Hugging Face's logo

ggml-org
/
stories15M_MOE

Text Generation
Transformers
Safetensors
GGUF
mixtral
text-generation-inference
Inference Endpoints
Model card Files Community
stories15M_MOE
File size: 8,890 Bytes 
04b43ee
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
 
{
  "metadata": {
    "total_size": 72744704,
    "format": "safetensors"
  },
  "weight_map": {
    "model.embed_tokens.weight": "model.safetensors",
    "model.norm.weight": "model.safetensors",
    "lm_head.weight": "model.safetensors",
    "model.layers.0.input_layernorm.weight": "model.safetensors",
    "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
    "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
    "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
    "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
    "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
    "model.layers.0.block_sparse_moe.gate.weight": "model.safetensors",
    "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model.safetensors",
    "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model.safetensors",
    "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model.safetensors",
    "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model.safetensors",
    "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model.safetensors",
    "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model.safetensors",
    "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model.safetensors",
    "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model.safetensors",
    "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model.safetensors",
    "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model.safetensors",
    "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model.safetensors",
    "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model.safetensors",
    "model.layers.1.input_layernorm.weight": "model.safetensors",
    "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
    "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
    "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
    "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
    "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
    "model.layers.1.block_sparse_moe.gate.weight": "model.safetensors",
    "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model.safetensors",
    "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model.safetensors",
    "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model.safetensors",
    "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model.safetensors",
    "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model.safetensors",
    "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model.safetensors",
    "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model.safetensors",
    "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model.safetensors",
    "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model.safetensors",
    "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model.safetensors",
    "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model.safetensors",
    "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model.safetensors",
    "model.layers.2.input_layernorm.weight": "model.safetensors",
    "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
    "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
    "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
    "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
    "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
    "model.layers.2.block_sparse_moe.gate.weight": "model.safetensors",
    "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model.safetensors",
    "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model.safetensors",
    "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model.safetensors",
    "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model.safetensors",
    "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model.safetensors",
    "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model.safetensors",
    "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model.safetensors",
    "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model.safetensors",
    "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model.safetensors",
    "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model.safetensors",
    "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model.safetensors",
    "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model.safetensors",
    "model.layers.3.input_layernorm.weight": "model.safetensors",
    "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
    "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
    "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
    "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
    "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
    "model.layers.3.block_sparse_moe.gate.weight": "model.safetensors",
    "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model.safetensors",
    "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model.safetensors",
    "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model.safetensors",
    "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model.safetensors",
    "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model.safetensors",
    "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model.safetensors",
    "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model.safetensors",
    "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model.safetensors",
    "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model.safetensors",
    "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model.safetensors",
    "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model.safetensors",
    "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model.safetensors",
    "model.layers.4.input_layernorm.weight": "model.safetensors",
    "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
    "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
    "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
    "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
    "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
    "model.layers.4.block_sparse_moe.gate.weight": "model.safetensors",
    "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model.safetensors",
    "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model.safetensors",
    "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model.safetensors",
    "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model.safetensors",
    "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model.safetensors",
    "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model.safetensors",
    "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model.safetensors",
    "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model.safetensors",
    "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model.safetensors",
    "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model.safetensors",
    "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model.safetensors",
    "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model.safetensors",
    "model.layers.5.input_layernorm.weight": "model.safetensors",
    "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
    "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
    "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
    "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
    "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
    "model.layers.5.block_sparse_moe.gate.weight": "model.safetensors",
    "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model.safetensors",
    "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model.safetensors",
    "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model.safetensors",
    "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model.safetensors",
    "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model.safetensors",
    "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model.safetensors",
    "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model.safetensors",
    "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model.safetensors",
    "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model.safetensors",
    "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model.safetensors",
    "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model.safetensors",
    "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model.safetensors"
  }
}