Hugging Face's logo

ggml-org
/
stories15M_MOE

Text Generation
Transformers
Safetensors
GGUF
mixtral
text-generation-inference
Inference Endpoints
Model card Files Community
ngxson HF staff commited on
Commit
04b43ee
•
1 Parent(s): 6c8c407

model.safetensors.index.json

Browse files
Files changed (1) hide show
  1. model.safetensors.index.json +125 -0
model.safetensors.index.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 72744704,
4
+ "format": "safetensors"
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.weight": "model.safetensors",
8
+ "model.norm.weight": "model.safetensors",
9
+ "lm_head.weight": "model.safetensors",
10
+ "model.layers.0.input_layernorm.weight": "model.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
12
+ "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
13
+ "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
14
+ "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
15
+ "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
16
+ "model.layers.0.block_sparse_moe.gate.weight": "model.safetensors",
17
+ "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model.safetensors",
18
+ "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model.safetensors",
19
+ "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model.safetensors",
20
+ "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model.safetensors",
21
+ "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model.safetensors",
22
+ "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model.safetensors",
23
+ "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model.safetensors",
24
+ "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model.safetensors",
25
+ "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model.safetensors",
26
+ "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model.safetensors",
27
+ "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model.safetensors",
28
+ "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model.safetensors",
29
+ "model.layers.1.input_layernorm.weight": "model.safetensors",
30
+ "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
31
+ "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
32
+ "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
33
+ "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
34
+ "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
35
+ "model.layers.1.block_sparse_moe.gate.weight": "model.safetensors",
36
+ "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model.safetensors",
37
+ "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model.safetensors",
38
+ "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model.safetensors",
39
+ "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model.safetensors",
40
+ "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model.safetensors",
41
+ "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model.safetensors",
42
+ "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model.safetensors",
43
+ "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model.safetensors",
44
+ "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model.safetensors",
45
+ "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model.safetensors",
46
+ "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model.safetensors",
47
+ "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model.safetensors",
48
+ "model.layers.2.input_layernorm.weight": "model.safetensors",
49
+ "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
50
+ "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
51
+ "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
52
+ "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
53
+ "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
54
+ "model.layers.2.block_sparse_moe.gate.weight": "model.safetensors",
55
+ "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model.safetensors",
56
+ "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model.safetensors",
57
+ "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model.safetensors",
58
+ "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model.safetensors",
59
+ "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model.safetensors",
60
+ "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model.safetensors",
61
+ "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model.safetensors",
62
+ "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model.safetensors",
63
+ "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model.safetensors",
64
+ "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model.safetensors",
65
+ "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model.safetensors",
66
+ "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model.safetensors",
67
+ "model.layers.3.input_layernorm.weight": "model.safetensors",
68
+ "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
69
+ "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
70
+ "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
71
+ "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
72
+ "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
73
+ "model.layers.3.block_sparse_moe.gate.weight": "model.safetensors",
74
+ "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model.safetensors",
75
+ "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model.safetensors",
76
+ "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model.safetensors",
77
+ "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model.safetensors",
78
+ "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model.safetensors",
79
+ "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model.safetensors",
80
+ "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model.safetensors",
81
+ "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model.safetensors",
82
+ "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model.safetensors",
83
+ "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model.safetensors",
84
+ "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model.safetensors",
85
+ "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model.safetensors",
86
+ "model.layers.4.input_layernorm.weight": "model.safetensors",
87
+ "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
88
+ "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
89
+ "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
90
+ "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
91
+ "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
92
+ "model.layers.4.block_sparse_moe.gate.weight": "model.safetensors",
93
+ "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model.safetensors",
94
+ "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model.safetensors",
95
+ "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model.safetensors",
96
+ "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model.safetensors",
97
+ "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model.safetensors",
98
+ "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model.safetensors",
99
+ "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model.safetensors",
100
+ "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model.safetensors",
101
+ "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model.safetensors",
102
+ "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model.safetensors",
103
+ "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model.safetensors",
104
+ "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model.safetensors",
105
+ "model.layers.5.input_layernorm.weight": "model.safetensors",
106
+ "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
107
+ "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
108
+ "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
109
+ "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
110
+ "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
111
+ "model.layers.5.block_sparse_moe.gate.weight": "model.safetensors",
112
+ "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model.safetensors",
113
+ "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model.safetensors",
114
+ "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model.safetensors",
115
+ "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model.safetensors",
116
+ "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model.safetensors",
117
+ "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model.safetensors",
118
+ "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model.safetensors",
119
+ "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model.safetensors",
120
+ "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model.safetensors",
121
+ "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model.safetensors",
122
+ "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model.safetensors",
123
+ "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model.safetensors"
124
+ }
125
+ }