Hugging Face's logo

vibrantumbra
/
vibrant-umbra-7b

Safetensors
English
zamba2
Model card Files Community
vibrantumbra commited on
Commit
0c6a2ef
·
verified ·
1 Parent(s): e30b477

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. config.json +149 -0
  2. generation_config.json +7 -0
  3. model-00001-of-00003.safetensors +3 -0
  4. model-00002-of-00003.safetensors +3 -0
  5. model-00003-of-00003.safetensors +3 -0
  6. model.safetensors.index.json +794 -0
  7. special_tokens_map.json +34 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +72 -0
config.json ADDED
@@ -0,0 +1,149 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/shared2/checkpoints/posttraining/zamba2_sft_dpo_score3161_upstream_rlvr_all/checkpoint-6562",
3
+ "adapter_rank": 128,
4
+ "add_bias_linear": false,
5
+ "architectures": [
6
+ "Zamba2ForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "attention_head_dim": 224,
10
+ "attention_hidden_size": 7168,
11
+ "bos_token_id": 32001,
12
+ "chunk_size": 256,
13
+ "eos_token_id": 32002,
14
+ "ffn_hidden_size": 14336,
15
+ "hidden_act": "gelu",
16
+ "hidden_size": 3584,
17
+ "hybrid_layer_ids": [
18
+ 6,
19
+ 11,
20
+ 17,
21
+ 23,
22
+ 29,
23
+ 35,
24
+ 41,
25
+ 47,
26
+ 53,
27
+ 59,
28
+ 65,
29
+ 71,
30
+ 77
31
+ ],
32
+ "initializer_range": 0.02,
33
+ "intermediate_size": 14336,
34
+ "kv_channels": 112,
35
+ "layers_block_type": [
36
+ "mamba",
37
+ "mamba",
38
+ "mamba",
39
+ "mamba",
40
+ "mamba",
41
+ "mamba",
42
+ "hybrid",
43
+ "mamba",
44
+ "mamba",
45
+ "mamba",
46
+ "mamba",
47
+ "hybrid",
48
+ "mamba",
49
+ "mamba",
50
+ "mamba",
51
+ "mamba",
52
+ "mamba",
53
+ "hybrid",
54
+ "mamba",
55
+ "mamba",
56
+ "mamba",
57
+ "mamba",
58
+ "mamba",
59
+ "hybrid",
60
+ "mamba",
61
+ "mamba",
62
+ "mamba",
63
+ "mamba",
64
+ "mamba",
65
+ "hybrid",
66
+ "mamba",
67
+ "mamba",
68
+ "mamba",
69
+ "mamba",
70
+ "mamba",
71
+ "hybrid",
72
+ "mamba",
73
+ "mamba",
74
+ "mamba",
75
+ "mamba",
76
+ "mamba",
77
+ "hybrid",
78
+ "mamba",
79
+ "mamba",
80
+ "mamba",
81
+ "mamba",
82
+ "mamba",
83
+ "hybrid",
84
+ "mamba",
85
+ "mamba",
86
+ "mamba",
87
+ "mamba",
88
+ "mamba",
89
+ "hybrid",
90
+ "mamba",
91
+ "mamba",
92
+ "mamba",
93
+ "mamba",
94
+ "mamba",
95
+ "hybrid",
96
+ "mamba",
97
+ "mamba",
98
+ "mamba",
99
+ "mamba",
100
+ "mamba",
101
+ "hybrid",
102
+ "mamba",
103
+ "mamba",
104
+ "mamba",
105
+ "mamba",
106
+ "mamba",
107
+ "hybrid",
108
+ "mamba",
109
+ "mamba",
110
+ "mamba",
111
+ "mamba",
112
+ "mamba",
113
+ "hybrid",
114
+ "mamba",
115
+ "mamba",
116
+ "mamba"
117
+ ],
118
+ "mamba_d_conv": 4,
119
+ "mamba_d_state": 64,
120
+ "mamba_expand": 2,
121
+ "mamba_headdim": 64,
122
+ "mamba_ngroups": 2,
123
+ "max_position_embeddings": 4096,
124
+ "model_type": "zamba2",
125
+ "n_mamba_heads": 112,
126
+ "num_attention_heads": 32,
127
+ "num_hidden_layers": 81,
128
+ "num_key_value_heads": 32,
129
+ "num_logits_to_keep": 1,
130
+ "num_mem_blocks": 2,
131
+ "num_query_groups": 32,
132
+ "pad_token_id": 32000,
133
+ "rms_norm_eps": 1e-05,
134
+ "rope_theta": 10000,
135
+ "time_step_floor": 0.0001,
136
+ "time_step_limit": null,
137
+ "time_step_max": 0.1,
138
+ "time_step_min": 0.001,
139
+ "torch_dtype": "bfloat16",
140
+ "transformers_version": "4.50.0.dev0",
141
+ "use_cache": false,
142
+ "use_conv_bias": true,
143
+ "use_long_context": false,
144
+ "use_mem_eff_path": false,
145
+ "use_mem_rope": true,
146
+ "use_shared_attention_adapter": false,
147
+ "use_shared_mlp_adapter": true,
148
+ "vocab_size": 32003
149
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "eos_token_id": 2,
4
+ "temperature": null,
5
+ "top_p": null,
6
+ "transformers_version": "4.50.0.dev0"
7
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:538f813fdc9775c9e8ba774e6ad823ea1ab03d15508d84160e281c5a7c3e302f
3
+ size 4992757608
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7b0e9747661fb51886698c7cb73bb2b60bf3e62e8a9f05932326b1699c54544
3
+ size 4991603936
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8cdc7499abd48a608b0aca9a6f75892afe86b45c685f2e4e3d85947c82d81a8
3
+ size 4729247376
model.safetensors.index.json ADDED
@@ -0,0 +1,794 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14713521024
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
7
+ "model.final_layernorm.weight": "model-00003-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mamba.A_log": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mamba.D": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.mamba.dt_bias": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.mamba.norm.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mamba.A_log": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mamba.D": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.mamba.dt_bias": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.mamba.norm.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
27
+ "model.layers.10.mamba.A_log": "model-00001-of-00003.safetensors",
28
+ "model.layers.10.mamba.D": "model-00001-of-00003.safetensors",
29
+ "model.layers.10.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
30
+ "model.layers.10.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
31
+ "model.layers.10.mamba.dt_bias": "model-00001-of-00003.safetensors",
32
+ "model.layers.10.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.10.mamba.norm.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.10.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.11.linear.weight": "model-00001-of-00003.safetensors",
36
+ "model.layers.11.mamba_decoder.input_layernorm.weight": "model-00001-of-00003.safetensors",
37
+ "model.layers.11.mamba_decoder.mamba.A_log": "model-00001-of-00003.safetensors",
38
+ "model.layers.11.mamba_decoder.mamba.D": "model-00001-of-00003.safetensors",
39
+ "model.layers.11.mamba_decoder.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
40
+ "model.layers.11.mamba_decoder.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
41
+ "model.layers.11.mamba_decoder.mamba.dt_bias": "model-00001-of-00003.safetensors",
42
+ "model.layers.11.mamba_decoder.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
43
+ "model.layers.11.mamba_decoder.mamba.norm.weight": "model-00001-of-00003.safetensors",
44
+ "model.layers.11.mamba_decoder.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
45
+ "model.layers.11.shared_transformer.feed_forward.down_proj.weight": "model-00001-of-00003.safetensors",
46
+ "model.layers.11.shared_transformer.feed_forward.gate_up_proj.weight": "model-00001-of-00003.safetensors",
47
+ "model.layers.11.shared_transformer.feed_forward.gate_up_proj_adapter_list.1.0.weight": "model-00001-of-00003.safetensors",
48
+ "model.layers.11.shared_transformer.feed_forward.gate_up_proj_adapter_list.1.1.weight": "model-00001-of-00003.safetensors",
49
+ "model.layers.11.shared_transformer.feed_forward.gate_up_proj_adapter_list.11.0.weight": "model-00001-of-00003.safetensors",
50
+ "model.layers.11.shared_transformer.feed_forward.gate_up_proj_adapter_list.11.1.weight": "model-00001-of-00003.safetensors",
51
+ "model.layers.11.shared_transformer.feed_forward.gate_up_proj_adapter_list.3.0.weight": "model-00001-of-00003.safetensors",
52
+ "model.layers.11.shared_transformer.feed_forward.gate_up_proj_adapter_list.3.1.weight": "model-00001-of-00003.safetensors",
53
+ "model.layers.11.shared_transformer.feed_forward.gate_up_proj_adapter_list.5.0.weight": "model-00001-of-00003.safetensors",
54
+ "model.layers.11.shared_transformer.feed_forward.gate_up_proj_adapter_list.5.1.weight": "model-00001-of-00003.safetensors",
55
+ "model.layers.11.shared_transformer.feed_forward.gate_up_proj_adapter_list.7.0.weight": "model-00001-of-00003.safetensors",
56
+ "model.layers.11.shared_transformer.feed_forward.gate_up_proj_adapter_list.7.1.weight": "model-00001-of-00003.safetensors",
57
+ "model.layers.11.shared_transformer.feed_forward.gate_up_proj_adapter_list.9.0.weight": "model-00001-of-00003.safetensors",
58
+ "model.layers.11.shared_transformer.feed_forward.gate_up_proj_adapter_list.9.1.weight": "model-00001-of-00003.safetensors",
59
+ "model.layers.11.shared_transformer.input_layernorm.weight": "model-00001-of-00003.safetensors",
60
+ "model.layers.11.shared_transformer.pre_ff_layernorm.weight": "model-00001-of-00003.safetensors",
61
+ "model.layers.11.shared_transformer.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
62
+ "model.layers.11.shared_transformer.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
63
+ "model.layers.11.shared_transformer.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
64
+ "model.layers.11.shared_transformer.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
65
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
66
+ "model.layers.12.mamba.A_log": "model-00001-of-00003.safetensors",
67
+ "model.layers.12.mamba.D": "model-00001-of-00003.safetensors",
68
+ "model.layers.12.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
69
+ "model.layers.12.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
70
+ "model.layers.12.mamba.dt_bias": "model-00001-of-00003.safetensors",
71
+ "model.layers.12.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
72
+ "model.layers.12.mamba.norm.weight": "model-00001-of-00003.safetensors",
73
+ "model.layers.12.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
74
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
75
+ "model.layers.13.mamba.A_log": "model-00001-of-00003.safetensors",
76
+ "model.layers.13.mamba.D": "model-00001-of-00003.safetensors",
77
+ "model.layers.13.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
78
+ "model.layers.13.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
79
+ "model.layers.13.mamba.dt_bias": "model-00001-of-00003.safetensors",
80
+ "model.layers.13.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
81
+ "model.layers.13.mamba.norm.weight": "model-00001-of-00003.safetensors",
82
+ "model.layers.13.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
83
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
84
+ "model.layers.14.mamba.A_log": "model-00001-of-00003.safetensors",
85
+ "model.layers.14.mamba.D": "model-00001-of-00003.safetensors",
86
+ "model.layers.14.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
87
+ "model.layers.14.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
88
+ "model.layers.14.mamba.dt_bias": "model-00001-of-00003.safetensors",
89
+ "model.layers.14.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
90
+ "model.layers.14.mamba.norm.weight": "model-00001-of-00003.safetensors",
91
+ "model.layers.14.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
93
+ "model.layers.15.mamba.A_log": "model-00001-of-00003.safetensors",
94
+ "model.layers.15.mamba.D": "model-00001-of-00003.safetensors",
95
+ "model.layers.15.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
96
+ "model.layers.15.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
97
+ "model.layers.15.mamba.dt_bias": "model-00001-of-00003.safetensors",
98
+ "model.layers.15.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
99
+ "model.layers.15.mamba.norm.weight": "model-00001-of-00003.safetensors",
100
+ "model.layers.15.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
101
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors",
102
+ "model.layers.16.mamba.A_log": "model-00001-of-00003.safetensors",
103
+ "model.layers.16.mamba.D": "model-00001-of-00003.safetensors",
104
+ "model.layers.16.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
105
+ "model.layers.16.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
106
+ "model.layers.16.mamba.dt_bias": "model-00001-of-00003.safetensors",
107
+ "model.layers.16.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
108
+ "model.layers.16.mamba.norm.weight": "model-00001-of-00003.safetensors",
109
+ "model.layers.16.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
110
+ "model.layers.17.linear.weight": "model-00001-of-00003.safetensors",
111
+ "model.layers.17.mamba_decoder.input_layernorm.weight": "model-00001-of-00003.safetensors",
112
+ "model.layers.17.mamba_decoder.mamba.A_log": "model-00001-of-00003.safetensors",
113
+ "model.layers.17.mamba_decoder.mamba.D": "model-00001-of-00003.safetensors",
114
+ "model.layers.17.mamba_decoder.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
115
+ "model.layers.17.mamba_decoder.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
116
+ "model.layers.17.mamba_decoder.mamba.dt_bias": "model-00001-of-00003.safetensors",
117
+ "model.layers.17.mamba_decoder.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.17.mamba_decoder.mamba.norm.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.17.mamba_decoder.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.18.mamba.A_log": "model-00001-of-00003.safetensors",
122
+ "model.layers.18.mamba.D": "model-00001-of-00003.safetensors",
123
+ "model.layers.18.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
124
+ "model.layers.18.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
125
+ "model.layers.18.mamba.dt_bias": "model-00001-of-00003.safetensors",
126
+ "model.layers.18.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
127
+ "model.layers.18.mamba.norm.weight": "model-00001-of-00003.safetensors",
128
+ "model.layers.18.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
129
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors",
130
+ "model.layers.19.mamba.A_log": "model-00001-of-00003.safetensors",
131
+ "model.layers.19.mamba.D": "model-00001-of-00003.safetensors",
132
+ "model.layers.19.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
133
+ "model.layers.19.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
134
+ "model.layers.19.mamba.dt_bias": "model-00001-of-00003.safetensors",
135
+ "model.layers.19.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
136
+ "model.layers.19.mamba.norm.weight": "model-00001-of-00003.safetensors",
137
+ "model.layers.19.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
138
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
139
+ "model.layers.2.mamba.A_log": "model-00001-of-00003.safetensors",
140
+ "model.layers.2.mamba.D": "model-00001-of-00003.safetensors",
141
+ "model.layers.2.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
142
+ "model.layers.2.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
143
+ "model.layers.2.mamba.dt_bias": "model-00001-of-00003.safetensors",
144
+ "model.layers.2.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
145
+ "model.layers.2.mamba.norm.weight": "model-00001-of-00003.safetensors",
146
+ "model.layers.2.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
147
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
148
+ "model.layers.20.mamba.A_log": "model-00001-of-00003.safetensors",
149
+ "model.layers.20.mamba.D": "model-00001-of-00003.safetensors",
150
+ "model.layers.20.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
151
+ "model.layers.20.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
152
+ "model.layers.20.mamba.dt_bias": "model-00001-of-00003.safetensors",
153
+ "model.layers.20.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
154
+ "model.layers.20.mamba.norm.weight": "model-00001-of-00003.safetensors",
155
+ "model.layers.20.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
156
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
157
+ "model.layers.21.mamba.A_log": "model-00002-of-00003.safetensors",
158
+ "model.layers.21.mamba.D": "model-00002-of-00003.safetensors",
159
+ "model.layers.21.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
160
+ "model.layers.21.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
161
+ "model.layers.21.mamba.dt_bias": "model-00002-of-00003.safetensors",
162
+ "model.layers.21.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
163
+ "model.layers.21.mamba.norm.weight": "model-00002-of-00003.safetensors",
164
+ "model.layers.21.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
165
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
166
+ "model.layers.22.mamba.A_log": "model-00002-of-00003.safetensors",
167
+ "model.layers.22.mamba.D": "model-00002-of-00003.safetensors",
168
+ "model.layers.22.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
169
+ "model.layers.22.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
170
+ "model.layers.22.mamba.dt_bias": "model-00002-of-00003.safetensors",
171
+ "model.layers.22.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
172
+ "model.layers.22.mamba.norm.weight": "model-00002-of-00003.safetensors",
173
+ "model.layers.22.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
174
+ "model.layers.23.linear.weight": "model-00002-of-00003.safetensors",
175
+ "model.layers.23.mamba_decoder.input_layernorm.weight": "model-00002-of-00003.safetensors",
176
+ "model.layers.23.mamba_decoder.mamba.A_log": "model-00002-of-00003.safetensors",
177
+ "model.layers.23.mamba_decoder.mamba.D": "model-00002-of-00003.safetensors",
178
+ "model.layers.23.mamba_decoder.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
179
+ "model.layers.23.mamba_decoder.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
180
+ "model.layers.23.mamba_decoder.mamba.dt_bias": "model-00002-of-00003.safetensors",
181
+ "model.layers.23.mamba_decoder.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
182
+ "model.layers.23.mamba_decoder.mamba.norm.weight": "model-00002-of-00003.safetensors",
183
+ "model.layers.23.mamba_decoder.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
184
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
185
+ "model.layers.24.mamba.A_log": "model-00002-of-00003.safetensors",
186
+ "model.layers.24.mamba.D": "model-00002-of-00003.safetensors",
187
+ "model.layers.24.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
188
+ "model.layers.24.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
189
+ "model.layers.24.mamba.dt_bias": "model-00002-of-00003.safetensors",
190
+ "model.layers.24.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
191
+ "model.layers.24.mamba.norm.weight": "model-00002-of-00003.safetensors",
192
+ "model.layers.24.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
193
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
194
+ "model.layers.25.mamba.A_log": "model-00002-of-00003.safetensors",
195
+ "model.layers.25.mamba.D": "model-00002-of-00003.safetensors",
196
+ "model.layers.25.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
197
+ "model.layers.25.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
198
+ "model.layers.25.mamba.dt_bias": "model-00002-of-00003.safetensors",
199
+ "model.layers.25.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
200
+ "model.layers.25.mamba.norm.weight": "model-00002-of-00003.safetensors",
201
+ "model.layers.25.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
202
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
203
+ "model.layers.26.mamba.A_log": "model-00002-of-00003.safetensors",
204
+ "model.layers.26.mamba.D": "model-00002-of-00003.safetensors",
205
+ "model.layers.26.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
206
+ "model.layers.26.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
207
+ "model.layers.26.mamba.dt_bias": "model-00002-of-00003.safetensors",
208
+ "model.layers.26.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
209
+ "model.layers.26.mamba.norm.weight": "model-00002-of-00003.safetensors",
210
+ "model.layers.26.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
211
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
212
+ "model.layers.27.mamba.A_log": "model-00002-of-00003.safetensors",
213
+ "model.layers.27.mamba.D": "model-00002-of-00003.safetensors",
214
+ "model.layers.27.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
215
+ "model.layers.27.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
216
+ "model.layers.27.mamba.dt_bias": "model-00002-of-00003.safetensors",
217
+ "model.layers.27.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
218
+ "model.layers.27.mamba.norm.weight": "model-00002-of-00003.safetensors",
219
+ "model.layers.27.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
220
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
221
+ "model.layers.28.mamba.A_log": "model-00002-of-00003.safetensors",
222
+ "model.layers.28.mamba.D": "model-00002-of-00003.safetensors",
223
+ "model.layers.28.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
224
+ "model.layers.28.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
225
+ "model.layers.28.mamba.dt_bias": "model-00002-of-00003.safetensors",
226
+ "model.layers.28.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
227
+ "model.layers.28.mamba.norm.weight": "model-00002-of-00003.safetensors",
228
+ "model.layers.28.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
229
+ "model.layers.29.linear.weight": "model-00002-of-00003.safetensors",
230
+ "model.layers.29.mamba_decoder.input_layernorm.weight": "model-00002-of-00003.safetensors",
231
+ "model.layers.29.mamba_decoder.mamba.A_log": "model-00002-of-00003.safetensors",
232
+ "model.layers.29.mamba_decoder.mamba.D": "model-00002-of-00003.safetensors",
233
+ "model.layers.29.mamba_decoder.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
234
+ "model.layers.29.mamba_decoder.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
235
+ "model.layers.29.mamba_decoder.mamba.dt_bias": "model-00002-of-00003.safetensors",
236
+ "model.layers.29.mamba_decoder.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
237
+ "model.layers.29.mamba_decoder.mamba.norm.weight": "model-00002-of-00003.safetensors",
238
+ "model.layers.29.mamba_decoder.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
239
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
240
+ "model.layers.3.mamba.A_log": "model-00001-of-00003.safetensors",
241
+ "model.layers.3.mamba.D": "model-00001-of-00003.safetensors",
242
+ "model.layers.3.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
243
+ "model.layers.3.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.3.mamba.dt_bias": "model-00001-of-00003.safetensors",
245
+ "model.layers.3.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
246
+ "model.layers.3.mamba.norm.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.3.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
249
+ "model.layers.30.mamba.A_log": "model-00002-of-00003.safetensors",
250
+ "model.layers.30.mamba.D": "model-00002-of-00003.safetensors",
251
+ "model.layers.30.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
252
+ "model.layers.30.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
253
+ "model.layers.30.mamba.dt_bias": "model-00002-of-00003.safetensors",
254
+ "model.layers.30.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
255
+ "model.layers.30.mamba.norm.weight": "model-00002-of-00003.safetensors",
256
+ "model.layers.30.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
257
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
258
+ "model.layers.31.mamba.A_log": "model-00002-of-00003.safetensors",
259
+ "model.layers.31.mamba.D": "model-00002-of-00003.safetensors",
260
+ "model.layers.31.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
261
+ "model.layers.31.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
262
+ "model.layers.31.mamba.dt_bias": "model-00002-of-00003.safetensors",
263
+ "model.layers.31.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
264
+ "model.layers.31.mamba.norm.weight": "model-00002-of-00003.safetensors",
265
+ "model.layers.31.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
266
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
267
+ "model.layers.32.mamba.A_log": "model-00002-of-00003.safetensors",
268
+ "model.layers.32.mamba.D": "model-00002-of-00003.safetensors",
269
+ "model.layers.32.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
270
+ "model.layers.32.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
271
+ "model.layers.32.mamba.dt_bias": "model-00002-of-00003.safetensors",
272
+ "model.layers.32.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
273
+ "model.layers.32.mamba.norm.weight": "model-00002-of-00003.safetensors",
274
+ "model.layers.32.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
275
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors",
276
+ "model.layers.33.mamba.A_log": "model-00002-of-00003.safetensors",
277
+ "model.layers.33.mamba.D": "model-00002-of-00003.safetensors",
278
+ "model.layers.33.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
279
+ "model.layers.33.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
280
+ "model.layers.33.mamba.dt_bias": "model-00002-of-00003.safetensors",
281
+ "model.layers.33.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
282
+ "model.layers.33.mamba.norm.weight": "model-00002-of-00003.safetensors",
283
+ "model.layers.33.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
284
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors",
285
+ "model.layers.34.mamba.A_log": "model-00002-of-00003.safetensors",
286
+ "model.layers.34.mamba.D": "model-00002-of-00003.safetensors",
287
+ "model.layers.34.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
288
+ "model.layers.34.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
289
+ "model.layers.34.mamba.dt_bias": "model-00002-of-00003.safetensors",
290
+ "model.layers.34.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
291
+ "model.layers.34.mamba.norm.weight": "model-00002-of-00003.safetensors",
292
+ "model.layers.34.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
293
+ "model.layers.35.linear.weight": "model-00002-of-00003.safetensors",
294
+ "model.layers.35.mamba_decoder.input_layernorm.weight": "model-00002-of-00003.safetensors",
295
+ "model.layers.35.mamba_decoder.mamba.A_log": "model-00002-of-00003.safetensors",
296
+ "model.layers.35.mamba_decoder.mamba.D": "model-00002-of-00003.safetensors",
297
+ "model.layers.35.mamba_decoder.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
298
+ "model.layers.35.mamba_decoder.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
299
+ "model.layers.35.mamba_decoder.mamba.dt_bias": "model-00002-of-00003.safetensors",
300
+ "model.layers.35.mamba_decoder.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
301
+ "model.layers.35.mamba_decoder.mamba.norm.weight": "model-00002-of-00003.safetensors",
302
+ "model.layers.35.mamba_decoder.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
303
+ "model.layers.36.input_layernorm.weight": "model-00002-of-00003.safetensors",
304
+ "model.layers.36.mamba.A_log": "model-00002-of-00003.safetensors",
305
+ "model.layers.36.mamba.D": "model-00002-of-00003.safetensors",
306
+ "model.layers.36.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
307
+ "model.layers.36.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
308
+ "model.layers.36.mamba.dt_bias": "model-00002-of-00003.safetensors",
309
+ "model.layers.36.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
310
+ "model.layers.36.mamba.norm.weight": "model-00002-of-00003.safetensors",
311
+ "model.layers.36.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
312
+ "model.layers.37.input_layernorm.weight": "model-00002-of-00003.safetensors",
313
+ "model.layers.37.mamba.A_log": "model-00002-of-00003.safetensors",
314
+ "model.layers.37.mamba.D": "model-00002-of-00003.safetensors",
315
+ "model.layers.37.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
316
+ "model.layers.37.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
317
+ "model.layers.37.mamba.dt_bias": "model-00002-of-00003.safetensors",
318
+ "model.layers.37.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
319
+ "model.layers.37.mamba.norm.weight": "model-00002-of-00003.safetensors",
320
+ "model.layers.37.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
321
+ "model.layers.38.input_layernorm.weight": "model-00002-of-00003.safetensors",
322
+ "model.layers.38.mamba.A_log": "model-00002-of-00003.safetensors",
323
+ "model.layers.38.mamba.D": "model-00002-of-00003.safetensors",
324
+ "model.layers.38.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
325
+ "model.layers.38.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
326
+ "model.layers.38.mamba.dt_bias": "model-00002-of-00003.safetensors",
327
+ "model.layers.38.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
328
+ "model.layers.38.mamba.norm.weight": "model-00002-of-00003.safetensors",
329
+ "model.layers.38.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
330
+ "model.layers.39.input_layernorm.weight": "model-00002-of-00003.safetensors",
331
+ "model.layers.39.mamba.A_log": "model-00002-of-00003.safetensors",
332
+ "model.layers.39.mamba.D": "model-00002-of-00003.safetensors",
333
+ "model.layers.39.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
334
+ "model.layers.39.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
335
+ "model.layers.39.mamba.dt_bias": "model-00002-of-00003.safetensors",
336
+ "model.layers.39.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
337
+ "model.layers.39.mamba.norm.weight": "model-00002-of-00003.safetensors",
338
+ "model.layers.39.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
339
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
340
+ "model.layers.4.mamba.A_log": "model-00001-of-00003.safetensors",
341
+ "model.layers.4.mamba.D": "model-00001-of-00003.safetensors",
342
+ "model.layers.4.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
343
+ "model.layers.4.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
344
+ "model.layers.4.mamba.dt_bias": "model-00001-of-00003.safetensors",
345
+ "model.layers.4.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
346
+ "model.layers.4.mamba.norm.weight": "model-00001-of-00003.safetensors",
347
+ "model.layers.4.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
348
+ "model.layers.40.input_layernorm.weight": "model-00002-of-00003.safetensors",
349
+ "model.layers.40.mamba.A_log": "model-00002-of-00003.safetensors",
350
+ "model.layers.40.mamba.D": "model-00002-of-00003.safetensors",
351
+ "model.layers.40.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
352
+ "model.layers.40.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
353
+ "model.layers.40.mamba.dt_bias": "model-00002-of-00003.safetensors",
354
+ "model.layers.40.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
355
+ "model.layers.40.mamba.norm.weight": "model-00002-of-00003.safetensors",
356
+ "model.layers.40.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
357
+ "model.layers.41.linear.weight": "model-00002-of-00003.safetensors",
358
+ "model.layers.41.mamba_decoder.input_layernorm.weight": "model-00002-of-00003.safetensors",
359
+ "model.layers.41.mamba_decoder.mamba.A_log": "model-00002-of-00003.safetensors",
360
+ "model.layers.41.mamba_decoder.mamba.D": "model-00002-of-00003.safetensors",
361
+ "model.layers.41.mamba_decoder.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
362
+ "model.layers.41.mamba_decoder.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
363
+ "model.layers.41.mamba_decoder.mamba.dt_bias": "model-00002-of-00003.safetensors",
364
+ "model.layers.41.mamba_decoder.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
365
+ "model.layers.41.mamba_decoder.mamba.norm.weight": "model-00002-of-00003.safetensors",
366
+ "model.layers.41.mamba_decoder.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
367
+ "model.layers.42.input_layernorm.weight": "model-00002-of-00003.safetensors",
368
+ "model.layers.42.mamba.A_log": "model-00002-of-00003.safetensors",
369
+ "model.layers.42.mamba.D": "model-00002-of-00003.safetensors",
370
+ "model.layers.42.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
371
+ "model.layers.42.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
372
+ "model.layers.42.mamba.dt_bias": "model-00002-of-00003.safetensors",
373
+ "model.layers.42.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
374
+ "model.layers.42.mamba.norm.weight": "model-00002-of-00003.safetensors",
375
+ "model.layers.42.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
376
+ "model.layers.43.input_layernorm.weight": "model-00002-of-00003.safetensors",
377
+ "model.layers.43.mamba.A_log": "model-00002-of-00003.safetensors",
378
+ "model.layers.43.mamba.D": "model-00002-of-00003.safetensors",
379
+ "model.layers.43.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
380
+ "model.layers.43.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
381
+ "model.layers.43.mamba.dt_bias": "model-00002-of-00003.safetensors",
382
+ "model.layers.43.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
383
+ "model.layers.43.mamba.norm.weight": "model-00002-of-00003.safetensors",
384
+ "model.layers.43.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
385
+ "model.layers.44.input_layernorm.weight": "model-00002-of-00003.safetensors",
386
+ "model.layers.44.mamba.A_log": "model-00002-of-00003.safetensors",
387
+ "model.layers.44.mamba.D": "model-00002-of-00003.safetensors",
388
+ "model.layers.44.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
389
+ "model.layers.44.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
390
+ "model.layers.44.mamba.dt_bias": "model-00002-of-00003.safetensors",
391
+ "model.layers.44.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
392
+ "model.layers.44.mamba.norm.weight": "model-00002-of-00003.safetensors",
393
+ "model.layers.44.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
394
+ "model.layers.45.input_layernorm.weight": "model-00002-of-00003.safetensors",
395
+ "model.layers.45.mamba.A_log": "model-00002-of-00003.safetensors",
396
+ "model.layers.45.mamba.D": "model-00002-of-00003.safetensors",
397
+ "model.layers.45.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
398
+ "model.layers.45.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
399
+ "model.layers.45.mamba.dt_bias": "model-00002-of-00003.safetensors",
400
+ "model.layers.45.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
401
+ "model.layers.45.mamba.norm.weight": "model-00002-of-00003.safetensors",
402
+ "model.layers.45.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
403
+ "model.layers.46.input_layernorm.weight": "model-00002-of-00003.safetensors",
404
+ "model.layers.46.mamba.A_log": "model-00002-of-00003.safetensors",
405
+ "model.layers.46.mamba.D": "model-00002-of-00003.safetensors",
406
+ "model.layers.46.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
407
+ "model.layers.46.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
408
+ "model.layers.46.mamba.dt_bias": "model-00002-of-00003.safetensors",
409
+ "model.layers.46.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
410
+ "model.layers.46.mamba.norm.weight": "model-00002-of-00003.safetensors",
411
+ "model.layers.46.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
412
+ "model.layers.47.linear.weight": "model-00002-of-00003.safetensors",
413
+ "model.layers.47.mamba_decoder.input_layernorm.weight": "model-00002-of-00003.safetensors",
414
+ "model.layers.47.mamba_decoder.mamba.A_log": "model-00002-of-00003.safetensors",
415
+ "model.layers.47.mamba_decoder.mamba.D": "model-00002-of-00003.safetensors",
416
+ "model.layers.47.mamba_decoder.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
417
+ "model.layers.47.mamba_decoder.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
418
+ "model.layers.47.mamba_decoder.mamba.dt_bias": "model-00002-of-00003.safetensors",
419
+ "model.layers.47.mamba_decoder.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
420
+ "model.layers.47.mamba_decoder.mamba.norm.weight": "model-00002-of-00003.safetensors",
421
+ "model.layers.47.mamba_decoder.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
422
+ "model.layers.48.input_layernorm.weight": "model-00002-of-00003.safetensors",
423
+ "model.layers.48.mamba.A_log": "model-00002-of-00003.safetensors",
424
+ "model.layers.48.mamba.D": "model-00002-of-00003.safetensors",
425
+ "model.layers.48.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
426
+ "model.layers.48.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
427
+ "model.layers.48.mamba.dt_bias": "model-00002-of-00003.safetensors",
428
+ "model.layers.48.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
429
+ "model.layers.48.mamba.norm.weight": "model-00002-of-00003.safetensors",
430
+ "model.layers.48.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
431
+ "model.layers.49.input_layernorm.weight": "model-00002-of-00003.safetensors",
432
+ "model.layers.49.mamba.A_log": "model-00002-of-00003.safetensors",
433
+ "model.layers.49.mamba.D": "model-00002-of-00003.safetensors",
434
+ "model.layers.49.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
435
+ "model.layers.49.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
436
+ "model.layers.49.mamba.dt_bias": "model-00002-of-00003.safetensors",
437
+ "model.layers.49.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
438
+ "model.layers.49.mamba.norm.weight": "model-00002-of-00003.safetensors",
439
+ "model.layers.49.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
440
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
441
+ "model.layers.5.mamba.A_log": "model-00001-of-00003.safetensors",
442
+ "model.layers.5.mamba.D": "model-00001-of-00003.safetensors",
443
+ "model.layers.5.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
444
+ "model.layers.5.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
445
+ "model.layers.5.mamba.dt_bias": "model-00001-of-00003.safetensors",
446
+ "model.layers.5.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
447
+ "model.layers.5.mamba.norm.weight": "model-00001-of-00003.safetensors",
448
+ "model.layers.5.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
449
+ "model.layers.50.input_layernorm.weight": "model-00002-of-00003.safetensors",
450
+ "model.layers.50.mamba.A_log": "model-00002-of-00003.safetensors",
451
+ "model.layers.50.mamba.D": "model-00002-of-00003.safetensors",
452
+ "model.layers.50.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
453
+ "model.layers.50.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
454
+ "model.layers.50.mamba.dt_bias": "model-00002-of-00003.safetensors",
455
+ "model.layers.50.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
456
+ "model.layers.50.mamba.norm.weight": "model-00002-of-00003.safetensors",
457
+ "model.layers.50.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
458
+ "model.layers.51.input_layernorm.weight": "model-00003-of-00003.safetensors",
459
+ "model.layers.51.mamba.A_log": "model-00002-of-00003.safetensors",
460
+ "model.layers.51.mamba.D": "model-00002-of-00003.safetensors",
461
+ "model.layers.51.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
462
+ "model.layers.51.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
463
+ "model.layers.51.mamba.dt_bias": "model-00002-of-00003.safetensors",
464
+ "model.layers.51.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
465
+ "model.layers.51.mamba.norm.weight": "model-00002-of-00003.safetensors",
466
+ "model.layers.51.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
467
+ "model.layers.52.input_layernorm.weight": "model-00003-of-00003.safetensors",
468
+ "model.layers.52.mamba.A_log": "model-00003-of-00003.safetensors",
469
+ "model.layers.52.mamba.D": "model-00003-of-00003.safetensors",
470
+ "model.layers.52.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
471
+ "model.layers.52.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
472
+ "model.layers.52.mamba.dt_bias": "model-00003-of-00003.safetensors",
473
+ "model.layers.52.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
474
+ "model.layers.52.mamba.norm.weight": "model-00003-of-00003.safetensors",
475
+ "model.layers.52.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
476
+ "model.layers.53.linear.weight": "model-00003-of-00003.safetensors",
477
+ "model.layers.53.mamba_decoder.input_layernorm.weight": "model-00003-of-00003.safetensors",
478
+ "model.layers.53.mamba_decoder.mamba.A_log": "model-00003-of-00003.safetensors",
479
+ "model.layers.53.mamba_decoder.mamba.D": "model-00003-of-00003.safetensors",
480
+ "model.layers.53.mamba_decoder.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
481
+ "model.layers.53.mamba_decoder.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
482
+ "model.layers.53.mamba_decoder.mamba.dt_bias": "model-00003-of-00003.safetensors",
483
+ "model.layers.53.mamba_decoder.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
484
+ "model.layers.53.mamba_decoder.mamba.norm.weight": "model-00003-of-00003.safetensors",
485
+ "model.layers.53.mamba_decoder.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
486
+ "model.layers.54.input_layernorm.weight": "model-00003-of-00003.safetensors",
487
+ "model.layers.54.mamba.A_log": "model-00003-of-00003.safetensors",
488
+ "model.layers.54.mamba.D": "model-00003-of-00003.safetensors",
489
+ "model.layers.54.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
490
+ "model.layers.54.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
491
+ "model.layers.54.mamba.dt_bias": "model-00003-of-00003.safetensors",
492
+ "model.layers.54.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
493
+ "model.layers.54.mamba.norm.weight": "model-00003-of-00003.safetensors",
494
+ "model.layers.54.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
495
+ "model.layers.55.input_layernorm.weight": "model-00003-of-00003.safetensors",
496
+ "model.layers.55.mamba.A_log": "model-00003-of-00003.safetensors",
497
+ "model.layers.55.mamba.D": "model-00003-of-00003.safetensors",
498
+ "model.layers.55.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
499
+ "model.layers.55.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
500
+ "model.layers.55.mamba.dt_bias": "model-00003-of-00003.safetensors",
501
+ "model.layers.55.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
502
+ "model.layers.55.mamba.norm.weight": "model-00003-of-00003.safetensors",
503
+ "model.layers.55.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
504
+ "model.layers.56.input_layernorm.weight": "model-00003-of-00003.safetensors",
505
+ "model.layers.56.mamba.A_log": "model-00003-of-00003.safetensors",
506
+ "model.layers.56.mamba.D": "model-00003-of-00003.safetensors",
507
+ "model.layers.56.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
508
+ "model.layers.56.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
509
+ "model.layers.56.mamba.dt_bias": "model-00003-of-00003.safetensors",
510
+ "model.layers.56.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
511
+ "model.layers.56.mamba.norm.weight": "model-00003-of-00003.safetensors",
512
+ "model.layers.56.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
513
+ "model.layers.57.input_layernorm.weight": "model-00003-of-00003.safetensors",
514
+ "model.layers.57.mamba.A_log": "model-00003-of-00003.safetensors",
515
+ "model.layers.57.mamba.D": "model-00003-of-00003.safetensors",
516
+ "model.layers.57.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
517
+ "model.layers.57.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
518
+ "model.layers.57.mamba.dt_bias": "model-00003-of-00003.safetensors",
519
+ "model.layers.57.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
520
+ "model.layers.57.mamba.norm.weight": "model-00003-of-00003.safetensors",
521
+ "model.layers.57.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
522
+ "model.layers.58.input_layernorm.weight": "model-00003-of-00003.safetensors",
523
+ "model.layers.58.mamba.A_log": "model-00003-of-00003.safetensors",
524
+ "model.layers.58.mamba.D": "model-00003-of-00003.safetensors",
525
+ "model.layers.58.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
526
+ "model.layers.58.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
527
+ "model.layers.58.mamba.dt_bias": "model-00003-of-00003.safetensors",
528
+ "model.layers.58.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
529
+ "model.layers.58.mamba.norm.weight": "model-00003-of-00003.safetensors",
530
+ "model.layers.58.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
531
+ "model.layers.59.linear.weight": "model-00003-of-00003.safetensors",
532
+ "model.layers.59.mamba_decoder.input_layernorm.weight": "model-00003-of-00003.safetensors",
533
+ "model.layers.59.mamba_decoder.mamba.A_log": "model-00003-of-00003.safetensors",
534
+ "model.layers.59.mamba_decoder.mamba.D": "model-00003-of-00003.safetensors",
535
+ "model.layers.59.mamba_decoder.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
536
+ "model.layers.59.mamba_decoder.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
537
+ "model.layers.59.mamba_decoder.mamba.dt_bias": "model-00003-of-00003.safetensors",
538
+ "model.layers.59.mamba_decoder.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
539
+ "model.layers.59.mamba_decoder.mamba.norm.weight": "model-00003-of-00003.safetensors",
540
+ "model.layers.59.mamba_decoder.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
541
+ "model.layers.6.linear.weight": "model-00001-of-00003.safetensors",
542
+ "model.layers.6.mamba_decoder.input_layernorm.weight": "model-00001-of-00003.safetensors",
543
+ "model.layers.6.mamba_decoder.mamba.A_log": "model-00001-of-00003.safetensors",
544
+ "model.layers.6.mamba_decoder.mamba.D": "model-00001-of-00003.safetensors",
545
+ "model.layers.6.mamba_decoder.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
546
+ "model.layers.6.mamba_decoder.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
547
+ "model.layers.6.mamba_decoder.mamba.dt_bias": "model-00001-of-00003.safetensors",
548
+ "model.layers.6.mamba_decoder.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
549
+ "model.layers.6.mamba_decoder.mamba.norm.weight": "model-00001-of-00003.safetensors",
550
+ "model.layers.6.mamba_decoder.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
551
+ "model.layers.6.shared_transformer.feed_forward.down_proj.weight": "model-00001-of-00003.safetensors",
552
+ "model.layers.6.shared_transformer.feed_forward.gate_up_proj.weight": "model-00001-of-00003.safetensors",
553
+ "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.0.0.weight": "model-00001-of-00003.safetensors",
554
+ "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.0.1.weight": "model-00001-of-00003.safetensors",
555
+ "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.10.0.weight": "model-00001-of-00003.safetensors",
556
+ "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.10.1.weight": "model-00001-of-00003.safetensors",
557
+ "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.12.0.weight": "model-00001-of-00003.safetensors",
558
+ "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.12.1.weight": "model-00001-of-00003.safetensors",
559
+ "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.2.0.weight": "model-00001-of-00003.safetensors",
560
+ "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.2.1.weight": "model-00001-of-00003.safetensors",
561
+ "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.4.0.weight": "model-00001-of-00003.safetensors",
562
+ "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.4.1.weight": "model-00001-of-00003.safetensors",
563
+ "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.6.0.weight": "model-00001-of-00003.safetensors",
564
+ "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.6.1.weight": "model-00001-of-00003.safetensors",
565
+ "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.8.0.weight": "model-00001-of-00003.safetensors",
566
+ "model.layers.6.shared_transformer.feed_forward.gate_up_proj_adapter_list.8.1.weight": "model-00001-of-00003.safetensors",
567
+ "model.layers.6.shared_transformer.input_layernorm.weight": "model-00001-of-00003.safetensors",
568
+ "model.layers.6.shared_transformer.pre_ff_layernorm.weight": "model-00001-of-00003.safetensors",
569
+ "model.layers.6.shared_transformer.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
570
+ "model.layers.6.shared_transformer.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
571
+ "model.layers.6.shared_transformer.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
572
+ "model.layers.6.shared_transformer.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
573
+ "model.layers.60.input_layernorm.weight": "model-00003-of-00003.safetensors",
574
+ "model.layers.60.mamba.A_log": "model-00003-of-00003.safetensors",
575
+ "model.layers.60.mamba.D": "model-00003-of-00003.safetensors",
576
+ "model.layers.60.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
577
+ "model.layers.60.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
578
+ "model.layers.60.mamba.dt_bias": "model-00003-of-00003.safetensors",
579
+ "model.layers.60.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
580
+ "model.layers.60.mamba.norm.weight": "model-00003-of-00003.safetensors",
581
+ "model.layers.60.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
582
+ "model.layers.61.input_layernorm.weight": "model-00003-of-00003.safetensors",
583
+ "model.layers.61.mamba.A_log": "model-00003-of-00003.safetensors",
584
+ "model.layers.61.mamba.D": "model-00003-of-00003.safetensors",
585
+ "model.layers.61.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
586
+ "model.layers.61.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
587
+ "model.layers.61.mamba.dt_bias": "model-00003-of-00003.safetensors",
588
+ "model.layers.61.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
589
+ "model.layers.61.mamba.norm.weight": "model-00003-of-00003.safetensors",
590
+ "model.layers.61.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
591
+ "model.layers.62.input_layernorm.weight": "model-00003-of-00003.safetensors",
592
+ "model.layers.62.mamba.A_log": "model-00003-of-00003.safetensors",
593
+ "model.layers.62.mamba.D": "model-00003-of-00003.safetensors",
594
+ "model.layers.62.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
595
+ "model.layers.62.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
596
+ "model.layers.62.mamba.dt_bias": "model-00003-of-00003.safetensors",
597
+ "model.layers.62.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
598
+ "model.layers.62.mamba.norm.weight": "model-00003-of-00003.safetensors",
599
+ "model.layers.62.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
600
+ "model.layers.63.input_layernorm.weight": "model-00003-of-00003.safetensors",
601
+ "model.layers.63.mamba.A_log": "model-00003-of-00003.safetensors",
602
+ "model.layers.63.mamba.D": "model-00003-of-00003.safetensors",
603
+ "model.layers.63.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
604
+ "model.layers.63.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
605
+ "model.layers.63.mamba.dt_bias": "model-00003-of-00003.safetensors",
606
+ "model.layers.63.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
607
+ "model.layers.63.mamba.norm.weight": "model-00003-of-00003.safetensors",
608
+ "model.layers.63.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
609
+ "model.layers.64.input_layernorm.weight": "model-00003-of-00003.safetensors",
610
+ "model.layers.64.mamba.A_log": "model-00003-of-00003.safetensors",
611
+ "model.layers.64.mamba.D": "model-00003-of-00003.safetensors",
612
+ "model.layers.64.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
613
+ "model.layers.64.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
614
+ "model.layers.64.mamba.dt_bias": "model-00003-of-00003.safetensors",
615
+ "model.layers.64.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
616
+ "model.layers.64.mamba.norm.weight": "model-00003-of-00003.safetensors",
617
+ "model.layers.64.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
618
+ "model.layers.65.linear.weight": "model-00003-of-00003.safetensors",
619
+ "model.layers.65.mamba_decoder.input_layernorm.weight": "model-00003-of-00003.safetensors",
620
+ "model.layers.65.mamba_decoder.mamba.A_log": "model-00003-of-00003.safetensors",
621
+ "model.layers.65.mamba_decoder.mamba.D": "model-00003-of-00003.safetensors",
622
+ "model.layers.65.mamba_decoder.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
623
+ "model.layers.65.mamba_decoder.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
624
+ "model.layers.65.mamba_decoder.mamba.dt_bias": "model-00003-of-00003.safetensors",
625
+ "model.layers.65.mamba_decoder.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
626
+ "model.layers.65.mamba_decoder.mamba.norm.weight": "model-00003-of-00003.safetensors",
627
+ "model.layers.65.mamba_decoder.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
628
+ "model.layers.66.input_layernorm.weight": "model-00003-of-00003.safetensors",
629
+ "model.layers.66.mamba.A_log": "model-00003-of-00003.safetensors",
630
+ "model.layers.66.mamba.D": "model-00003-of-00003.safetensors",
631
+ "model.layers.66.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
632
+ "model.layers.66.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
633
+ "model.layers.66.mamba.dt_bias": "model-00003-of-00003.safetensors",
634
+ "model.layers.66.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
635
+ "model.layers.66.mamba.norm.weight": "model-00003-of-00003.safetensors",
636
+ "model.layers.66.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
637
+ "model.layers.67.input_layernorm.weight": "model-00003-of-00003.safetensors",
638
+ "model.layers.67.mamba.A_log": "model-00003-of-00003.safetensors",
639
+ "model.layers.67.mamba.D": "model-00003-of-00003.safetensors",
640
+ "model.layers.67.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
641
+ "model.layers.67.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
642
+ "model.layers.67.mamba.dt_bias": "model-00003-of-00003.safetensors",
643
+ "model.layers.67.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
644
+ "model.layers.67.mamba.norm.weight": "model-00003-of-00003.safetensors",
645
+ "model.layers.67.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
646
+ "model.layers.68.input_layernorm.weight": "model-00003-of-00003.safetensors",
647
+ "model.layers.68.mamba.A_log": "model-00003-of-00003.safetensors",
648
+ "model.layers.68.mamba.D": "model-00003-of-00003.safetensors",
649
+ "model.layers.68.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
650
+ "model.layers.68.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
651
+ "model.layers.68.mamba.dt_bias": "model-00003-of-00003.safetensors",
652
+ "model.layers.68.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
653
+ "model.layers.68.mamba.norm.weight": "model-00003-of-00003.safetensors",
654
+ "model.layers.68.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
655
+ "model.layers.69.input_layernorm.weight": "model-00003-of-00003.safetensors",
656
+ "model.layers.69.mamba.A_log": "model-00003-of-00003.safetensors",
657
+ "model.layers.69.mamba.D": "model-00003-of-00003.safetensors",
658
+ "model.layers.69.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
659
+ "model.layers.69.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
660
+ "model.layers.69.mamba.dt_bias": "model-00003-of-00003.safetensors",
661
+ "model.layers.69.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
662
+ "model.layers.69.mamba.norm.weight": "model-00003-of-00003.safetensors",
663
+ "model.layers.69.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
664
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
665
+ "model.layers.7.mamba.A_log": "model-00001-of-00003.safetensors",
666
+ "model.layers.7.mamba.D": "model-00001-of-00003.safetensors",
667
+ "model.layers.7.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
668
+ "model.layers.7.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
669
+ "model.layers.7.mamba.dt_bias": "model-00001-of-00003.safetensors",
670
+ "model.layers.7.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
671
+ "model.layers.7.mamba.norm.weight": "model-00001-of-00003.safetensors",
672
+ "model.layers.7.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
673
+ "model.layers.70.input_layernorm.weight": "model-00003-of-00003.safetensors",
674
+ "model.layers.70.mamba.A_log": "model-00003-of-00003.safetensors",
675
+ "model.layers.70.mamba.D": "model-00003-of-00003.safetensors",
676
+ "model.layers.70.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
677
+ "model.layers.70.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
678
+ "model.layers.70.mamba.dt_bias": "model-00003-of-00003.safetensors",
679
+ "model.layers.70.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
680
+ "model.layers.70.mamba.norm.weight": "model-00003-of-00003.safetensors",
681
+ "model.layers.70.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
682
+ "model.layers.71.linear.weight": "model-00003-of-00003.safetensors",
683
+ "model.layers.71.mamba_decoder.input_layernorm.weight": "model-00003-of-00003.safetensors",
684
+ "model.layers.71.mamba_decoder.mamba.A_log": "model-00003-of-00003.safetensors",
685
+ "model.layers.71.mamba_decoder.mamba.D": "model-00003-of-00003.safetensors",
686
+ "model.layers.71.mamba_decoder.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
687
+ "model.layers.71.mamba_decoder.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
688
+ "model.layers.71.mamba_decoder.mamba.dt_bias": "model-00003-of-00003.safetensors",
689
+ "model.layers.71.mamba_decoder.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
690
+ "model.layers.71.mamba_decoder.mamba.norm.weight": "model-00003-of-00003.safetensors",
691
+ "model.layers.71.mamba_decoder.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
692
+ "model.layers.72.input_layernorm.weight": "model-00003-of-00003.safetensors",
693
+ "model.layers.72.mamba.A_log": "model-00003-of-00003.safetensors",
694
+ "model.layers.72.mamba.D": "model-00003-of-00003.safetensors",
695
+ "model.layers.72.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
696
+ "model.layers.72.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
697
+ "model.layers.72.mamba.dt_bias": "model-00003-of-00003.safetensors",
698
+ "model.layers.72.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
699
+ "model.layers.72.mamba.norm.weight": "model-00003-of-00003.safetensors",
700
+ "model.layers.72.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
701
+ "model.layers.73.input_layernorm.weight": "model-00003-of-00003.safetensors",
702
+ "model.layers.73.mamba.A_log": "model-00003-of-00003.safetensors",
703
+ "model.layers.73.mamba.D": "model-00003-of-00003.safetensors",
704
+ "model.layers.73.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
705
+ "model.layers.73.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
706
+ "model.layers.73.mamba.dt_bias": "model-00003-of-00003.safetensors",
707
+ "model.layers.73.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
708
+ "model.layers.73.mamba.norm.weight": "model-00003-of-00003.safetensors",
709
+ "model.layers.73.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
710
+ "model.layers.74.input_layernorm.weight": "model-00003-of-00003.safetensors",
711
+ "model.layers.74.mamba.A_log": "model-00003-of-00003.safetensors",
712
+ "model.layers.74.mamba.D": "model-00003-of-00003.safetensors",
713
+ "model.layers.74.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
714
+ "model.layers.74.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
715
+ "model.layers.74.mamba.dt_bias": "model-00003-of-00003.safetensors",
716
+ "model.layers.74.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
717
+ "model.layers.74.mamba.norm.weight": "model-00003-of-00003.safetensors",
718
+ "model.layers.74.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
719
+ "model.layers.75.input_layernorm.weight": "model-00003-of-00003.safetensors",
720
+ "model.layers.75.mamba.A_log": "model-00003-of-00003.safetensors",
721
+ "model.layers.75.mamba.D": "model-00003-of-00003.safetensors",
722
+ "model.layers.75.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
723
+ "model.layers.75.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
724
+ "model.layers.75.mamba.dt_bias": "model-00003-of-00003.safetensors",
725
+ "model.layers.75.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
726
+ "model.layers.75.mamba.norm.weight": "model-00003-of-00003.safetensors",
727
+ "model.layers.75.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
728
+ "model.layers.76.input_layernorm.weight": "model-00003-of-00003.safetensors",
729
+ "model.layers.76.mamba.A_log": "model-00003-of-00003.safetensors",
730
+ "model.layers.76.mamba.D": "model-00003-of-00003.safetensors",
731
+ "model.layers.76.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
732
+ "model.layers.76.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
733
+ "model.layers.76.mamba.dt_bias": "model-00003-of-00003.safetensors",
734
+ "model.layers.76.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
735
+ "model.layers.76.mamba.norm.weight": "model-00003-of-00003.safetensors",
736
+ "model.layers.76.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
737
+ "model.layers.77.linear.weight": "model-00003-of-00003.safetensors",
738
+ "model.layers.77.mamba_decoder.input_layernorm.weight": "model-00003-of-00003.safetensors",
739
+ "model.layers.77.mamba_decoder.mamba.A_log": "model-00003-of-00003.safetensors",
740
+ "model.layers.77.mamba_decoder.mamba.D": "model-00003-of-00003.safetensors",
741
+ "model.layers.77.mamba_decoder.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
742
+ "model.layers.77.mamba_decoder.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
743
+ "model.layers.77.mamba_decoder.mamba.dt_bias": "model-00003-of-00003.safetensors",
744
+ "model.layers.77.mamba_decoder.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
745
+ "model.layers.77.mamba_decoder.mamba.norm.weight": "model-00003-of-00003.safetensors",
746
+ "model.layers.77.mamba_decoder.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
747
+ "model.layers.78.input_layernorm.weight": "model-00003-of-00003.safetensors",
748
+ "model.layers.78.mamba.A_log": "model-00003-of-00003.safetensors",
749
+ "model.layers.78.mamba.D": "model-00003-of-00003.safetensors",
750
+ "model.layers.78.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
751
+ "model.layers.78.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
752
+ "model.layers.78.mamba.dt_bias": "model-00003-of-00003.safetensors",
753
+ "model.layers.78.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
754
+ "model.layers.78.mamba.norm.weight": "model-00003-of-00003.safetensors",
755
+ "model.layers.78.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
756
+ "model.layers.79.input_layernorm.weight": "model-00003-of-00003.safetensors",
757
+ "model.layers.79.mamba.A_log": "model-00003-of-00003.safetensors",
758
+ "model.layers.79.mamba.D": "model-00003-of-00003.safetensors",
759
+ "model.layers.79.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
760
+ "model.layers.79.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
761
+ "model.layers.79.mamba.dt_bias": "model-00003-of-00003.safetensors",
762
+ "model.layers.79.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
763
+ "model.layers.79.mamba.norm.weight": "model-00003-of-00003.safetensors",
764
+ "model.layers.79.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
765
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
766
+ "model.layers.8.mamba.A_log": "model-00001-of-00003.safetensors",
767
+ "model.layers.8.mamba.D": "model-00001-of-00003.safetensors",
768
+ "model.layers.8.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
769
+ "model.layers.8.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
770
+ "model.layers.8.mamba.dt_bias": "model-00001-of-00003.safetensors",
771
+ "model.layers.8.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
772
+ "model.layers.8.mamba.norm.weight": "model-00001-of-00003.safetensors",
773
+ "model.layers.8.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
774
+ "model.layers.80.input_layernorm.weight": "model-00003-of-00003.safetensors",
775
+ "model.layers.80.mamba.A_log": "model-00003-of-00003.safetensors",
776
+ "model.layers.80.mamba.D": "model-00003-of-00003.safetensors",
777
+ "model.layers.80.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
778
+ "model.layers.80.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
779
+ "model.layers.80.mamba.dt_bias": "model-00003-of-00003.safetensors",
780
+ "model.layers.80.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
781
+ "model.layers.80.mamba.norm.weight": "model-00003-of-00003.safetensors",
782
+ "model.layers.80.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
783
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
784
+ "model.layers.9.mamba.A_log": "model-00001-of-00003.safetensors",
785
+ "model.layers.9.mamba.D": "model-00001-of-00003.safetensors",
786
+ "model.layers.9.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
787
+ "model.layers.9.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
788
+ "model.layers.9.mamba.dt_bias": "model-00001-of-00003.safetensors",
789
+ "model.layers.9.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
790
+ "model.layers.9.mamba.norm.weight": "model-00001-of-00003.safetensors",
791
+ "model.layers.9.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
792
+ "model.rotary_emb.inv_freq": "model-00003-of-00003.safetensors"
793
+ }
794
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<s>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "</s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "[PAD]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "32000": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|im_start|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|im_end|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ }
54
+ },
55
+ "additional_special_tokens": [
56
+ "<|im_start|>",
57
+ "<|im_end|>"
58
+ ],
59
+ "bos_token": "<s>",
60
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
61
+ "clean_up_tokenization_spaces": false,
62
+ "eos_token": "</s>",
63
+ "extra_special_tokens": {},
64
+ "legacy": true,
65
+ "model_max_length": 4096,
66
+ "pad_token": "[PAD]",
67
+ "sp_model_kwargs": {},
68
+ "spaces_between_special_tokens": false,
69
+ "tokenizer_class": "LlamaTokenizerFast",
70
+ "unk_token": "<unk>",
71
+ "use_default_system_prompt": false
72
+ }