj.weight_scale_2": "model-00001-of-00010.safetensors",
31
+ "backbone.layers.2.mixer.in_proj.input_scale": "model-00001-of-00010.safetensors",
32
+ "backbone.layers.2.mixer.out_proj.weight": "model-00001-of-00010.safetensors",
33
+ "backbone.layers.2.mixer.out_proj.weight_scale": "model-00001-of-00010.safetensors",
34
+ "backbone.layers.2.mixer.out_proj.weight_scale_2": "model-00001-of-00010.safetensors",
35
+ "backbone.layers.2.mixer.out_proj.input_scale": "model-00001-of-00010.safetensors",
36
+ "backbone.layers.3.norm.weight": "model-00001-of-00010.safetensors",
37
+ "backbone.layers.3.mixer.up_proj.weight": "model-00001-of-00010.safetensors",
38
+ "backbone.layers.3.mixer.up_proj.weight_scale": "model-00001-of-00010.safetensors",
39
+ "backbone.layers.3.mixer.up_proj.weight_scale_2": "model-00001-of-00010.safetensors",
40
+ "backbone.layers.3.mixer.up_proj.input_scale": "model-00001-of-00010.safetensors",
41
+ "backbone.layers.3.mixer.down_proj.weight": "model-00001-of-00010.safetensors",
42
+ "backbone.layers.3.mixer.down_proj.weight_scale": "model-00001-of-00010.safetensors",
43
+ "backbone.layers.3.mixer.down_proj.weight_scale_2": "model-00001-of-00010.safetensors",
44
+ "backbone.layers.3.mixer.down_proj.input_scale": "model-00001-of-00010.safetensors",
45
+ "backbone.layers.4.norm.weight": "model-00001-of-00010.safetensors",
46
+ "backbone.layers.4.mixer.norm.weight": "model-00001-of-00010.safetensors",
47
+ "backbone.layers.4.mixer.A_log": "model-00001-of-00010.safetensors",
48
+ "backbone.layers.4.mixer.D": "model-00001-of-00010.safetensors",
49
+ "backbone.layers.4.mixer.dt_bias": "model-00001-of-00010.safetensors",
50
+ "backbone.layers.4.mixer.conv1d.weight": "model-00001-of-00010.safetensors",
51
+ "backbone.layers.4.mixer.conv1d.bias": "model-00001-of-00010.safetensors",
52
+ "backbone.layers.4.mixer.in_proj.weight": "model-00001-of-00010.safetensors",
53
+ "backbone.layers.4.mixer.in_proj.weight_scale": "model-00001-of-00010.safetensors",
54
+ "backbone.layers.4.mixer.in_proj.weight_scale_2": "model-00001-of-00010.safetensors",
55
+ "backbone.layers.4.mixer.in_proj.input_scale": "model-00001-of-00010.safetensors",
56
+ "backbone.layers.4.mixer.out_proj.weight": "model-00001-of-00010.safetensors",
57
+ "backbone.layers.4.mixer.out_proj.weight_scale": "model-00001-of-00010.safetensors",
58
+ "backbone.layers.4.mixer.out_proj.weight_scale_2": "model-00001-of-00010.safetensors",
59
+ "backbone.layers.4.mixer.out_proj.input_scale": "model-00001-of-00010.safetensors",
60
+ "backbone.layers.5.norm.weight": "model-00001-of-00010.safetensors",
61
+ "backbone.layers.5.mixer.up_proj.weight": "model-00001-of-00010.safetensors",
62
+ "backbone.layers.5.mixer.up_proj.weight_scale": "model-00001-of-00010.safetensors",
63
+ "backbone.layers.5.mixer.up_proj.weight_scale_2": "model-00001-of-00010.safetensors",
64
+ "backbone.layers.5.mixer.up_proj.input_scale": "model-00001-of-00010.safetensors",
65
+ "backbone.layers.5.mixer.down_proj.weight": "model-00001-of-00010.safetensors",
66
+ "backbone.layers.5.mixer.down_proj.weight_scale": "model-00001-of-00010.safetensors",
67
+ "backbone.layers.5.mixer.down_proj.weight_scale_2": "model-00001-of-00010.safetensors",
68
+ "backbone.layers.5.mixer.down_proj.input_scale": "model-00001-of-00010.safetensors",
69
+ "backbone.layers.6.norm.weight": "model-00001-of-00010.safetensors",
70
+ "backbone.layers.6.mixer.norm.weight": "model-00001-of-00010.safetensors",
71
+ "backbone.layers.6.mixer.A_log": "model-00001-of-00010.safetensors",
72
+ "backbone.layers.6.mixer.D": "model-00001-of-00010.safetensors",
73
+ "backbone.layers.6.mixer.dt_bias": "model-00001-of-00010.safetensors",
74
+ "backbone.layers.6.mixer.conv1d.weight": "model-00001-of-00010.safetensors",
75
+ "backbone.layers.6.mixer.conv1d.bias": "model-00001-of-00010.safetensors",
76
+ "backbone.layers.6.mixer.in_proj.weight": "model-00001-of-00010.safetensors",
77
+ "backbone.layers.6.mixer.in_proj.weight_scale": "model-00001-of-00010.safetensors",
78
+ "backbone.layers.6.mixer.in_proj.weight_scale_2": "model-00001-of-00010.safetensors",
79
+ "backbone.layers.6.mixer.in_proj.input_scale": "model-00001-of-00010.safetensors",
80
+ "backbone.layers.6.mixer.out_proj.weight": "model-00001-of-00010.safetensors",
81
+ "backbone.layers.6.mixer.out_proj.weight_scale": "model-00001-of-00010.safetensors",
82
+ "backbone.layers.6.mixer.out_proj.weight_scale_2": "model-00001-of-00010.safetensors",
83
+ "backbone.layers.6.mixer.out_proj.input_scale": "model-00001-of-00010.safetensors",
84
+ "backbone.layers.7.norm.weight": "model-00001-of-00010.safetensors",
85
+ "backbone.layers.7.mixer.norm.weight": "model-00001-of-00010.safetensors",
86
+ "backbone.layers.7.mixer.A_log": "model-00001-of-00010.safetensors",
87
+ "backbone.layers.7.mixer.D": "model-00001-of-00010.safetensors",
88
+ "backbone.layers.7.mixer.dt_bias": "model-00001-of-00010.safetensors",
89
+ "backbone.layers.7.mixer.conv1d.weight": "model-00001-of-00010.safetensors",
90
+ "backbone.layers.7.mixer.conv1d.bias": "model-00001-of-00010.safetensors",
91
+ "backbone.layers.7.mixer.in_proj.weight": "model-00001-of-00010.safetensors",
92
+ "backbone.layers.7.mixer.in_proj.weight_scale": "model-00001-of-00010.safetensors",
93
+ "backbone.layers.7.mixer.in_proj.weight_scale_2": "model-00001-of-00010.safetensors",
94
+ "backbone.layers.7.mixer.in_proj.input_scale": "model-00001-of-00010.safetensors",
95
+ "backbone.layers.7.mixer.out_proj.weight": "model-00001-of-00010.safetensors",
96
+ "backbone.layers.7.mixer.out_proj.weight_scale": "model-00001-of-00010.safetensors",
97
+ "backbone.layers.7.mixer.out_proj.weight_scale_2": "model-00001-of-00010.safetensors",
98
+ "backbone.layers.7.mixer.out_proj.input_scale": "model-00001-of-00010.safetensors",
99
+ "backbone.layers.8.norm.weight": "model-00001-of-00010.safetensors",
100
+ "backbone.layers.8.mixer.up_proj.weight": "model-00001-of-00010.safetensors",
101
+ "backbone.layers.8.mixer.up_proj.weight_scale": "model-00001-of-00010.safetensors",
102
+ "backbone.layers.8.mixer.up_proj.weight_scale_2": "model-00001-of-00010.safetensors",
103
+ "backbone.layers.8.mixer.up_proj.input_scale": "model-00001-of-00010.safetensors",
104
+ "backbone.layers.8.mixer.down_proj.weight": "model-00001-of-00010.safetensors",
105
+ "backbone.layers.8.mixer.down_proj.weight_scale": "model-00001-of-00010.safetensors",
106
+ "backbone.layers.8.mixer.down_proj.weight_scale_2": "model-00001-of-00010.safetensors",
107
+ "backbone.layers.8.mixer.down_proj.input_scale": "model-00001-of-00010.safetensors",
108
+ "backbone.layers.9.norm.weight": "model-00001-of-00010.safetensors",
109
+ "backbone.layers.9.mixer.norm.weight": "model-00001-of-00010.safetensors",
110
+ "backbone.layers.9.mixer.A_log": "model-00001-of-00010.safetensors",
111
+ "backbone.layers.9.mixer.D": "model-00001-of-00010.safetensors",
112
+ "backbone.layers.9.mixer.dt_bias": "model-00001-of-00010.safetensors",
113
+ "backbone.layers.9.mixer.conv1d.weight": "model-00001-of-00010.safetensors",
114
+ "backbone.layers.9.mixer.conv1d.bias": "model-00001-of-00010.safetensors",
115
+ "backbone.layers.9.mixer.in_proj.weight": "model-00001-of-00010.safetensors",
116
+ "backbone.layers.9.mixer.in_proj.weight_scale": "model-00001-of-00010.safetensors",
117
+ "backbone.layers.9.mixer.in_proj.weight_scale_2": "model-00001-of-00010.safetensors",
118
+ "backbone.layers.9.mixer.in_proj.input_scale": "model-00001-of-00010.safetensors",
119
+ "backbone.layers.9.mixer.out_proj.weight": "model-00001-of-00010.safetensors",
120
+ "backbone.layers.9.mixer.out_proj.weight_scale": "model-00001-of-00010.safetensors",
121
+ "backbone.layers.9.mixer.out_proj.weight_scale_2": "model-00001-of-00010.safetensors",
122
+ "backbone.layers.9.mixer.out_proj.input_scale": "model-00001-of-00010.safetensors",
123
+ "backbone.layers.10.norm.weight": "model-00001-of-00010.safetensors",
124
+ "backbone.layers.10.mixer.up_proj.weight": "model-00001-of-00010.safetensors",
125
+ "backbone.layers.10.mixer.up_proj.weight_scale": "model-00001-of-00010.safetensors",
126
+ "backbone.layers.10.mixer.up_proj.weight_scale_2": "model-00001-of-00010.safetensors",
127
+ "backbone.layers.10.mixer.up_proj.input_scale": "model-00001-of-00010.safetensors",
128
+ "backbone.layers.10.mixer.down_proj.weight": "model-00001-of-00010.safetensors",
129
+ "backbone.layers.10.mixer.down_proj.weight_scale": "model-00001-of-00010.safetensors",
130
+ "backbone.layers.10.mixer.down_proj.weight_scale_2": "model-00001-of-00010.safetensors",
131
+ "backbone.layers.10.mixer.down_proj.input_scale": "model-00001-of-00010.safetensors",
132
+ "backbone.layers.11.norm.weight": "model-00001-of-00010.safetensors",
133
+ "backbone.layers.11.mixer.norm.weight": "model-00001-of-00010.safetensors",
134
+ "backbone.layers.11.mixer.A_log": "model-00001-of-00010.safetensors",
135
+ "backbone.layers.11.mixer.D": "model-00001-of-00010.safetensors",
136
+ "backbone.layers.11.mixer.dt_bias": "model-00001-of-00010.safetensors",
137
+ "backbone.layers.11.mixer.conv1d.weight": "model-00001-of-00010.safetensors",
138
+ "backbone.layers.11.mixer.conv1d.bias": "model-00001-of-00010.safetensors",
139
+ "backbone.layers.11.mixer.in_proj.weight": "model-00001-of-00010.safetensors",
140
+ "backbone.layers.11.mixer.in_proj.weight_scale": "model-00001-of-00010.safetensors",
141
+ "backbone.layers.11.mixer.in_proj.weight_scale_2": "model-00001-of-00010.safetensors",
142
+ "backbone.layers.11.mixer.in_proj.input_scale": "model-00001-of-00010.safetensors",
143
+ "backbone.layers.11.mixer.out_proj.weight": "model-00001-of-00010.safetensors",
144
+ "backbone.layers.11.mixer.out_proj.weight_scale": "model-00001-of-00010.safetensors",
145
+ "backbone.layers.11.mixer.out_proj.weight_scale_2": "model-00001-of-00010.safetensors",
146
+ "backbone.layers.11.mixer.out_proj.input_scale": "model-00001-of-00010.safetensors",
147
+ "backbone.layers.12.norm.weight": "model-00001-of-00010.safetensors",
148
+ "backbone.layers.12.mixer.up_proj.weight": "model-00001-of-00010.safetensors",
149
+ "backbone.layers.12.mixer.up_proj.weight_scale": "model-00001-of-00010.safetensors",
150
+ "backbone.layers.12.mixer.up_proj.weight_scale_2": "model-00001-of-00010.safetensors",
151
+ "backbone.layers.12.mixer.up_proj.input_scale": "model-00001-of-00010.safetensors",
152
+ "backbone.layers.12.mixer.down_proj.weight": "model-00001-of-00010.safetensors",
153
+ "backbone.layers.12.mixer.down_proj.weight_scale": "model-00001-of-00010.safetensors",
154
+ "backbone.layers.12.mixer.down_proj.weight_scale_2": "model-00001-of-00010.safetensors",
155
+ "backbone.layers.12.mixer.down_proj.input_scale": "model-00001-of-00010.safetensors",
156
+ "backbone.layers.13.norm.weight": "model-00001-of-00010.safetensors",
157
+ "backbone.layers.13.mixer.norm.weight": "model-00001-of-00010.safetensors",
158
+ "backbone.layers.13.mixer.A_log": "model-00001-of-00010.safetensors",
159
+ "backbone.layers.13.mixer.D": "model-00001-of-00010.safetensors",
160
+ "backbone.layers.13.mixer.dt_bias": "model-00001-of-00010.safetensors",
161
+ "backbone.layers.13.mixer.conv1d.weight": "model-00001-of-00010.safetensors",
162
+ "backbone.layers.13.mixer.conv1d.bias": "model-00001-of-00010.safetensors",
163
+ "backbone.layers.13.mixer.in_proj.weight": "model-00001-of-00010.safetensors",
164
+ "backbone.layers.13.mixer.in_proj.weight_scale": "model-00001-of-00010.safetensors",
165
+ "backbone.layers.13.mixer.in_proj.weight_scale_2": "model-00001-of-00010.safetensors",
166
+ "backbone.layers.13.mixer.in_proj.input_scale": "model-00001-of-00010.safetensors",
167
+ "backbone.layers.13.mixer.out_proj.weight": "model-00001-of-00010.safetensors",
168
+ "backbone.layers.13.mixer.out_proj.weight_scale": "model-00001-of-00010.safetensors",
169
+ "backbone.layers.13.mixer.out_proj.weight_scale_2": "model-00001-of-00010.safetensors",
170
+ "backbone.layers.13.mixer.out_proj.input_scale": "model-00001-of-00010.safetensors",
171
+ "backbone.layers.14.norm.weight": "model-00001-of-00010.safetensors",
172
+ "backbone.layers.14.mixer.q_proj.weight": "model-00001-of-00010.safetensors",
173
+ "backbone.layers.14.mixer.k_proj.weight": "model-00001-of-00010.safetensors",
174
+ "backbone.layers.14.mixer.v_proj.weight": "model-00001-of-00010.safetensors",
175
+ "backbone.layers.14.mixer.o_proj.weight": "model-00002-of-00010.safetensors",
176
+ "backbone.layers.15.norm.weight": "model-00002-of-00010.safetensors",
177
+ "backbone.layers.15.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
178
+ "backbone.layers.15.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
179
+ "backbone.layers.15.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
180
+ "backbone.layers.15.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
181
+ "backbone.layers.15.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
182
+ "backbone.layers.15.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
183
+ "backbone.layers.15.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
184
+ "backbone.layers.15.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
185
+ "backbone.layers.16.norm.weight": "model-00002-of-00010.safetensors",
186
+ "backbone.layers.16.mixer.norm.weight": "model-00002-of-00010.safetensors",
187
+ "backbone.layers.16.mixer.A_log": "model-00002-of-00010.safetensors",
188
+ "backbone.layers.16.mixer.D": "model-00002-of-00010.safetensors",
189
+ "backbone.layers.16.mixer.dt_bias": "model-00002-of-00010.safetensors",
190
+ "backbone.layers.16.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
191
+ "backbone.layers.16.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
192
+ "backbone.layers.16.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
193
+ "backbone.layers.16.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
194
+ "backbone.layers.16.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
195
+ "backbone.layers.16.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
196
+ "backbone.layers.16.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
197
+ "backbone.layers.16.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
198
+ "backbone.layers.16.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
199
+ "backbone.layers.16.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
200
+ "backbone.layers.17.norm.weight": "model-00002-of-00010.safetensors",
201
+ "backbone.layers.17.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
202
+ "backbone.layers.17.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
203
+ "backbone.layers.17.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
204
+ "backbone.layers.17.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
205
+ "backbone.layers.17.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
206
+ "backbone.layers.17.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
207
+ "backbone.layers.17.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
208
+ "backbone.layers.17.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
209
+ "backbone.layers.18.norm.weight": "model-00002-of-00010.safetensors",
210
+ "backbone.layers.18.mixer.norm.weight": "model-00002-of-00010.safetensors",
211
+ "backbone.layers.18.mixer.A_log": "model-00002-of-00010.safetensors",
212
+ "backbone.layers.18.mixer.D": "model-00002-of-00010.safetensors",
213
+ "backbone.layers.18.mixer.dt_bias": "model-00002-of-00010.safetensors",
214
+ "backbone.layers.18.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
215
+ "backbone.layers.18.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
216
+ "backbone.layers.18.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
217
+ "backbone.layers.18.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
218
+ "backbone.layers.18.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
219
+ "backbone.layers.18.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
220
+ "backbone.layers.18.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
221
+ "backbone.layers.18.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
222
+ "backbone.layers.18.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
223
+ "backbone.layers.18.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
224
+ "backbone.layers.19.norm.weight": "model-00002-of-00010.safetensors",
225
+ "backbone.layers.19.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
226
+ "backbone.layers.19.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
227
+ "backbone.layers.19.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
228
+ "backbone.layers.19.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
229
+ "backbone.layers.19.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
230
+ "backbone.layers.19.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
231
+ "backbone.layers.19.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
232
+ "backbone.layers.19.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
233
+ "backbone.layers.20.norm.weight": "model-00002-of-00010.safetensors",
234
+ "backbone.layers.20.mixer.norm.weight": "model-00002-of-00010.safetensors",
235
+ "backbone.layers.20.mixer.A_log": "model-00002-of-00010.safetensors",
236
+ "backbone.layers.20.mixer.D": "model-00002-of-00010.safetensors",
237
+ "backbone.layers.20.mixer.dt_bias": "model-00002-of-00010.safetensors",
238
+ "backbone.layers.20.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
239
+ "backbone.layers.20.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
240
+ "backbone.layers.20.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
241
+ "backbone.layers.20.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
242
+ "backbone.layers.20.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
243
+ "backbone.layers.20.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
244
+ "backbone.layers.20.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
245
+ "backbone.layers.20.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
246
+ "backbone.layers.20.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
247
+ "backbone.layers.20.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
248
+ "backbone.layers.21.norm.weight": "model-00002-of-00010.safetensors",
249
+ "backbone.layers.21.mixer.q_proj.weight": "model-00002-of-00010.safetensors",
250
+ "backbone.layers.21.mixer.k_proj.weight": "model-00002-of-00010.safetensors",
251
+ "backbone.layers.21.mixer.v_proj.weight": "model-00002-of-00010.safetensors",
252
+ "backbone.layers.21.mixer.o_proj.weight": "model-00002-of-00010.safetensors",
253
+ "backbone.layers.22.norm.weight": "model-00002-of-00010.safetensors",
254
+ "backbone.layers.22.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
255
+ "backbone.layers.22.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
256
+ "backbone.layers.22.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
257
+ "backbone.layers.22.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
258
+ "backbone.layers.22.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
259
+ "backbone.layers.22.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
260
+ "backbone.layers.22.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
261
+ "backbone.layers.22.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
262
+ "backbone.layers.23.norm.weight": "model-00002-of-00010.safetensors",
263
+ "backbone.layers.23.mixer.norm.weight": "model-00002-of-00010.safetensors",
264
+ "backbone.layers.23.mixer.A_log": "model-00002-of-00010.safetensors",
265
+ "backbone.layers.23.mixer.D": "model-00002-of-00010.safetensors",
266
+ "backbone.layers.23.mixer.dt_bias": "model-00002-of-00010.safetensors",
267
+ "backbone.layers.23.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
268
+ "backbone.layers.23.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
269
+ "backbone.layers.23.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
270
+ "backbone.layers.23.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
271
+ "backbone.layers.23.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
272
+ "backbone.layers.23.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
273
+ "backbone.layers.23.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
274
+ "backbone.layers.23.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
275
+ "backbone.layers.23.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
276
+ "backbone.layers.23.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
277
+ "backbone.layers.24.norm.weight": "model-00002-of-00010.safetensors",
278
+ "backbone.layers.24.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
279
+ "backbone.layers.24.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
280
+ "backbone.layers.24.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
281
+ "backbone.layers.24.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
282
+ "backbone.layers.24.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
283
+ "backbone.layers.24.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
284
+ "backbone.layers.24.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
285
+ "backbone.layers.24.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
286
+ "backbone.layers.25.norm.weight": "model-00002-of-00010.safetensors",
287
+ "backbone.layers.25.mixer.norm.weight": "model-00002-of-00010.safetensors",
288
+ "backbone.layers.25.mixer.A_log": "model-00002-of-00010.safetensors",
289
+ "backbone.layers.25.mixer.D": "model-00002-of-00010.safetensors",
290
+ "backbone.layers.25.mixer.dt_bias": "model-00002-of-00010.safetensors",
291
+ "backbone.layers.25.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
292
+ "backbone.layers.25.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
293
+ "backbone.layers.25.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
294
+ "backbone.layers.25.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
295
+ "backbone.layers.25.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
296
+ "backbone.layers.25.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
297
+ "backbone.layers.25.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
298
+ "backbone.layers.25.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
299
+ "backbone.layers.25.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
300
+ "backbone.layers.25.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
301
+ "backbone.layers.26.norm.weight": "model-00002-of-00010.safetensors",
302
+ "backbone.layers.26.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
303
+ "backbone.layers.26.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
304
+ "backbone.layers.26.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
305
+ "backbone.layers.26.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
306
+ "backbone.layers.26.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
307
+ "backbone.layers.26.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
308
+ "backbone.layers.26.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
309
+ "backbone.layers.26.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
310
+ "backbone.layers.27.norm.weight": "model-00002-of-00010.safetensors",
311
+ "backbone.layers.27.mixer.norm.weight": "model-00002-of-00010.safetensors",
312
+ "backbone.layers.27.mixer.A_log": "model-00002-of-00010.safetensors",
313
+ "backbone.layers.27.mixer.D": "model-00002-of-00010.safetensors",
314
+ "backbone.layers.27.mixer.dt_bias": "model-00002-of-00010.safetensors",
315
+ "backbone.layers.27.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
316
+ "backbone.layers.27.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
317
+ "backbone.layers.27.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
318
+ "backbone.layers.27.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
319
+ "backbone.layers.27.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
320
+ "backbone.layers.27.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
321
+ "backbone.layers.27.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
322
+ "backbone.layers.27.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
323
+ "backbone.layers.27.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
324
+ "backbone.layers.27.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
325
+ "backbone.layers.28.norm.weight": "model-00002-of-00010.safetensors",
326
+ "backbone.layers.28.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
327
+ "backbone.layers.28.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
328
+ "backbone.layers.28.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
329
+ "backbone.layers.28.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
330
+ "backbone.layers.28.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
331
+ "backbone.layers.28.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
332
+ "backbone.layers.28.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
333
+ "backbone.layers.28.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
334
+ "backbone.layers.29.norm.weight": "model-00002-of-00010.safetensors",
335
+ "backbone.layers.29.mixer.norm.weight": "model-00002-of-00010.safetensors",
336
+ "backbone.layers.29.mixer.A_log": "model-00002-of-00010.safetensors",
337
+ "backbone.layers.29.mixer.D": "model-00002-of-00010.safetensors",
338
+ "backbone.layers.29.mixer.dt_bias": "model-00002-of-00010.safetensors",
339
+ "backbone.layers.29.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
340
+ "backbone.layers.29.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
341
+ "backbone.layers.29.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
342
+ "backbone.layers.29.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
343
+ "backbone.layers.29.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
344
+ "backbone.layers.29.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
345
+ "backbone.layers.29.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
346
+ "backbone.layers.29.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
347
+ "backbone.layers.29.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
348
+ "backbone.layers.29.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
349
+ "backbone.layers.30.norm.weight": "model-00002-of-00010.safetensors",
350
+ "backbone.layers.30.mixer.q_proj.weight": "model-00002-of-00010.safetensors",
351
+ "backbone.layers.30.mixer.k_proj.weight": "model-00002-of-00010.safetensors",
352
+ "backbone.layers.30.mixer.v_proj.weight": "model-00002-of-00010.safetensors",
353
+ "backbone.layers.30.mixer.o_proj.weight": "model-00002-of-00010.safetensors",
354
+ "backbone.layers.31.norm.weight": "model-00002-of-00010.safetensors",
355
+ "backbone.layers.31.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
356
+ "backbone.layers.31.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
357
+ "backbone.layers.31.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
358
+ "backbone.layers.31.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
359
+ "backbone.layers.31.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
360
+ "backbone.layers.31.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
361
+ "backbone.layers.31.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
362
+ "backbone.layers.31.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
363
+ "backbone.layers.32.norm.weight": "model-00002-of-00010.safetensors",
364
+ "backbone.layers.32.mixer.norm.weight": "model-00002-of-00010.safetensors",
365
+ "backbone.layers.32.mixer.A_log": "model-00002-of-00010.safetensors",
366
+ "backbone.layers.32.mixer.D": "model-00002-of-00010.safetensors",
367
+ "backbone.layers.32.mixer.dt_bias": "model-00002-of-00010.safetensors",
368
+ "backbone.layers.32.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
369
+ "backbone.layers.32.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
370
+ "backbone.layers.32.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
371
+ "backbone.layers.32.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
372
+ "backbone.layers.32.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
373
+ "backbone.layers.32.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
374
+ "backbone.layers.32.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
375
+ "backbone.layers.32.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
376
+ "backbone.layers.32.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
377
+ "backbone.layers.32.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
378
+ "backbone.layers.33.norm.weight": "model-00002-of-00010.safetensors",
379
+ "backbone.layers.33.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
380
+ "backbone.layers.33.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
381
+ "backbone.layers.33.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
382
+ "backbone.layers.33.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
383
+ "backbone.layers.33.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
384
+ "backbone.layers.33.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
385
+ "backbone.layers.33.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
386
+ "backbone.layers.33.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
387
+ "backbone.layers.34.norm.weight": "model-00002-of-00010.safetensors",
388
+ "backbone.layers.34.mixer.norm.weight": "model-00002-of-00010.safetensors",
389
+ "backbone.layers.34.mixer.A_log": "model-00002-of-00010.safetensors",
390
+ "backbone.layers.34.mixer.D": "model-00002-of-00010.safetensors",
391
+ "backbone.layers.34.mixer.dt_bias": "model-00002-of-00010.safetensors",
392
+ "backbone.layers.34.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
393
+ "backbone.layers.34.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
394
+ "backbone.layers.34.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
395
+ "backbone.layers.34.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
396
+ "backbone.layers.34.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
397
+ "backbone.layers.34.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
398
+ "backbone.layers.34.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
399
+ "backbone.layers.34.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
400
+ "backbone.layers.34.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
401
+ "backbone.layers.34.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
402
+ "backbone.layers.35.norm.weight": "model-00002-of-00010.safetensors",
403
+ "backbone.layers.35.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
404
+ "backbone.layers.35.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
405
+ "backbone.layers.35.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
406
+ "backbone.layers.35.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
407
+ "backbone.layers.35.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
408
+ "backbone.layers.35.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
409
+ "backbone.layers.35.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
410
+ "backbone.layers.35.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
411
+ "backbone.layers.36.norm.weight": "model-00002-of-00010.safetensors",
412
+ "backbone.layers.36.mixer.norm.weight": "model-00002-of-00010.safetensors",
413
+ "backbone.layers.36.mixer.A_log": "model-00002-of-00010.safetensors",
414
+ "backbone.layers.36.mixer.D": "model-00002-of-00010.safetensors",
415
+ "backbone.layers.36.mixer.dt_bias": "model-00002-of-00010.safetensors",
416
+ "backbone.layers.36.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
417
+ "backbone.layers.36.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
418
+ "backbone.layers.36.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
419
+ "backbone.layers.36.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
420
+ "backbone.layers.36.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
421
+ "backbone.layers.36.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
422
+ "backbone.layers.36.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
423
+ "backbone.layers.36.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
424
+ "backbone.layers.36.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
425
+ "backbone.layers.36.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
426
+ "backbone.layers.37.norm.weight": "model-00002-of-00010.safetensors",
427
+ "backbone.layers.37.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
428
+ "backbone.layers.37.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
429
+ "backbone.layers.37.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
430
+ "backbone.layers.37.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
431
+ "backbone.layers.37.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
432
+ "backbone.layers.37.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
433
+ "backbone.layers.37.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
434
+ "backbone.layers.37.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
435
+ "backbone.layers.38.norm.weight": "model-00002-of-00010.safetensors",
436
+ "backbone.layers.38.mixer.norm.weight": "model-00002-of-00010.safetensors",
437
+ "backbone.layers.38.mixer.A_log": "model-00002-of-00010.safetensors",
438
+ "backbone.layers.38.mixer.D": "model-00002-of-00010.safetensors",
439
+ "backbone.layers.38.mixer.dt_bias": "model-00002-of-00010.safetensors",
440
+ "backbone.layers.38.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
441
+ "backbone.layers.38.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
442
+ "backbone.layers.38.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
443
+ "backbone.layers.38.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
444
+ "backbone.layers.38.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
445
+ "backbone.layers.38.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
446
+ "backbone.layers.38.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
447
+ "backbone.layers.38.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
448
+ "backbone.layers.38.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
449
+ "backbone.layers.38.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
450
+ "backbone.layers.39.norm.weight": "model-00002-of-00010.safetensors",
451
+ "backbone.layers.39.mixer.q_proj.weight": "model-00002-of-00010.safetensors",
452
+ "backbone.layers.39.mixer.k_proj.weight": "model-00002-of-00010.safetensors",
453
+ "backbone.layers.39.mixer.v_proj.weight": "model-00002-of-00010.safetensors",
454
+ "backbone.layers.39.mixer.o_proj.weight": "model-00002-of-00010.safetensors",
455
+ "backbone.layers.40.norm.weight": "model-00002-of-00010.safetensors",
456
+ "backbone.layers.40.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
457
+ "backbone.layers.40.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
458
+ "backbone.layers.40.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
459
+ "backbone.layers.40.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
460
+ "backbone.layers.40.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
461
+ "backbone.layers.40.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
462
+ "backbone.layers.40.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
463
+ "backbone.layers.40.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
464
+ "backbone.layers.41.norm.weight": "model-00002-of-00010.safetensors",
465
+ "backbone.layers.41.mixer.norm.weight": "model-00002-of-00010.safetensors",
466
+ "backbone.layers.41.mixer.A_log": "model-00002-of-00010.safetensors",
467
+ "backbone.layers.41.mixer.D": "model-00002-of-00010.safetensors",
468
+ "backbone.layers.41.mixer.dt_bias": "model-00002-of-00010.safetensors",
469
+ "backbone.layers.41.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
470
+ "backbone.layers.41.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
471
+ "backbone.layers.41.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
472
+ "backbone.layers.41.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
473
+ "backbone.layers.41.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
474
+ "backbone.layers.41.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
475
+ "backbone.layers.41.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
476
+ "backbone.layers.41.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
477
+ "backbone.layers.41.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
478
+ "backbone.layers.41.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
479
+ "backbone.layers.42.norm.weight": "model-00002-of-00010.safetensors",
480
+ "backbone.layers.42.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
481
+ "backbone.layers.42.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
482
+ "backbone.layers.42.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
483
+ "backbone.layers.42.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
484
+ "backbone.layers.42.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
485
+ "backbone.layers.42.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
486
+ "backbone.layers.42.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
487
+ "backbone.layers.42.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
488
+ "backbone.layers.43.norm.weight": "model-00002-of-00010.safetensors",
489
+ "backbone.layers.43.mixer.norm.weight": "model-00002-of-00010.safetensors",
490
+ "backbone.layers.43.mixer.A_log": "model-00002-of-00010.safetensors",
491
+ "backbone.layers.43.mixer.D": "model-00002-of-00010.safetensors",
492
+ "backbone.layers.43.mixer.dt_bias": "model-00002-of-00010.safetensors",
493
+ "backbone.layers.43.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
494
+ "backbone.layers.43.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
495
+ "backbone.layers.43.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
496
+ "backbone.layers.43.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
497
+ "backbone.layers.43.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
498
+ "backbone.layers.43.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
499
+ "backbone.layers.43.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
500
+ "backbone.layers.43.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
501
+ "backbone.layers.43.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
502
+ "backbone.layers.43.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
503
+ "backbone.layers.44.norm.weight": "model-00002-of-00010.safetensors",
504
+ "backbone.layers.44.mixer.norm.weight": "model-00002-of-00010.safetensors",
505
+ "backbone.layers.44.mixer.A_log": "model-00002-of-00010.safetensors",
506
+ "backbone.layers.44.mixer.D": "model-00002-of-00010.safetensors",
507
+ "backbone.layers.44.mixer.dt_bias": "model-00002-of-00010.safetensors",
508
+ "backbone.layers.44.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
509
+ "backbone.layers.44.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
510
+ "backbone.layers.44.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
511
+ "backbone.layers.44.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
512
+ "backbone.layers.44.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
513
+ "backbone.layers.44.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
514
+ "backbone.layers.44.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
515
+ "backbone.layers.44.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
516
+ "backbone.layers.44.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
517
+ "backbone.layers.44.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
518
+ "backbone.layers.45.norm.weight": "model-00002-of-00010.safetensors",
519
+ "backbone.layers.45.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
520
+ "backbone.layers.45.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
521
+ "backbone.layers.45.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
522
+ "backbone.layers.45.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
523
+ "backbone.layers.45.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
524
+ "backbone.layers.45.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
525
+ "backbone.layers.45.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
526
+ "backbone.layers.45.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
527
+ "backbone.layers.46.norm.weight": "model-00002-of-00010.safetensors",
528
+ "backbone.layers.46.mixer.norm.weight": "model-00002-of-00010.safetensors",
529
+ "backbone.layers.46.mixer.A_log": "model-00002-of-00010.safetensors",
530
+ "backbone.layers.46.mixer.D": "model-00002-of-00010.safetensors",
531
+ "backbone.layers.46.mixer.dt_bias": "model-00002-of-00010.safetensors",
532
+ "backbone.layers.46.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
533
+ "backbone.layers.46.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
534
+ "backbone.layers.46.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
535
+ "backbone.layers.46.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
536
+ "backbone.layers.46.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
537
+ "backbone.layers.46.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
538
+ "backbone.layers.46.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
539
+ "backbone.layers.46.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
540
+ "backbone.layers.46.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
541
+ "backbone.layers.46.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
542
+ "backbone.layers.47.norm.weight": "model-00002-of-00010.safetensors",
543
+ "backbone.layers.47.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
544
+ "backbone.layers.47.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
545
+ "backbone.layers.47.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
546
+ "backbone.layers.47.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
547
+ "backbone.layers.47.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
548
+ "backbone.layers.47.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
549
+ "backbone.layers.47.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
550
+ "backbone.layers.47.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
551
+ "backbone.layers.48.norm.weight": "model-00002-of-00010.safetensors",
552
+ "backbone.layers.48.mixer.norm.weight": "model-00002-of-00010.safetensors",
553
+ "backbone.layers.48.mixer.A_log": "model-00002-of-00010.safetensors",
554
+ "backbone.layers.48.mixer.D": "model-00002-of-00010.safetensors",
555
+ "backbone.layers.48.mixer.dt_bias": "model-00002-of-00010.safetensors",
556
+ "backbone.layers.48.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
557
+ "backbone.layers.48.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
558
+ "backbone.layers.48.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
559
+ "backbone.layers.48.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
560
+ "backbone.layers.48.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
561
+ "backbone.layers.48.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
562
+ "backbone.layers.48.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
563
+ "backbone.layers.48.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
564
+ "backbone.layers.48.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
565
+ "backbone.layers.48.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
566
+ "backbone.layers.49.norm.weight": "model-00002-of-00010.safetensors",
567
+ "backbone.layers.49.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
568
+ "backbone.layers.49.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
569
+ "backbone.layers.49.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
570
+ "backbone.layers.49.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
571
+ "backbone.layers.49.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
572
+ "backbone.layers.49.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
573
+ "backbone.layers.49.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
574
+ "backbone.layers.49.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
575
+ "backbone.layers.50.norm.weight": "model-00002-of-00010.safetensors",
576
+ "backbone.layers.50.mixer.norm.weight": "model-00002-of-00010.safetensors",
577
+ "backbone.layers.50.mixer.A_log": "model-00002-of-00010.safetensors",
578
+ "backbone.layers.50.mixer.D": "model-00002-of-00010.safetensors",
579
+ "backbone.layers.50.mixer.dt_bias": "model-00002-of-00010.safetensors",
580
+ "backbone.layers.50.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
581
+ "backbone.layers.50.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
582
+ "backbone.layers.50.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
583
+ "backbone.layers.50.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
584
+ "backbone.layers.50.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
585
+ "backbone.layers.50.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
586
+ "backbone.layers.50.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
587
+ "backbone.layers.50.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
588
+ "backbone.layers.50.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
589
+ "backbone.layers.50.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
590
+ "backbone.layers.51.norm.weight": "model-00002-of-00010.safetensors",
591
+ "backbone.layers.51.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
592
+ "backbone.layers.51.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
593
+ "backbone.layers.51.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
594
+ "backbone.layers.51.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
595
+ "backbone.layers.51.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
596
+ "backbone.layers.51.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
597
+ "backbone.layers.51.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
598
+ "backbone.layers.51.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
599
+ "backbone.layers.52.norm.weight": "model-00002-of-00010.safetensors",
600
+ "backbone.layers.52.mixer.norm.weight": "model-00002-of-00010.safetensors",
601
+ "backbone.layers.52.mixer.A_log": "model-00002-of-00010.safetensors",
602
+ "backbone.layers.52.mixer.D": "model-00002-of-00010.safetensors",
603
+ "backbone.layers.52.mixer.dt_bias": "model-00002-of-00010.safetensors",
604
+ "backbone.layers.52.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
605
+ "backbone.layers.52.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
606
+ "backbone.layers.52.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
607
+ "backbone.layers.52.mixer.in_proj.weight_scale": "model-00002-of-00010.safetensors",
608
+ "backbone.layers.52.mixer.in_proj.weight_scale_2": "model-00002-of-00010.safetensors",
609
+ "backbone.layers.52.mixer.in_proj.input_scale": "model-00002-of-00010.safetensors",
610
+ "backbone.layers.52.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
611
+ "backbone.layers.52.mixer.out_proj.weight_scale": "model-00002-of-00010.safetensors",
612
+ "backbone.layers.52.mixer.out_proj.weight_scale_2": "model-00002-of-00010.safetensors",
613
+ "backbone.layers.52.mixer.out_proj.input_scale": "model-00002-of-00010.safetensors",
614
+ "backbone.layers.53.norm.weight": "model-00002-of-00010.safetensors",
615
+ "backbone.layers.53.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
616
+ "backbone.layers.53.mixer.up_proj.weight_scale": "model-00002-of-00010.safetensors",
617
+ "backbone.layers.53.mixer.up_proj.weight_scale_2": "model-00002-of-00010.safetensors",
618
+ "backbone.layers.53.mixer.up_proj.input_scale": "model-00002-of-00010.safetensors",
619
+ "backbone.layers.53.mixer.down_proj.weight": "model-00002-of-00010.safetensors",
620
+ "backbone.layers.53.mixer.down_proj.weight_scale": "model-00002-of-00010.safetensors",
621
+ "backbone.layers.53.mixer.down_proj.weight_scale_2": "model-00002-of-00010.safetensors",
622
+ "backbone.layers.53.mixer.down_proj.input_scale": "model-00002-of-00010.safetensors",
623
+ "backbone.layers.54.norm.weight": "model-00002-of-00010.safetensors",
624
+ "backbone.layers.54.mixer.norm.weight": "model-00002-of-00010.safetensors",
625
+ "backbone.layers.54.mixer.A_log": "model-00002-of-00010.safetensors",
626
+ "backbone.layers.54.mixer.D": "model-00002-of-00010.safetensors",
627
+ "backbone.layers.54.mixer.dt_bias": "model-00002-of-00010.safetensors",
628
+ "backbone.layers.54.mixer.conv1d.weight": "model-00002-of-00010.safetensors",
629
+ "backbone.layers.54.mixer.conv1d.bias": "model-00002-of-00010.safetensors",
630
+ "backbone.layers.54.mixer.in_proj.weight": "model-00002-of-00010.safetensors",
631
+ "backbone.layers.54.mixer.out_proj.weight": "model-00002-of-00010.safetensors",
632
+ "backbone.layers.55.norm.weight": "model-00002-of-00010.safetensors",
633
+ "backbone.layers.55.mixer.up_proj.weight": "model-00002-of-00010.safetensors",
634
+ "backbone.layers.55.mixer.down_proj.weight": "model-00002-of-00010.safetensors"
635
+ }
636
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<SPECIAL_12>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3277c00fe5fb3963b3cb7c07b7f183722d2af4d775a4aea7cfb3684d7cccbc2f
3
+ size 17078330
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff