Text Generation
Transformers
Safetensors
PyTorch
English
nvidia
conversational
bkartal commited on
Commit
c2d8a6a
·
verified ·
1 Parent(s): 0b0d1d0

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 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "NemotronHForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "attention_head_dim": 128,
8
+ "bos_token_id": 1,
9
+ "chunk_size": 256,
10
+ "conv_kernel": 4,
11
+ "eos_token_id": 2,
12
+ "expand": 2,
13
+ "hidden_dropout": 0.0,
14
+ "hidden_size": 4096,
15
+ "hybrid_override_pattern": "M-M-M-M*-M-M-M-M-M*-M-M-M-M-M*-M-M-M-M-M*-M-M-M-M-M-",
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 21504,
18
+ "layer_norm_epsilon": 1e-05,
19
+ "mamba_head_dim": 64,
20
+ "mamba_hidden_act": "silu",
21
+ "mamba_num_heads": 128,
22
+ "mamba_proj_bias": false,
23
+ "max_position_embeddings": 131072,
24
+ "mlp_bias": false,
25
+ "mlp_hidden_act": "relu2",
26
+ "model_type": "nemotron_h",
27
+ "n_groups": 8,
28
+ "num_attention_heads": 32,
29
+ "num_hidden_layers": 52,
30
+ "num_key_value_heads": 8,
31
+ "num_logits_to_keep": 1,
32
+ "pad_token_id": 0,
33
+ "rescale_prenorm_residual": true,
34
+ "residual_in_fp32": false,
35
+ "rms_norm_eps": 1e-05,
36
+ "sliding_window": null,
37
+ "ssm_state_size": 128,
38
+ "tie_word_embeddings": false,
39
+ "time_step_floor": 0.0001,
40
+ "time_step_limit": [
41
+ 0.0,
42
+ Infinity
43
+ ],
44
+ "time_step_max": 0.1,
45
+ "time_step_min": 0.001,
46
+ "time_step_rank": 256,
47
+ "torch_dtype": "bfloat16",
48
+ "transformers_version": "4.51.3",
49
+ "use_bias": false,
50
+ "use_cache": true,
51
+ "use_conv_bias": true,
52
+ "use_mamba_kernels": true,
53
+ "vocab_size": 131072,
54
+ "quantization_config": {
55
+ "config_groups": {
56
+ "group_0": {
57
+ "input_activations": {
58
+ "dynamic": false,
59
+ "num_bits": 8,
60
+ "type": "float"
61
+ },
62
+ "weights": {
63
+ "dynamic": false,
64
+ "num_bits": 8,
65
+ "type": "float"
66
+ }
67
+ }
68
+ },
69
+ "ignore": [
70
+ "model.layers.backbone.layers.0.mixer.conv1d",
71
+ "model.layers.backbone.layers.11.mixer.conv1d",
72
+ "model.layers.backbone.layers.13.mixer.conv1d",
73
+ "model.layers.backbone.layers.15.mixer.conv1d",
74
+ "model.layers.backbone.layers.17.mixer.conv1d",
75
+ "model.layers.backbone.layers.2.mixer.conv1d",
76
+ "model.layers.backbone.layers.20.mixer.conv1d",
77
+ "model.layers.backbone.layers.22.mixer.conv1d",
78
+ "model.layers.backbone.layers.24.mixer.conv1d",
79
+ "model.layers.backbone.layers.26.mixer.conv1d",
80
+ "model.layers.backbone.layers.28.mixer.conv1d",
81
+ "model.layers.backbone.layers.31.mixer.conv1d",
82
+ "model.layers.backbone.layers.33.mixer.conv1d",
83
+ "model.layers.backbone.layers.35.mixer.conv1d",
84
+ "model.layers.backbone.layers.37.mixer.conv1d",
85
+ "model.layers.backbone.layers.39.mixer.conv1d",
86
+ "model.layers.backbone.layers.4.mixer.conv1d",
87
+ "model.layers.backbone.layers.42.mixer.conv1d",
88
+ "model.layers.backbone.layers.44.mixer.conv1d",
89
+ "model.layers.backbone.layers.46.mixer.conv1d",
90
+ "model.layers.backbone.layers.48.mixer.conv1d",
91
+ "model.layers.backbone.layers.50.mixer.conv1d",
92
+ "model.layers.backbone.layers.6.mixer.conv1d",
93
+ "model.layers.backbone.layers.9.mixer.conv1d",
94
+ "model.layers.lm_head"
95
+ ],
96
+ "quant_algo": "FP8",
97
+ "kv_cache_scheme": "FP8",
98
+ "producer": {
99
+ "name": "modelopt",
100
+ "version": "0.30.1.dev44+gd6269109"
101
+ }
102
+ }
103
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.51.3"
7
+ }
hf_quant_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "producer": {
3
+ "name": "modelopt",
4
+ "version": "0.30.1.dev44+gd6269109"
5
+ },
6
+ "quantization": {
7
+ "quant_algo": "FP8",
8
+ "kv_cache_quant_algo": "FP8",
9
+ "exclude_modules": [
10
+ "model.layers.backbone.layers.0.mixer.conv1d",
11
+ "model.layers.backbone.layers.11.mixer.conv1d",
12
+ "model.layers.backbone.layers.13.mixer.conv1d",
13
+ "model.layers.backbone.layers.15.mixer.conv1d",
14
+ "model.layers.backbone.layers.17.mixer.conv1d",
15
+ "model.layers.backbone.layers.2.mixer.conv1d",
16
+ "model.layers.backbone.layers.20.mixer.conv1d",
17
+ "model.layers.backbone.layers.22.mixer.conv1d",
18
+ "model.layers.backbone.layers.24.mixer.conv1d",
19
+ "model.layers.backbone.layers.26.mixer.conv1d",
20
+ "model.layers.backbone.layers.28.mixer.conv1d",
21
+ "model.layers.backbone.layers.31.mixer.conv1d",
22
+ "model.layers.backbone.layers.33.mixer.conv1d",
23
+ "model.layers.backbone.layers.35.mixer.conv1d",
24
+ "model.layers.backbone.layers.37.mixer.conv1d",
25
+ "model.layers.backbone.layers.39.mixer.conv1d",
26
+ "model.layers.backbone.layers.4.mixer.conv1d",
27
+ "model.layers.backbone.layers.42.mixer.conv1d",
28
+ "model.layers.backbone.layers.44.mixer.conv1d",
29
+ "model.layers.backbone.layers.46.mixer.conv1d",
30
+ "model.layers.backbone.layers.48.mixer.conv1d",
31
+ "model.layers.backbone.layers.50.mixer.conv1d",
32
+ "model.layers.backbone.layers.6.mixer.conv1d",
33
+ "model.layers.backbone.layers.9.mixer.conv1d",
34
+ "model.layers.lm_head"
35
+ ]
36
+ }
37
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbf7d00d48dae1c66261d9f398cdcaae3b3987bcbc932ee3e3fbd5efda82f615
3
+ size 4983737056
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a37f87d8d25a2d71c8478286dff9286128c45bd3cafd470eddf6c158f78dd7f
3
+ size 4192567384
model.safetensors.index.json ADDED
@@ -0,0 +1,550 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 9176247200
4
+ },
5
+ "weight_map": {
6
+ "backbone.embeddings.weight": "model-00001-of-00002.safetensors",
7
+ "backbone.layers.0.mixer.A_log": "model-00001-of-00002.safetensors",
8
+ "backbone.layers.0.mixer.D": "model-00001-of-00002.safetensors",
9
+ "backbone.layers.0.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
10
+ "backbone.layers.0.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
11
+ "backbone.layers.0.mixer.dt_bias": "model-00001-of-00002.safetensors",
12
+ "backbone.layers.0.mixer.in_proj.input_scale": "model-00001-of-00002.safetensors",
13
+ "backbone.layers.0.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
14
+ "backbone.layers.0.mixer.in_proj.weight_scale": "model-00001-of-00002.safetensors",
15
+ "backbone.layers.0.mixer.norm.weight": "model-00001-of-00002.safetensors",
16
+ "backbone.layers.0.mixer.out_proj.input_scale": "model-00001-of-00002.safetensors",
17
+ "backbone.layers.0.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
18
+ "backbone.layers.0.mixer.out_proj.weight_scale": "model-00001-of-00002.safetensors",
19
+ "backbone.layers.0.norm.weight": "model-00001-of-00002.safetensors",
20
+ "backbone.layers.1.mixer.down_proj.input_scale": "model-00001-of-00002.safetensors",
21
+ "backbone.layers.1.mixer.down_proj.weight": "model-00001-of-00002.safetensors",
22
+ "backbone.layers.1.mixer.down_proj.weight_scale": "model-00001-of-00002.safetensors",
23
+ "backbone.layers.1.mixer.up_proj.input_scale": "model-00001-of-00002.safetensors",
24
+ "backbone.layers.1.mixer.up_proj.weight": "model-00001-of-00002.safetensors",
25
+ "backbone.layers.1.mixer.up_proj.weight_scale": "model-00001-of-00002.safetensors",
26
+ "backbone.layers.1.norm.weight": "model-00001-of-00002.safetensors",
27
+ "backbone.layers.10.mixer.down_proj.input_scale": "model-00001-of-00002.safetensors",
28
+ "backbone.layers.10.mixer.down_proj.weight": "model-00001-of-00002.safetensors",
29
+ "backbone.layers.10.mixer.down_proj.weight_scale": "model-00001-of-00002.safetensors",
30
+ "backbone.layers.10.mixer.up_proj.input_scale": "model-00001-of-00002.safetensors",
31
+ "backbone.layers.10.mixer.up_proj.weight": "model-00001-of-00002.safetensors",
32
+ "backbone.layers.10.mixer.up_proj.weight_scale": "model-00001-of-00002.safetensors",
33
+ "backbone.layers.10.norm.weight": "model-00001-of-00002.safetensors",
34
+ "backbone.layers.11.mixer.A_log": "model-00001-of-00002.safetensors",
35
+ "backbone.layers.11.mixer.D": "model-00001-of-00002.safetensors",
36
+ "backbone.layers.11.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
37
+ "backbone.layers.11.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
38
+ "backbone.layers.11.mixer.dt_bias": "model-00001-of-00002.safetensors",
39
+ "backbone.layers.11.mixer.in_proj.input_scale": "model-00001-of-00002.safetensors",
40
+ "backbone.layers.11.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
41
+ "backbone.layers.11.mixer.in_proj.weight_scale": "model-00001-of-00002.safetensors",
42
+ "backbone.layers.11.mixer.norm.weight": "model-00001-of-00002.safetensors",
43
+ "backbone.layers.11.mixer.out_proj.input_scale": "model-00001-of-00002.safetensors",
44
+ "backbone.layers.11.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
45
+ "backbone.layers.11.mixer.out_proj.weight_scale": "model-00001-of-00002.safetensors",
46
+ "backbone.layers.11.norm.weight": "model-00001-of-00002.safetensors",
47
+ "backbone.layers.12.mixer.down_proj.input_scale": "model-00001-of-00002.safetensors",
48
+ "backbone.layers.12.mixer.down_proj.weight": "model-00001-of-00002.safetensors",
49
+ "backbone.layers.12.mixer.down_proj.weight_scale": "model-00001-of-00002.safetensors",
50
+ "backbone.layers.12.mixer.up_proj.input_scale": "model-00001-of-00002.safetensors",
51
+ "backbone.layers.12.mixer.up_proj.weight": "model-00001-of-00002.safetensors",
52
+ "backbone.layers.12.mixer.up_proj.weight_scale": "model-00001-of-00002.safetensors",
53
+ "backbone.layers.12.norm.weight": "model-00001-of-00002.safetensors",
54
+ "backbone.layers.13.mixer.A_log": "model-00001-of-00002.safetensors",
55
+ "backbone.layers.13.mixer.D": "model-00001-of-00002.safetensors",
56
+ "backbone.layers.13.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
57
+ "backbone.layers.13.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
58
+ "backbone.layers.13.mixer.dt_bias": "model-00001-of-00002.safetensors",
59
+ "backbone.layers.13.mixer.in_proj.input_scale": "model-00001-of-00002.safetensors",
60
+ "backbone.layers.13.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
61
+ "backbone.layers.13.mixer.in_proj.weight_scale": "model-00001-of-00002.safetensors",
62
+ "backbone.layers.13.mixer.norm.weight": "model-00001-of-00002.safetensors",
63
+ "backbone.layers.13.mixer.out_proj.input_scale": "model-00001-of-00002.safetensors",
64
+ "backbone.layers.13.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
65
+ "backbone.layers.13.mixer.out_proj.weight_scale": "model-00001-of-00002.safetensors",
66
+ "backbone.layers.13.norm.weight": "model-00001-of-00002.safetensors",
67
+ "backbone.layers.14.mixer.down_proj.input_scale": "model-00001-of-00002.safetensors",
68
+ "backbone.layers.14.mixer.down_proj.weight": "model-00001-of-00002.safetensors",
69
+ "backbone.layers.14.mixer.down_proj.weight_scale": "model-00001-of-00002.safetensors",
70
+ "backbone.layers.14.mixer.up_proj.input_scale": "model-00001-of-00002.safetensors",
71
+ "backbone.layers.14.mixer.up_proj.weight": "model-00001-of-00002.safetensors",
72
+ "backbone.layers.14.mixer.up_proj.weight_scale": "model-00001-of-00002.safetensors",
73
+ "backbone.layers.14.norm.weight": "model-00001-of-00002.safetensors",
74
+ "backbone.layers.15.mixer.A_log": "model-00001-of-00002.safetensors",
75
+ "backbone.layers.15.mixer.D": "model-00001-of-00002.safetensors",
76
+ "backbone.layers.15.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
77
+ "backbone.layers.15.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
78
+ "backbone.layers.15.mixer.dt_bias": "model-00001-of-00002.safetensors",
79
+ "backbone.layers.15.mixer.in_proj.input_scale": "model-00001-of-00002.safetensors",
80
+ "backbone.layers.15.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
81
+ "backbone.layers.15.mixer.in_proj.weight_scale": "model-00001-of-00002.safetensors",
82
+ "backbone.layers.15.mixer.norm.weight": "model-00001-of-00002.safetensors",
83
+ "backbone.layers.15.mixer.out_proj.input_scale": "model-00001-of-00002.safetensors",
84
+ "backbone.layers.15.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
85
+ "backbone.layers.15.mixer.out_proj.weight_scale": "model-00001-of-00002.safetensors",
86
+ "backbone.layers.15.norm.weight": "model-00001-of-00002.safetensors",
87
+ "backbone.layers.16.mixer.down_proj.input_scale": "model-00001-of-00002.safetensors",
88
+ "backbone.layers.16.mixer.down_proj.weight": "model-00001-of-00002.safetensors",
89
+ "backbone.layers.16.mixer.down_proj.weight_scale": "model-00001-of-00002.safetensors",
90
+ "backbone.layers.16.mixer.up_proj.input_scale": "model-00001-of-00002.safetensors",
91
+ "backbone.layers.16.mixer.up_proj.weight": "model-00001-of-00002.safetensors",
92
+ "backbone.layers.16.mixer.up_proj.weight_scale": "model-00001-of-00002.safetensors",
93
+ "backbone.layers.16.norm.weight": "model-00001-of-00002.safetensors",
94
+ "backbone.layers.17.mixer.A_log": "model-00001-of-00002.safetensors",
95
+ "backbone.layers.17.mixer.D": "model-00001-of-00002.safetensors",
96
+ "backbone.layers.17.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
97
+ "backbone.layers.17.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
98
+ "backbone.layers.17.mixer.dt_bias": "model-00001-of-00002.safetensors",
99
+ "backbone.layers.17.mixer.in_proj.input_scale": "model-00001-of-00002.safetensors",
100
+ "backbone.layers.17.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
101
+ "backbone.layers.17.mixer.in_proj.weight_scale": "model-00001-of-00002.safetensors",
102
+ "backbone.layers.17.mixer.norm.weight": "model-00001-of-00002.safetensors",
103
+ "backbone.layers.17.mixer.out_proj.input_scale": "model-00001-of-00002.safetensors",
104
+ "backbone.layers.17.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
105
+ "backbone.layers.17.mixer.out_proj.weight_scale": "model-00001-of-00002.safetensors",
106
+ "backbone.layers.17.norm.weight": "model-00001-of-00002.safetensors",
107
+ "backbone.layers.18.mixer.k_proj.input_scale": "model-00001-of-00002.safetensors",
108
+ "backbone.layers.18.mixer.k_proj.k_scale": "model-00001-of-00002.safetensors",
109
+ "backbone.layers.18.mixer.k_proj.weight": "model-00001-of-00002.safetensors",
110
+ "backbone.layers.18.mixer.k_proj.weight_scale": "model-00001-of-00002.safetensors",
111
+ "backbone.layers.18.mixer.o_proj.input_scale": "model-00001-of-00002.safetensors",
112
+ "backbone.layers.18.mixer.o_proj.weight": "model-00001-of-00002.safetensors",
113
+ "backbone.layers.18.mixer.o_proj.weight_scale": "model-00001-of-00002.safetensors",
114
+ "backbone.layers.18.mixer.q_proj.input_scale": "model-00001-of-00002.safetensors",
115
+ "backbone.layers.18.mixer.q_proj.weight": "model-00001-of-00002.safetensors",
116
+ "backbone.layers.18.mixer.q_proj.weight_scale": "model-00001-of-00002.safetensors",
117
+ "backbone.layers.18.mixer.v_proj.input_scale": "model-00001-of-00002.safetensors",
118
+ "backbone.layers.18.mixer.v_proj.v_scale": "model-00001-of-00002.safetensors",
119
+ "backbone.layers.18.mixer.v_proj.weight": "model-00001-of-00002.safetensors",
120
+ "backbone.layers.18.mixer.v_proj.weight_scale": "model-00001-of-00002.safetensors",
121
+ "backbone.layers.18.norm.weight": "model-00001-of-00002.safetensors",
122
+ "backbone.layers.19.mixer.down_proj.input_scale": "model-00001-of-00002.safetensors",
123
+ "backbone.layers.19.mixer.down_proj.weight": "model-00001-of-00002.safetensors",
124
+ "backbone.layers.19.mixer.down_proj.weight_scale": "model-00001-of-00002.safetensors",
125
+ "backbone.layers.19.mixer.up_proj.input_scale": "model-00001-of-00002.safetensors",
126
+ "backbone.layers.19.mixer.up_proj.weight": "model-00001-of-00002.safetensors",
127
+ "backbone.layers.19.mixer.up_proj.weight_scale": "model-00001-of-00002.safetensors",
128
+ "backbone.layers.19.norm.weight": "model-00001-of-00002.safetensors",
129
+ "backbone.layers.2.mixer.A_log": "model-00001-of-00002.safetensors",
130
+ "backbone.layers.2.mixer.D": "model-00001-of-00002.safetensors",
131
+ "backbone.layers.2.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
132
+ "backbone.layers.2.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
133
+ "backbone.layers.2.mixer.dt_bias": "model-00001-of-00002.safetensors",
134
+ "backbone.layers.2.mixer.in_proj.input_scale": "model-00001-of-00002.safetensors",
135
+ "backbone.layers.2.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
136
+ "backbone.layers.2.mixer.in_proj.weight_scale": "model-00001-of-00002.safetensors",
137
+ "backbone.layers.2.mixer.norm.weight": "model-00001-of-00002.safetensors",
138
+ "backbone.layers.2.mixer.out_proj.input_scale": "model-00001-of-00002.safetensors",
139
+ "backbone.layers.2.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
140
+ "backbone.layers.2.mixer.out_proj.weight_scale": "model-00001-of-00002.safetensors",
141
+ "backbone.layers.2.norm.weight": "model-00001-of-00002.safetensors",
142
+ "backbone.layers.20.mixer.A_log": "model-00001-of-00002.safetensors",
143
+ "backbone.layers.20.mixer.D": "model-00001-of-00002.safetensors",
144
+ "backbone.layers.20.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
145
+ "backbone.layers.20.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
146
+ "backbone.layers.20.mixer.dt_bias": "model-00001-of-00002.safetensors",
147
+ "backbone.layers.20.mixer.in_proj.input_scale": "model-00001-of-00002.safetensors",
148
+ "backbone.layers.20.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
149
+ "backbone.layers.20.mixer.in_proj.weight_scale": "model-00001-of-00002.safetensors",
150
+ "backbone.layers.20.mixer.norm.weight": "model-00001-of-00002.safetensors",
151
+ "backbone.layers.20.mixer.out_proj.input_scale": "model-00001-of-00002.safetensors",
152
+ "backbone.layers.20.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
153
+ "backbone.layers.20.mixer.out_proj.weight_scale": "model-00001-of-00002.safetensors",
154
+ "backbone.layers.20.norm.weight": "model-00001-of-00002.safetensors",
155
+ "backbone.layers.21.mixer.down_proj.input_scale": "model-00001-of-00002.safetensors",
156
+ "backbone.layers.21.mixer.down_proj.weight": "model-00001-of-00002.safetensors",
157
+ "backbone.layers.21.mixer.down_proj.weight_scale": "model-00001-of-00002.safetensors",
158
+ "backbone.layers.21.mixer.up_proj.input_scale": "model-00001-of-00002.safetensors",
159
+ "backbone.layers.21.mixer.up_proj.weight": "model-00001-of-00002.safetensors",
160
+ "backbone.layers.21.mixer.up_proj.weight_scale": "model-00001-of-00002.safetensors",
161
+ "backbone.layers.21.norm.weight": "model-00001-of-00002.safetensors",
162
+ "backbone.layers.22.mixer.A_log": "model-00001-of-00002.safetensors",
163
+ "backbone.layers.22.mixer.D": "model-00001-of-00002.safetensors",
164
+ "backbone.layers.22.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
165
+ "backbone.layers.22.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
166
+ "backbone.layers.22.mixer.dt_bias": "model-00001-of-00002.safetensors",
167
+ "backbone.layers.22.mixer.in_proj.input_scale": "model-00001-of-00002.safetensors",
168
+ "backbone.layers.22.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
169
+ "backbone.layers.22.mixer.in_proj.weight_scale": "model-00001-of-00002.safetensors",
170
+ "backbone.layers.22.mixer.norm.weight": "model-00001-of-00002.safetensors",
171
+ "backbone.layers.22.mixer.out_proj.input_scale": "model-00001-of-00002.safetensors",
172
+ "backbone.layers.22.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
173
+ "backbone.layers.22.mixer.out_proj.weight_scale": "model-00001-of-00002.safetensors",
174
+ "backbone.layers.22.norm.weight": "model-00001-of-00002.safetensors",
175
+ "backbone.layers.23.mixer.down_proj.input_scale": "model-00001-of-00002.safetensors",
176
+ "backbone.layers.23.mixer.down_proj.weight": "model-00001-of-00002.safetensors",
177
+ "backbone.layers.23.mixer.down_proj.weight_scale": "model-00001-of-00002.safetensors",
178
+ "backbone.layers.23.mixer.up_proj.input_scale": "model-00001-of-00002.safetensors",
179
+ "backbone.layers.23.mixer.up_proj.weight": "model-00001-of-00002.safetensors",
180
+ "backbone.layers.23.mixer.up_proj.weight_scale": "model-00001-of-00002.safetensors",
181
+ "backbone.layers.23.norm.weight": "model-00001-of-00002.safetensors",
182
+ "backbone.layers.24.mixer.A_log": "model-00001-of-00002.safetensors",
183
+ "backbone.layers.24.mixer.D": "model-00001-of-00002.safetensors",
184
+ "backbone.layers.24.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
185
+ "backbone.layers.24.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
186
+ "backbone.layers.24.mixer.dt_bias": "model-00001-of-00002.safetensors",
187
+ "backbone.layers.24.mixer.in_proj.input_scale": "model-00001-of-00002.safetensors",
188
+ "backbone.layers.24.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
189
+ "backbone.layers.24.mixer.in_proj.weight_scale": "model-00001-of-00002.safetensors",
190
+ "backbone.layers.24.mixer.norm.weight": "model-00001-of-00002.safetensors",
191
+ "backbone.layers.24.mixer.out_proj.input_scale": "model-00001-of-00002.safetensors",
192
+ "backbone.layers.24.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
193
+ "backbone.layers.24.mixer.out_proj.weight_scale": "model-00001-of-00002.safetensors",
194
+ "backbone.layers.24.norm.weight": "model-00001-of-00002.safetensors",
195
+ "backbone.layers.25.mixer.down_proj.input_scale": "model-00001-of-00002.safetensors",
196
+ "backbone.layers.25.mixer.down_proj.weight": "model-00001-of-00002.safetensors",
197
+ "backbone.layers.25.mixer.down_proj.weight_scale": "model-00001-of-00002.safetensors",
198
+ "backbone.layers.25.mixer.up_proj.input_scale": "model-00001-of-00002.safetensors",
199
+ "backbone.layers.25.mixer.up_proj.weight": "model-00001-of-00002.safetensors",
200
+ "backbone.layers.25.mixer.up_proj.weight_scale": "model-00001-of-00002.safetensors",
201
+ "backbone.layers.25.norm.weight": "model-00001-of-00002.safetensors",
202
+ "backbone.layers.26.mixer.A_log": "model-00001-of-00002.safetensors",
203
+ "backbone.layers.26.mixer.D": "model-00001-of-00002.safetensors",
204
+ "backbone.layers.26.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
205
+ "backbone.layers.26.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
206
+ "backbone.layers.26.mixer.dt_bias": "model-00001-of-00002.safetensors",
207
+ "backbone.layers.26.mixer.in_proj.input_scale": "model-00001-of-00002.safetensors",
208
+ "backbone.layers.26.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
209
+ "backbone.layers.26.mixer.in_proj.weight_scale": "model-00001-of-00002.safetensors",
210
+ "backbone.layers.26.mixer.norm.weight": "model-00001-of-00002.safetensors",
211
+ "backbone.layers.26.mixer.out_proj.input_scale": "model-00001-of-00002.safetensors",
212
+ "backbone.layers.26.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
213
+ "backbone.layers.26.mixer.out_proj.weight_scale": "model-00001-of-00002.safetensors",
214
+ "backbone.layers.26.norm.weight": "model-00001-of-00002.safetensors",
215
+ "backbone.layers.27.mixer.down_proj.input_scale": "model-00001-of-00002.safetensors",
216
+ "backbone.layers.27.mixer.down_proj.weight": "model-00001-of-00002.safetensors",
217
+ "backbone.layers.27.mixer.down_proj.weight_scale": "model-00001-of-00002.safetensors",
218
+ "backbone.layers.27.mixer.up_proj.input_scale": "model-00001-of-00002.safetensors",
219
+ "backbone.layers.27.mixer.up_proj.weight": "model-00001-of-00002.safetensors",
220
+ "backbone.layers.27.mixer.up_proj.weight_scale": "model-00001-of-00002.safetensors",
221
+ "backbone.layers.27.norm.weight": "model-00001-of-00002.safetensors",
222
+ "backbone.layers.28.mixer.A_log": "model-00001-of-00002.safetensors",
223
+ "backbone.layers.28.mixer.D": "model-00001-of-00002.safetensors",
224
+ "backbone.layers.28.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
225
+ "backbone.layers.28.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
226
+ "backbone.layers.28.mixer.dt_bias": "model-00001-of-00002.safetensors",
227
+ "backbone.layers.28.mixer.in_proj.input_scale": "model-00001-of-00002.safetensors",
228
+ "backbone.layers.28.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
229
+ "backbone.layers.28.mixer.in_proj.weight_scale": "model-00001-of-00002.safetensors",
230
+ "backbone.layers.28.mixer.norm.weight": "model-00001-of-00002.safetensors",
231
+ "backbone.layers.28.mixer.out_proj.input_scale": "model-00001-of-00002.safetensors",
232
+ "backbone.layers.28.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
233
+ "backbone.layers.28.mixer.out_proj.weight_scale": "model-00001-of-00002.safetensors",
234
+ "backbone.layers.28.norm.weight": "model-00001-of-00002.safetensors",
235
+ "backbone.layers.29.mixer.k_proj.input_scale": "model-00002-of-00002.safetensors",
236
+ "backbone.layers.29.mixer.k_proj.k_scale": "model-00002-of-00002.safetensors",
237
+ "backbone.layers.29.mixer.k_proj.weight": "model-00002-of-00002.safetensors",
238
+ "backbone.layers.29.mixer.k_proj.weight_scale": "model-00002-of-00002.safetensors",
239
+ "backbone.layers.29.mixer.o_proj.input_scale": "model-00002-of-00002.safetensors",
240
+ "backbone.layers.29.mixer.o_proj.weight": "model-00002-of-00002.safetensors",
241
+ "backbone.layers.29.mixer.o_proj.weight_scale": "model-00002-of-00002.safetensors",
242
+ "backbone.layers.29.mixer.q_proj.input_scale": "model-00002-of-00002.safetensors",
243
+ "backbone.layers.29.mixer.q_proj.weight": "model-00002-of-00002.safetensors",
244
+ "backbone.layers.29.mixer.q_proj.weight_scale": "model-00002-of-00002.safetensors",
245
+ "backbone.layers.29.mixer.v_proj.input_scale": "model-00002-of-00002.safetensors",
246
+ "backbone.layers.29.mixer.v_proj.v_scale": "model-00002-of-00002.safetensors",
247
+ "backbone.layers.29.mixer.v_proj.weight": "model-00002-of-00002.safetensors",
248
+ "backbone.layers.29.mixer.v_proj.weight_scale": "model-00002-of-00002.safetensors",
249
+ "backbone.layers.29.norm.weight": "model-00001-of-00002.safetensors",
250
+ "backbone.layers.3.mixer.down_proj.input_scale": "model-00001-of-00002.safetensors",
251
+ "backbone.layers.3.mixer.down_proj.weight": "model-00001-of-00002.safetensors",
252
+ "backbone.layers.3.mixer.down_proj.weight_scale": "model-00001-of-00002.safetensors",
253
+ "backbone.layers.3.mixer.up_proj.input_scale": "model-00001-of-00002.safetensors",
254
+ "backbone.layers.3.mixer.up_proj.weight": "model-00001-of-00002.safetensors",
255
+ "backbone.layers.3.mixer.up_proj.weight_scale": "model-00001-of-00002.safetensors",
256
+ "backbone.layers.3.norm.weight": "model-00001-of-00002.safetensors",
257
+ "backbone.layers.30.mixer.down_proj.input_scale": "model-00002-of-00002.safetensors",
258
+ "backbone.layers.30.mixer.down_proj.weight": "model-00002-of-00002.safetensors",
259
+ "backbone.layers.30.mixer.down_proj.weight_scale": "model-00002-of-00002.safetensors",
260
+ "backbone.layers.30.mixer.up_proj.input_scale": "model-00002-of-00002.safetensors",
261
+ "backbone.layers.30.mixer.up_proj.weight": "model-00002-of-00002.safetensors",
262
+ "backbone.layers.30.mixer.up_proj.weight_scale": "model-00002-of-00002.safetensors",
263
+ "backbone.layers.30.norm.weight": "model-00002-of-00002.safetensors",
264
+ "backbone.layers.31.mixer.A_log": "model-00002-of-00002.safetensors",
265
+ "backbone.layers.31.mixer.D": "model-00002-of-00002.safetensors",
266
+ "backbone.layers.31.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
267
+ "backbone.layers.31.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
268
+ "backbone.layers.31.mixer.dt_bias": "model-00002-of-00002.safetensors",
269
+ "backbone.layers.31.mixer.in_proj.input_scale": "model-00002-of-00002.safetensors",
270
+ "backbone.layers.31.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
271
+ "backbone.layers.31.mixer.in_proj.weight_scale": "model-00002-of-00002.safetensors",
272
+ "backbone.layers.31.mixer.norm.weight": "model-00002-of-00002.safetensors",
273
+ "backbone.layers.31.mixer.out_proj.input_scale": "model-00002-of-00002.safetensors",
274
+ "backbone.layers.31.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
275
+ "backbone.layers.31.mixer.out_proj.weight_scale": "model-00002-of-00002.safetensors",
276
+ "backbone.layers.31.norm.weight": "model-00002-of-00002.safetensors",
277
+ "backbone.layers.32.mixer.down_proj.input_scale": "model-00002-of-00002.safetensors",
278
+ "backbone.layers.32.mixer.down_proj.weight": "model-00002-of-00002.safetensors",
279
+ "backbone.layers.32.mixer.down_proj.weight_scale": "model-00002-of-00002.safetensors",
280
+ "backbone.layers.32.mixer.up_proj.input_scale": "model-00002-of-00002.safetensors",
281
+ "backbone.layers.32.mixer.up_proj.weight": "model-00002-of-00002.safetensors",
282
+ "backbone.layers.32.mixer.up_proj.weight_scale": "model-00002-of-00002.safetensors",
283
+ "backbone.layers.32.norm.weight": "model-00002-of-00002.safetensors",
284
+ "backbone.layers.33.mixer.A_log": "model-00002-of-00002.safetensors",
285
+ "backbone.layers.33.mixer.D": "model-00002-of-00002.safetensors",
286
+ "backbone.layers.33.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
287
+ "backbone.layers.33.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
288
+ "backbone.layers.33.mixer.dt_bias": "model-00002-of-00002.safetensors",
289
+ "backbone.layers.33.mixer.in_proj.input_scale": "model-00002-of-00002.safetensors",
290
+ "backbone.layers.33.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
291
+ "backbone.layers.33.mixer.in_proj.weight_scale": "model-00002-of-00002.safetensors",
292
+ "backbone.layers.33.mixer.norm.weight": "model-00002-of-00002.safetensors",
293
+ "backbone.layers.33.mixer.out_proj.input_scale": "model-00002-of-00002.safetensors",
294
+ "backbone.layers.33.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
295
+ "backbone.layers.33.mixer.out_proj.weight_scale": "model-00002-of-00002.safetensors",
296
+ "backbone.layers.33.norm.weight": "model-00002-of-00002.safetensors",
297
+ "backbone.layers.34.mixer.down_proj.input_scale": "model-00002-of-00002.safetensors",
298
+ "backbone.layers.34.mixer.down_proj.weight": "model-00002-of-00002.safetensors",
299
+ "backbone.layers.34.mixer.down_proj.weight_scale": "model-00002-of-00002.safetensors",
300
+ "backbone.layers.34.mixer.up_proj.input_scale": "model-00002-of-00002.safetensors",
301
+ "backbone.layers.34.mixer.up_proj.weight": "model-00002-of-00002.safetensors",
302
+ "backbone.layers.34.mixer.up_proj.weight_scale": "model-00002-of-00002.safetensors",
303
+ "backbone.layers.34.norm.weight": "model-00002-of-00002.safetensors",
304
+ "backbone.layers.35.mixer.A_log": "model-00002-of-00002.safetensors",
305
+ "backbone.layers.35.mixer.D": "model-00002-of-00002.safetensors",
306
+ "backbone.layers.35.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
307
+ "backbone.layers.35.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
308
+ "backbone.layers.35.mixer.dt_bias": "model-00002-of-00002.safetensors",
309
+ "backbone.layers.35.mixer.in_proj.input_scale": "model-00002-of-00002.safetensors",
310
+ "backbone.layers.35.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
311
+ "backbone.layers.35.mixer.in_proj.weight_scale": "model-00002-of-00002.safetensors",
312
+ "backbone.layers.35.mixer.norm.weight": "model-00002-of-00002.safetensors",
313
+ "backbone.layers.35.mixer.out_proj.input_scale": "model-00002-of-00002.safetensors",
314
+ "backbone.layers.35.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
315
+ "backbone.layers.35.mixer.out_proj.weight_scale": "model-00002-of-00002.safetensors",
316
+ "backbone.layers.35.norm.weight": "model-00002-of-00002.safetensors",
317
+ "backbone.layers.36.mixer.down_proj.input_scale": "model-00002-of-00002.safetensors",
318
+ "backbone.layers.36.mixer.down_proj.weight": "model-00002-of-00002.safetensors",
319
+ "backbone.layers.36.mixer.down_proj.weight_scale": "model-00002-of-00002.safetensors",
320
+ "backbone.layers.36.mixer.up_proj.input_scale": "model-00002-of-00002.safetensors",
321
+ "backbone.layers.36.mixer.up_proj.weight": "model-00002-of-00002.safetensors",
322
+ "backbone.layers.36.mixer.up_proj.weight_scale": "model-00002-of-00002.safetensors",
323
+ "backbone.layers.36.norm.weight": "model-00002-of-00002.safetensors",
324
+ "backbone.layers.37.mixer.A_log": "model-00002-of-00002.safetensors",
325
+ "backbone.layers.37.mixer.D": "model-00002-of-00002.safetensors",
326
+ "backbone.layers.37.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
327
+ "backbone.layers.37.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
328
+ "backbone.layers.37.mixer.dt_bias": "model-00002-of-00002.safetensors",
329
+ "backbone.layers.37.mixer.in_proj.input_scale": "model-00002-of-00002.safetensors",
330
+ "backbone.layers.37.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
331
+ "backbone.layers.37.mixer.in_proj.weight_scale": "model-00002-of-00002.safetensors",
332
+ "backbone.layers.37.mixer.norm.weight": "model-00002-of-00002.safetensors",
333
+ "backbone.layers.37.mixer.out_proj.input_scale": "model-00002-of-00002.safetensors",
334
+ "backbone.layers.37.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
335
+ "backbone.layers.37.mixer.out_proj.weight_scale": "model-00002-of-00002.safetensors",
336
+ "backbone.layers.37.norm.weight": "model-00002-of-00002.safetensors",
337
+ "backbone.layers.38.mixer.down_proj.input_scale": "model-00002-of-00002.safetensors",
338
+ "backbone.layers.38.mixer.down_proj.weight": "model-00002-of-00002.safetensors",
339
+ "backbone.layers.38.mixer.down_proj.weight_scale": "model-00002-of-00002.safetensors",
340
+ "backbone.layers.38.mixer.up_proj.input_scale": "model-00002-of-00002.safetensors",
341
+ "backbone.layers.38.mixer.up_proj.weight": "model-00002-of-00002.safetensors",
342
+ "backbone.layers.38.mixer.up_proj.weight_scale": "model-00002-of-00002.safetensors",
343
+ "backbone.layers.38.norm.weight": "model-00002-of-00002.safetensors",
344
+ "backbone.layers.39.mixer.A_log": "model-00002-of-00002.safetensors",
345
+ "backbone.layers.39.mixer.D": "model-00002-of-00002.safetensors",
346
+ "backbone.layers.39.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
347
+ "backbone.layers.39.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
348
+ "backbone.layers.39.mixer.dt_bias": "model-00002-of-00002.safetensors",
349
+ "backbone.layers.39.mixer.in_proj.input_scale": "model-00002-of-00002.safetensors",
350
+ "backbone.layers.39.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
351
+ "backbone.layers.39.mixer.in_proj.weight_scale": "model-00002-of-00002.safetensors",
352
+ "backbone.layers.39.mixer.norm.weight": "model-00002-of-00002.safetensors",
353
+ "backbone.layers.39.mixer.out_proj.input_scale": "model-00002-of-00002.safetensors",
354
+ "backbone.layers.39.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
355
+ "backbone.layers.39.mixer.out_proj.weight_scale": "model-00002-of-00002.safetensors",
356
+ "backbone.layers.39.norm.weight": "model-00002-of-00002.safetensors",
357
+ "backbone.layers.4.mixer.A_log": "model-00001-of-00002.safetensors",
358
+ "backbone.layers.4.mixer.D": "model-00001-of-00002.safetensors",
359
+ "backbone.layers.4.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
360
+ "backbone.layers.4.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
361
+ "backbone.layers.4.mixer.dt_bias": "model-00001-of-00002.safetensors",
362
+ "backbone.layers.4.mixer.in_proj.input_scale": "model-00001-of-00002.safetensors",
363
+ "backbone.layers.4.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
364
+ "backbone.layers.4.mixer.in_proj.weight_scale": "model-00001-of-00002.safetensors",
365
+ "backbone.layers.4.mixer.norm.weight": "model-00001-of-00002.safetensors",
366
+ "backbone.layers.4.mixer.out_proj.input_scale": "model-00001-of-00002.safetensors",
367
+ "backbone.layers.4.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
368
+ "backbone.layers.4.mixer.out_proj.weight_scale": "model-00001-of-00002.safetensors",
369
+ "backbone.layers.4.norm.weight": "model-00001-of-00002.safetensors",
370
+ "backbone.layers.40.mixer.k_proj.input_scale": "model-00002-of-00002.safetensors",
371
+ "backbone.layers.40.mixer.k_proj.k_scale": "model-00002-of-00002.safetensors",
372
+ "backbone.layers.40.mixer.k_proj.weight": "model-00002-of-00002.safetensors",
373
+ "backbone.layers.40.mixer.k_proj.weight_scale": "model-00002-of-00002.safetensors",
374
+ "backbone.layers.40.mixer.o_proj.input_scale": "model-00002-of-00002.safetensors",
375
+ "backbone.layers.40.mixer.o_proj.weight": "model-00002-of-00002.safetensors",
376
+ "backbone.layers.40.mixer.o_proj.weight_scale": "model-00002-of-00002.safetensors",
377
+ "backbone.layers.40.mixer.q_proj.input_scale": "model-00002-of-00002.safetensors",
378
+ "backbone.layers.40.mixer.q_proj.weight": "model-00002-of-00002.safetensors",
379
+ "backbone.layers.40.mixer.q_proj.weight_scale": "model-00002-of-00002.safetensors",
380
+ "backbone.layers.40.mixer.v_proj.input_scale": "model-00002-of-00002.safetensors",
381
+ "backbone.layers.40.mixer.v_proj.v_scale": "model-00002-of-00002.safetensors",
382
+ "backbone.layers.40.mixer.v_proj.weight": "model-00002-of-00002.safetensors",
383
+ "backbone.layers.40.mixer.v_proj.weight_scale": "model-00002-of-00002.safetensors",
384
+ "backbone.layers.40.norm.weight": "model-00002-of-00002.safetensors",
385
+ "backbone.layers.41.mixer.down_proj.input_scale": "model-00002-of-00002.safetensors",
386
+ "backbone.layers.41.mixer.down_proj.weight": "model-00002-of-00002.safetensors",
387
+ "backbone.layers.41.mixer.down_proj.weight_scale": "model-00002-of-00002.safetensors",
388
+ "backbone.layers.41.mixer.up_proj.input_scale": "model-00002-of-00002.safetensors",
389
+ "backbone.layers.41.mixer.up_proj.weight": "model-00002-of-00002.safetensors",
390
+ "backbone.layers.41.mixer.up_proj.weight_scale": "model-00002-of-00002.safetensors",
391
+ "backbone.layers.41.norm.weight": "model-00002-of-00002.safetensors",
392
+ "backbone.layers.42.mixer.A_log": "model-00002-of-00002.safetensors",
393
+ "backbone.layers.42.mixer.D": "model-00002-of-00002.safetensors",
394
+ "backbone.layers.42.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
395
+ "backbone.layers.42.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
396
+ "backbone.layers.42.mixer.dt_bias": "model-00002-of-00002.safetensors",
397
+ "backbone.layers.42.mixer.in_proj.input_scale": "model-00002-of-00002.safetensors",
398
+ "backbone.layers.42.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
399
+ "backbone.layers.42.mixer.in_proj.weight_scale": "model-00002-of-00002.safetensors",
400
+ "backbone.layers.42.mixer.norm.weight": "model-00002-of-00002.safetensors",
401
+ "backbone.layers.42.mixer.out_proj.input_scale": "model-00002-of-00002.safetensors",
402
+ "backbone.layers.42.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
403
+ "backbone.layers.42.mixer.out_proj.weight_scale": "model-00002-of-00002.safetensors",
404
+ "backbone.layers.42.norm.weight": "model-00002-of-00002.safetensors",
405
+ "backbone.layers.43.mixer.down_proj.input_scale": "model-00002-of-00002.safetensors",
406
+ "backbone.layers.43.mixer.down_proj.weight": "model-00002-of-00002.safetensors",
407
+ "backbone.layers.43.mixer.down_proj.weight_scale": "model-00002-of-00002.safetensors",
408
+ "backbone.layers.43.mixer.up_proj.input_scale": "model-00002-of-00002.safetensors",
409
+ "backbone.layers.43.mixer.up_proj.weight": "model-00002-of-00002.safetensors",
410
+ "backbone.layers.43.mixer.up_proj.weight_scale": "model-00002-of-00002.safetensors",
411
+ "backbone.layers.43.norm.weight": "model-00002-of-00002.safetensors",
412
+ "backbone.layers.44.mixer.A_log": "model-00002-of-00002.safetensors",
413
+ "backbone.layers.44.mixer.D": "model-00002-of-00002.safetensors",
414
+ "backbone.layers.44.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
415
+ "backbone.layers.44.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
416
+ "backbone.layers.44.mixer.dt_bias": "model-00002-of-00002.safetensors",
417
+ "backbone.layers.44.mixer.in_proj.input_scale": "model-00002-of-00002.safetensors",
418
+ "backbone.layers.44.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
419
+ "backbone.layers.44.mixer.in_proj.weight_scale": "model-00002-of-00002.safetensors",
420
+ "backbone.layers.44.mixer.norm.weight": "model-00002-of-00002.safetensors",
421
+ "backbone.layers.44.mixer.out_proj.input_scale": "model-00002-of-00002.safetensors",
422
+ "backbone.layers.44.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
423
+ "backbone.layers.44.mixer.out_proj.weight_scale": "model-00002-of-00002.safetensors",
424
+ "backbone.layers.44.norm.weight": "model-00002-of-00002.safetensors",
425
+ "backbone.layers.45.mixer.down_proj.input_scale": "model-00002-of-00002.safetensors",
426
+ "backbone.layers.45.mixer.down_proj.weight": "model-00002-of-00002.safetensors",
427
+ "backbone.layers.45.mixer.down_proj.weight_scale": "model-00002-of-00002.safetensors",
428
+ "backbone.layers.45.mixer.up_proj.input_scale": "model-00002-of-00002.safetensors",
429
+ "backbone.layers.45.mixer.up_proj.weight": "model-00002-of-00002.safetensors",
430
+ "backbone.layers.45.mixer.up_proj.weight_scale": "model-00002-of-00002.safetensors",
431
+ "backbone.layers.45.norm.weight": "model-00002-of-00002.safetensors",
432
+ "backbone.layers.46.mixer.A_log": "model-00002-of-00002.safetensors",
433
+ "backbone.layers.46.mixer.D": "model-00002-of-00002.safetensors",
434
+ "backbone.layers.46.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
435
+ "backbone.layers.46.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
436
+ "backbone.layers.46.mixer.dt_bias": "model-00002-of-00002.safetensors",
437
+ "backbone.layers.46.mixer.in_proj.input_scale": "model-00002-of-00002.safetensors",
438
+ "backbone.layers.46.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
439
+ "backbone.layers.46.mixer.in_proj.weight_scale": "model-00002-of-00002.safetensors",
440
+ "backbone.layers.46.mixer.norm.weight": "model-00002-of-00002.safetensors",
441
+ "backbone.layers.46.mixer.out_proj.input_scale": "model-00002-of-00002.safetensors",
442
+ "backbone.layers.46.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
443
+ "backbone.layers.46.mixer.out_proj.weight_scale": "model-00002-of-00002.safetensors",
444
+ "backbone.layers.46.norm.weight": "model-00002-of-00002.safetensors",
445
+ "backbone.layers.47.mixer.down_proj.input_scale": "model-00002-of-00002.safetensors",
446
+ "backbone.layers.47.mixer.down_proj.weight": "model-00002-of-00002.safetensors",
447
+ "backbone.layers.47.mixer.down_proj.weight_scale": "model-00002-of-00002.safetensors",
448
+ "backbone.layers.47.mixer.up_proj.input_scale": "model-00002-of-00002.safetensors",
449
+ "backbone.layers.47.mixer.up_proj.weight": "model-00002-of-00002.safetensors",
450
+ "backbone.layers.47.mixer.up_proj.weight_scale": "model-00002-of-00002.safetensors",
451
+ "backbone.layers.47.norm.weight": "model-00002-of-00002.safetensors",
452
+ "backbone.layers.48.mixer.A_log": "model-00002-of-00002.safetensors",
453
+ "backbone.layers.48.mixer.D": "model-00002-of-00002.safetensors",
454
+ "backbone.layers.48.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
455
+ "backbone.layers.48.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
456
+ "backbone.layers.48.mixer.dt_bias": "model-00002-of-00002.safetensors",
457
+ "backbone.layers.48.mixer.in_proj.input_scale": "model-00002-of-00002.safetensors",
458
+ "backbone.layers.48.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
459
+ "backbone.layers.48.mixer.in_proj.weight_scale": "model-00002-of-00002.safetensors",
460
+ "backbone.layers.48.mixer.norm.weight": "model-00002-of-00002.safetensors",
461
+ "backbone.layers.48.mixer.out_proj.input_scale": "model-00002-of-00002.safetensors",
462
+ "backbone.layers.48.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
463
+ "backbone.layers.48.mixer.out_proj.weight_scale": "model-00002-of-00002.safetensors",
464
+ "backbone.layers.48.norm.weight": "model-00002-of-00002.safetensors",
465
+ "backbone.layers.49.mixer.down_proj.input_scale": "model-00002-of-00002.safetensors",
466
+ "backbone.layers.49.mixer.down_proj.weight": "model-00002-of-00002.safetensors",
467
+ "backbone.layers.49.mixer.down_proj.weight_scale": "model-00002-of-00002.safetensors",
468
+ "backbone.layers.49.mixer.up_proj.input_scale": "model-00002-of-00002.safetensors",
469
+ "backbone.layers.49.mixer.up_proj.weight": "model-00002-of-00002.safetensors",
470
+ "backbone.layers.49.mixer.up_proj.weight_scale": "model-00002-of-00002.safetensors",
471
+ "backbone.layers.49.norm.weight": "model-00002-of-00002.safetensors",
472
+ "backbone.layers.5.mixer.down_proj.input_scale": "model-00001-of-00002.safetensors",
473
+ "backbone.layers.5.mixer.down_proj.weight": "model-00001-of-00002.safetensors",
474
+ "backbone.layers.5.mixer.down_proj.weight_scale": "model-00001-of-00002.safetensors",
475
+ "backbone.layers.5.mixer.up_proj.input_scale": "model-00001-of-00002.safetensors",
476
+ "backbone.layers.5.mixer.up_proj.weight": "model-00001-of-00002.safetensors",
477
+ "backbone.layers.5.mixer.up_proj.weight_scale": "model-00001-of-00002.safetensors",
478
+ "backbone.layers.5.norm.weight": "model-00001-of-00002.safetensors",
479
+ "backbone.layers.50.mixer.A_log": "model-00002-of-00002.safetensors",
480
+ "backbone.layers.50.mixer.D": "model-00002-of-00002.safetensors",
481
+ "backbone.layers.50.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
482
+ "backbone.layers.50.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
483
+ "backbone.layers.50.mixer.dt_bias": "model-00002-of-00002.safetensors",
484
+ "backbone.layers.50.mixer.in_proj.input_scale": "model-00002-of-00002.safetensors",
485
+ "backbone.layers.50.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
486
+ "backbone.layers.50.mixer.in_proj.weight_scale": "model-00002-of-00002.safetensors",
487
+ "backbone.layers.50.mixer.norm.weight": "model-00002-of-00002.safetensors",
488
+ "backbone.layers.50.mixer.out_proj.input_scale": "model-00002-of-00002.safetensors",
489
+ "backbone.layers.50.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
490
+ "backbone.layers.50.mixer.out_proj.weight_scale": "model-00002-of-00002.safetensors",
491
+ "backbone.layers.50.norm.weight": "model-00002-of-00002.safetensors",
492
+ "backbone.layers.51.mixer.down_proj.input_scale": "model-00002-of-00002.safetensors",
493
+ "backbone.layers.51.mixer.down_proj.weight": "model-00002-of-00002.safetensors",
494
+ "backbone.layers.51.mixer.down_proj.weight_scale": "model-00002-of-00002.safetensors",
495
+ "backbone.layers.51.mixer.up_proj.input_scale": "model-00002-of-00002.safetensors",
496
+ "backbone.layers.51.mixer.up_proj.weight": "model-00002-of-00002.safetensors",
497
+ "backbone.layers.51.mixer.up_proj.weight_scale": "model-00002-of-00002.safetensors",
498
+ "backbone.layers.51.norm.weight": "model-00002-of-00002.safetensors",
499
+ "backbone.layers.6.mixer.A_log": "model-00001-of-00002.safetensors",
500
+ "backbone.layers.6.mixer.D": "model-00001-of-00002.safetensors",
501
+ "backbone.layers.6.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
502
+ "backbone.layers.6.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
503
+ "backbone.layers.6.mixer.dt_bias": "model-00001-of-00002.safetensors",
504
+ "backbone.layers.6.mixer.in_proj.input_scale": "model-00001-of-00002.safetensors",
505
+ "backbone.layers.6.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
506
+ "backbone.layers.6.mixer.in_proj.weight_scale": "model-00001-of-00002.safetensors",
507
+ "backbone.layers.6.mixer.norm.weight": "model-00001-of-00002.safetensors",
508
+ "backbone.layers.6.mixer.out_proj.input_scale": "model-00001-of-00002.safetensors",
509
+ "backbone.layers.6.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
510
+ "backbone.layers.6.mixer.out_proj.weight_scale": "model-00001-of-00002.safetensors",
511
+ "backbone.layers.6.norm.weight": "model-00001-of-00002.safetensors",
512
+ "backbone.layers.7.mixer.k_proj.input_scale": "model-00001-of-00002.safetensors",
513
+ "backbone.layers.7.mixer.k_proj.k_scale": "model-00001-of-00002.safetensors",
514
+ "backbone.layers.7.mixer.k_proj.weight": "model-00001-of-00002.safetensors",
515
+ "backbone.layers.7.mixer.k_proj.weight_scale": "model-00001-of-00002.safetensors",
516
+ "backbone.layers.7.mixer.o_proj.input_scale": "model-00001-of-00002.safetensors",
517
+ "backbone.layers.7.mixer.o_proj.weight": "model-00001-of-00002.safetensors",
518
+ "backbone.layers.7.mixer.o_proj.weight_scale": "model-00001-of-00002.safetensors",
519
+ "backbone.layers.7.mixer.q_proj.input_scale": "model-00001-of-00002.safetensors",
520
+ "backbone.layers.7.mixer.q_proj.weight": "model-00001-of-00002.safetensors",
521
+ "backbone.layers.7.mixer.q_proj.weight_scale": "model-00001-of-00002.safetensors",
522
+ "backbone.layers.7.mixer.v_proj.input_scale": "model-00001-of-00002.safetensors",
523
+ "backbone.layers.7.mixer.v_proj.v_scale": "model-00001-of-00002.safetensors",
524
+ "backbone.layers.7.mixer.v_proj.weight": "model-00001-of-00002.safetensors",
525
+ "backbone.layers.7.mixer.v_proj.weight_scale": "model-00001-of-00002.safetensors",
526
+ "backbone.layers.7.norm.weight": "model-00001-of-00002.safetensors",
527
+ "backbone.layers.8.mixer.down_proj.input_scale": "model-00001-of-00002.safetensors",
528
+ "backbone.layers.8.mixer.down_proj.weight": "model-00001-of-00002.safetensors",
529
+ "backbone.layers.8.mixer.down_proj.weight_scale": "model-00001-of-00002.safetensors",
530
+ "backbone.layers.8.mixer.up_proj.input_scale": "model-00001-of-00002.safetensors",
531
+ "backbone.layers.8.mixer.up_proj.weight": "model-00001-of-00002.safetensors",
532
+ "backbone.layers.8.mixer.up_proj.weight_scale": "model-00001-of-00002.safetensors",
533
+ "backbone.layers.8.norm.weight": "model-00001-of-00002.safetensors",
534
+ "backbone.layers.9.mixer.A_log": "model-00001-of-00002.safetensors",
535
+ "backbone.layers.9.mixer.D": "model-00001-of-00002.safetensors",
536
+ "backbone.layers.9.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
537
+ "backbone.layers.9.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
538
+ "backbone.layers.9.mixer.dt_bias": "model-00001-of-00002.safetensors",
539
+ "backbone.layers.9.mixer.in_proj.input_scale": "model-00001-of-00002.safetensors",
540
+ "backbone.layers.9.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
541
+ "backbone.layers.9.mixer.in_proj.weight_scale": "model-00001-of-00002.safetensors",
542
+ "backbone.layers.9.mixer.norm.weight": "model-00001-of-00002.safetensors",
543
+ "backbone.layers.9.mixer.out_proj.input_scale": "model-00001-of-00002.safetensors",
544
+ "backbone.layers.9.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
545
+ "backbone.layers.9.mixer.out_proj.weight_scale": "model-00001-of-00002.safetensors",
546
+ "backbone.layers.9.norm.weight": "model-00001-of-00002.safetensors",
547
+ "backbone.norm_f.weight": "model-00002-of-00002.safetensors",
548
+ "lm_head.weight": "model-00002-of-00002.safetensors"
549
+ }
550
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "<SPECIAL_11>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": "<SPECIAL_11>",
10
+ "unk_token": {
11
+ "content": "<unk>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ }
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