Hugging Face's logo

thrunlab
/
cats_exp

Text Generation
Transformers
Safetensors
cats_model
custom_code
Model card Files Community
vxbrandon commited on
Commit
2d850d9
•
1 Parent(s): f0daaee

Upload model

Browse files
Files changed (8) hide show
  1. config.json +27 -0
  2. model-00001-of-00006.safetensors +3 -0
  3. model-00002-of-00006.safetensors +3 -0
  4. model-00003-of-00006.safetensors +3 -0
  5. model-00004-of-00006.safetensors +3 -0
  6. model-00005-of-00006.safetensors +3 -0
  7. model-00006-of-00006.safetensors +3 -0
  8. model.safetensors.index.json +329 -0
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "CatsModel"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "hidden_act": "silu",
7
+ "hidden_size": 4096,
8
+ "initializer_range": 0.02,
9
+ "intermediate_size": 14336,
10
+ "max_position_embeddings": 32768,
11
+ "model_type": "cats_model",
12
+ "num_attention_heads": 32,
13
+ "num_hidden_layers": 32,
14
+ "num_key_value_heads": 8,
15
+ "rms_norm_eps": 1e-05,
16
+ "rope_theta": 10000.0,
17
+ "sliding_window": 4096,
18
+ "target_modules": [
19
+ "act_fn"
20
+ ],
21
+ "target_sparsity": 0.5,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.36.2",
24
+ "use_cache": true,
25
+ "vocab_size": 32000,
26
+ "wrapped_model_class_name": "MistralForCausalLM"
27
+ }
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:044c421332ba646b63a13010bc95f811ad5a404938aaa994cd9ac0ac8157ba3f
3
+ size 4987198176
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd2405841fa4e94e4c310666958a12d6a177e2b77e63ce6c0e22b9b6bb94859a
3
+ size 4899117664
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:521321be08b44e5771763a36ab725bc5e789ccae288161328230ba859d4a62e6
3
+ size 4999814528
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68fea5d81c21bedda77fb786b3bec7f40cf5a4b8126c6172f4e569e9f25c0e49
3
+ size 4999814528
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a8ea0de0ca168ce00d81a0f5117c12211af21d2945ef9607d5b3b8ef597ad8c
3
+ size 4832008712
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bd7d95c6a7a9a8e65e97b1a2586294625e657f46fa08698eda2ef67bd0889b6
3
+ size 3724727904
model.safetensors.index.json ADDED
@@ -0,0 +1,329 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 28442640640
4
+ },
5
+ "weight_map": {
6
+ "wrapped_model.model.embed_tokens.weight": "model-00001-of-00006.safetensors",
7
+ "wrapped_model.model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
8
+ "wrapped_model.model.layers.0.mlp.act_fn.threshold": "model-00001-of-00006.safetensors",
9
+ "wrapped_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
10
+ "wrapped_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
11
+ "wrapped_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
12
+ "wrapped_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
13
+ "wrapped_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
14
+ "wrapped_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
15
+ "wrapped_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
16
+ "wrapped_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
17
+ "wrapped_model.model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
18
+ "wrapped_model.model.layers.1.mlp.act_fn.threshold": "model-00001-of-00006.safetensors",
19
+ "wrapped_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
20
+ "wrapped_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
21
+ "wrapped_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
22
+ "wrapped_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
23
+ "wrapped_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
24
+ "wrapped_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
25
+ "wrapped_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
26
+ "wrapped_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
27
+ "wrapped_model.model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
28
+ "wrapped_model.model.layers.10.mlp.act_fn.threshold": "model-00003-of-00006.safetensors",
29
+ "wrapped_model.model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
30
+ "wrapped_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
31
+ "wrapped_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
32
+ "wrapped_model.model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
33
+ "wrapped_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
34
+ "wrapped_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
35
+ "wrapped_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
36
+ "wrapped_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
37
+ "wrapped_model.model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
38
+ "wrapped_model.model.layers.11.mlp.act_fn.threshold": "model-00003-of-00006.safetensors",
39
+ "wrapped_model.model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
40
+ "wrapped_model.model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
41
+ "wrapped_model.model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
42
+ "wrapped_model.model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
43
+ "wrapped_model.model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
44
+ "wrapped_model.model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
45
+ "wrapped_model.model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
46
+ "wrapped_model.model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
47
+ "wrapped_model.model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
48
+ "wrapped_model.model.layers.12.mlp.act_fn.threshold": "model-00003-of-00006.safetensors",
49
+ "wrapped_model.model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
50
+ "wrapped_model.model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
51
+ "wrapped_model.model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
52
+ "wrapped_model.model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
53
+ "wrapped_model.model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
54
+ "wrapped_model.model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
55
+ "wrapped_model.model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
56
+ "wrapped_model.model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
57
+ "wrapped_model.model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
58
+ "wrapped_model.model.layers.13.mlp.act_fn.threshold": "model-00003-of-00006.safetensors",
59
+ "wrapped_model.model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
60
+ "wrapped_model.model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
61
+ "wrapped_model.model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
62
+ "wrapped_model.model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
63
+ "wrapped_model.model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
64
+ "wrapped_model.model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
65
+ "wrapped_model.model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
66
+ "wrapped_model.model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
67
+ "wrapped_model.model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
68
+ "wrapped_model.model.layers.14.mlp.act_fn.threshold": "model-00003-of-00006.safetensors",
69
+ "wrapped_model.model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
70
+ "wrapped_model.model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
71
+ "wrapped_model.model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
72
+ "wrapped_model.model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
73
+ "wrapped_model.model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
74
+ "wrapped_model.model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
75
+ "wrapped_model.model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
76
+ "wrapped_model.model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
77
+ "wrapped_model.model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
78
+ "wrapped_model.model.layers.15.mlp.act_fn.threshold": "model-00003-of-00006.safetensors",
79
+ "wrapped_model.model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
80
+ "wrapped_model.model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
81
+ "wrapped_model.model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
82
+ "wrapped_model.model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
83
+ "wrapped_model.model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
84
+ "wrapped_model.model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
85
+ "wrapped_model.model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
86
+ "wrapped_model.model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
87
+ "wrapped_model.model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
88
+ "wrapped_model.model.layers.16.mlp.act_fn.threshold": "model-00004-of-00006.safetensors",
89
+ "wrapped_model.model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
90
+ "wrapped_model.model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
91
+ "wrapped_model.model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
92
+ "wrapped_model.model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
93
+ "wrapped_model.model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
94
+ "wrapped_model.model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
95
+ "wrapped_model.model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
96
+ "wrapped_model.model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
97
+ "wrapped_model.model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
98
+ "wrapped_model.model.layers.17.mlp.act_fn.threshold": "model-00004-of-00006.safetensors",
99
+ "wrapped_model.model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
100
+ "wrapped_model.model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
101
+ "wrapped_model.model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
102
+ "wrapped_model.model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
103
+ "wrapped_model.model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
104
+ "wrapped_model.model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
105
+ "wrapped_model.model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
106
+ "wrapped_model.model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
107
+ "wrapped_model.model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
108
+ "wrapped_model.model.layers.18.mlp.act_fn.threshold": "model-00004-of-00006.safetensors",
109
+ "wrapped_model.model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
110
+ "wrapped_model.model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
111
+ "wrapped_model.model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
112
+ "wrapped_model.model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
113
+ "wrapped_model.model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
114
+ "wrapped_model.model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
115
+ "wrapped_model.model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
116
+ "wrapped_model.model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
117
+ "wrapped_model.model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
118
+ "wrapped_model.model.layers.19.mlp.act_fn.threshold": "model-00004-of-00006.safetensors",
119
+ "wrapped_model.model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
120
+ "wrapped_model.model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
121
+ "wrapped_model.model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
122
+ "wrapped_model.model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
123
+ "wrapped_model.model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
124
+ "wrapped_model.model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
125
+ "wrapped_model.model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
126
+ "wrapped_model.model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
127
+ "wrapped_model.model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
128
+ "wrapped_model.model.layers.2.mlp.act_fn.threshold": "model-00001-of-00006.safetensors",
129
+ "wrapped_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
130
+ "wrapped_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
131
+ "wrapped_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
132
+ "wrapped_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
133
+ "wrapped_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
134
+ "wrapped_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
135
+ "wrapped_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
136
+ "wrapped_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
137
+ "wrapped_model.model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
138
+ "wrapped_model.model.layers.20.mlp.act_fn.threshold": "model-00004-of-00006.safetensors",
139
+ "wrapped_model.model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
140
+ "wrapped_model.model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
141
+ "wrapped_model.model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
142
+ "wrapped_model.model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
143
+ "wrapped_model.model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
144
+ "wrapped_model.model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
145
+ "wrapped_model.model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
146
+ "wrapped_model.model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
147
+ "wrapped_model.model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
148
+ "wrapped_model.model.layers.21.mlp.act_fn.threshold": "model-00004-of-00006.safetensors",
149
+ "wrapped_model.model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
150
+ "wrapped_model.model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
151
+ "wrapped_model.model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
152
+ "wrapped_model.model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
153
+ "wrapped_model.model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
154
+ "wrapped_model.model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
155
+ "wrapped_model.model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
156
+ "wrapped_model.model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
157
+ "wrapped_model.model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
158
+ "wrapped_model.model.layers.22.mlp.act_fn.threshold": "model-00005-of-00006.safetensors",
159
+ "wrapped_model.model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
160
+ "wrapped_model.model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
161
+ "wrapped_model.model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
162
+ "wrapped_model.model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
163
+ "wrapped_model.model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
164
+ "wrapped_model.model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
165
+ "wrapped_model.model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
166
+ "wrapped_model.model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
167
+ "wrapped_model.model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
168
+ "wrapped_model.model.layers.23.mlp.act_fn.threshold": "model-00005-of-00006.safetensors",
169
+ "wrapped_model.model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
170
+ "wrapped_model.model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
171
+ "wrapped_model.model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
172
+ "wrapped_model.model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
173
+ "wrapped_model.model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
174
+ "wrapped_model.model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
175
+ "wrapped_model.model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
176
+ "wrapped_model.model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
177
+ "wrapped_model.model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
178
+ "wrapped_model.model.layers.24.mlp.act_fn.threshold": "model-00005-of-00006.safetensors",
179
+ "wrapped_model.model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
180
+ "wrapped_model.model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
181
+ "wrapped_model.model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
182
+ "wrapped_model.model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
183
+ "wrapped_model.model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
184
+ "wrapped_model.model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
185
+ "wrapped_model.model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
186
+ "wrapped_model.model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
187
+ "wrapped_model.model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
188
+ "wrapped_model.model.layers.25.mlp.act_fn.threshold": "model-00005-of-00006.safetensors",
189
+ "wrapped_model.model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
190
+ "wrapped_model.model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
191
+ "wrapped_model.model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
192
+ "wrapped_model.model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
193
+ "wrapped_model.model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
194
+ "wrapped_model.model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
195
+ "wrapped_model.model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
196
+ "wrapped_model.model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
197
+ "wrapped_model.model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
198
+ "wrapped_model.model.layers.26.mlp.act_fn.threshold": "model-00005-of-00006.safetensors",
199
+ "wrapped_model.model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
200
+ "wrapped_model.model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
201
+ "wrapped_model.model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
202
+ "wrapped_model.model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
203
+ "wrapped_model.model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
204
+ "wrapped_model.model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
205
+ "wrapped_model.model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
206
+ "wrapped_model.model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
207
+ "wrapped_model.model.layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
208
+ "wrapped_model.model.layers.27.mlp.act_fn.threshold": "model-00006-of-00006.safetensors",
209
+ "wrapped_model.model.layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
210
+ "wrapped_model.model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
211
+ "wrapped_model.model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
212
+ "wrapped_model.model.layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
213
+ "wrapped_model.model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
214
+ "wrapped_model.model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
215
+ "wrapped_model.model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
216
+ "wrapped_model.model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
217
+ "wrapped_model.model.layers.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
218
+ "wrapped_model.model.layers.28.mlp.act_fn.threshold": "model-00006-of-00006.safetensors",
219
+ "wrapped_model.model.layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
220
+ "wrapped_model.model.layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
221
+ "wrapped_model.model.layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
222
+ "wrapped_model.model.layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
223
+ "wrapped_model.model.layers.28.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
224
+ "wrapped_model.model.layers.28.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
225
+ "wrapped_model.model.layers.28.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
226
+ "wrapped_model.model.layers.28.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
227
+ "wrapped_model.model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
228
+ "wrapped_model.model.layers.29.mlp.act_fn.threshold": "model-00006-of-00006.safetensors",
229
+ "wrapped_model.model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
230
+ "wrapped_model.model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
231
+ "wrapped_model.model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
232
+ "wrapped_model.model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
233
+ "wrapped_model.model.layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
234
+ "wrapped_model.model.layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
235
+ "wrapped_model.model.layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
236
+ "wrapped_model.model.layers.29.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
237
+ "wrapped_model.model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
238
+ "wrapped_model.model.layers.3.mlp.act_fn.threshold": "model-00001-of-00006.safetensors",
239
+ "wrapped_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
240
+ "wrapped_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
241
+ "wrapped_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
242
+ "wrapped_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
243
+ "wrapped_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
244
+ "wrapped_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
245
+ "wrapped_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
246
+ "wrapped_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
247
+ "wrapped_model.model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
248
+ "wrapped_model.model.layers.30.mlp.act_fn.threshold": "model-00006-of-00006.safetensors",
249
+ "wrapped_model.model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
250
+ "wrapped_model.model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
251
+ "wrapped_model.model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
252
+ "wrapped_model.model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
253
+ "wrapped_model.model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
254
+ "wrapped_model.model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
255
+ "wrapped_model.model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
256
+ "wrapped_model.model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
257
+ "wrapped_model.model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
258
+ "wrapped_model.model.layers.31.mlp.act_fn.threshold": "model-00006-of-00006.safetensors",
259
+ "wrapped_model.model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
260
+ "wrapped_model.model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
261
+ "wrapped_model.model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
262
+ "wrapped_model.model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
263
+ "wrapped_model.model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
264
+ "wrapped_model.model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
265
+ "wrapped_model.model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
266
+ "wrapped_model.model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
267
+ "wrapped_model.model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
268
+ "wrapped_model.model.layers.4.mlp.act_fn.threshold": "model-00001-of-00006.safetensors",
269
+ "wrapped_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
270
+ "wrapped_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
271
+ "wrapped_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
272
+ "wrapped_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
273
+ "wrapped_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
274
+ "wrapped_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
275
+ "wrapped_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
276
+ "wrapped_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
277
+ "wrapped_model.model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
278
+ "wrapped_model.model.layers.5.mlp.act_fn.threshold": "model-00002-of-00006.safetensors",
279
+ "wrapped_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
280
+ "wrapped_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
281
+ "wrapped_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
282
+ "wrapped_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
283
+ "wrapped_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
284
+ "wrapped_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
285
+ "wrapped_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
286
+ "wrapped_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
287
+ "wrapped_model.model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
288
+ "wrapped_model.model.layers.6.mlp.act_fn.threshold": "model-00002-of-00006.safetensors",
289
+ "wrapped_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
290
+ "wrapped_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
291
+ "wrapped_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
292
+ "wrapped_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
293
+ "wrapped_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
294
+ "wrapped_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
295
+ "wrapped_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
296
+ "wrapped_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
297
+ "wrapped_model.model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
298
+ "wrapped_model.model.layers.7.mlp.act_fn.threshold": "model-00002-of-00006.safetensors",
299
+ "wrapped_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
300
+ "wrapped_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
301
+ "wrapped_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
302
+ "wrapped_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
303
+ "wrapped_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
304
+ "wrapped_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
305
+ "wrapped_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
306
+ "wrapped_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
307
+ "wrapped_model.model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
308
+ "wrapped_model.model.layers.8.mlp.act_fn.threshold": "model-00002-of-00006.safetensors",
309
+ "wrapped_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
310
+ "wrapped_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
311
+ "wrapped_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
312
+ "wrapped_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
313
+ "wrapped_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
314
+ "wrapped_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
315
+ "wrapped_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
316
+ "wrapped_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
317
+ "wrapped_model.model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
318
+ "wrapped_model.model.layers.9.mlp.act_fn.threshold": "model-00002-of-00006.safetensors",
319
+ "wrapped_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
320
+ "wrapped_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
321
+ "wrapped_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
322
+ "wrapped_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
323
+ "wrapped_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
324
+ "wrapped_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
325
+ "wrapped_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
326
+ "wrapped_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
327
+ "wrapped_model.model.norm.weight": "model-00006-of-00006.safetensors"
328
+ }
329
+ }