Hugging Face's logo

tensorhydra
/
gpt-oss-20b-numinamath

Text Generation
Transformers
Safetensors
PEFT
gpt_oss
math
reasoning
lora
mixture-of-experts
conversational
Model card Files
xet
 Community
gpt-oss-20b-numinamath
File size: 11,253 Bytes
4624d4a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
{
  "weight_map": {
    "model.layers.8.self_attn.sinks": "model-00004-of-00008.safetensors",
    "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
    "model.layers.8.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
    "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
    "model.layers.8.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
    "model.layers.8.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
    "model.layers.8.self_attn.o_proj.bias": "model-00004-of-00008.safetensors",
    "model.layers.8.mlp.router.weight": "model-00004-of-00008.safetensors",
    "model.layers.8.mlp.router.bias": "model-00004-of-00008.safetensors",
    "model.layers.8.mlp.experts.gate_up_proj": "model-00004-of-00008.safetensors",
    "model.layers.8.mlp.experts.gate_up_proj_bias": "model-00004-of-00008.safetensors",
    "model.layers.8.mlp.experts.down_proj": "model-00004-of-00008.safetensors",
    "model.layers.8.mlp.experts.down_proj_bias": "model-00004-of-00008.safetensors",
    "model.layers.8.input_layernorm.weight": "model-00004-of-00008.safetensors",
    "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
    "model.layers.9.self_attn.sinks": "model-00004-of-00008.safetensors",
    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
    "model.layers.9.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
    "model.layers.9.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
    "model.layers.9.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
    "model.layers.9.self_attn.o_proj.bias": "model-00004-of-00008.safetensors",
    "model.layers.9.mlp.router.weight": "model-00004-of-00008.safetensors",
    "model.layers.9.mlp.router.bias": "model-00004-of-00008.safetensors",
    "model.layers.9.mlp.experts.gate_up_proj": "model-00004-of-00008.safetensors",
    "model.layers.9.mlp.experts.gate_up_proj_bias": "model-00004-of-00008.safetensors",
    "model.layers.9.mlp.experts.down_proj": "model-00004-of-00008.safetensors",
    "model.layers.9.mlp.experts.down_proj_bias": "model-00004-of-00008.safetensors",
    "model.layers.9.input_layernorm.weight": "model-00004-of-00008.safetensors",
    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
    "model.layers.10.self_attn.sinks": "model-00004-of-00008.safetensors",
    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
    "model.layers.10.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
    "model.layers.10.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
    "model.layers.10.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
    "model.layers.10.self_attn.o_proj.bias": "model-00004-of-00008.safetensors",
    "model.layers.10.mlp.router.weight": "model-00004-of-00008.safetensors",
    "model.layers.10.mlp.router.bias": "model-00004-of-00008.safetensors",
    "model.layers.10.mlp.experts.gate_up_proj": "model-00004-of-00008.safetensors",
    "model.layers.10.mlp.experts.gate_up_proj_bias": "model-00004-of-00008.safetensors",
    "model.layers.10.mlp.experts.down_proj": "model-00004-of-00008.safetensors",
    "model.layers.10.mlp.experts.down_proj_bias": "model-00004-of-00008.safetensors",
    "model.layers.10.input_layernorm.weight": "model-00004-of-00008.safetensors",
    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
    "model.layers.11.self_attn.sinks": "model-00004-of-00008.safetensors",
    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
    "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
    "model.layers.11.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
    "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
    "model.layers.11.self_attn.o_proj.bias": "model-00004-of-00008.safetensors",
    "model.layers.11.mlp.router.weight": "model-00004-of-00008.safetensors",
    "model.layers.11.mlp.router.bias": "model-00004-of-00008.safetensors",
    "model.layers.11.mlp.experts.gate_up_proj": "model-00005-of-00008.safetensors",
    "model.layers.11.mlp.experts.gate_up_proj_bias": "model-00005-of-00008.safetensors",
    "model.layers.11.mlp.experts.down_proj": "model-00005-of-00008.safetensors",
    "model.layers.11.mlp.experts.down_proj_bias": "model-00005-of-00008.safetensors",
    "model.layers.11.input_layernorm.weight": "model-00005-of-00008.safetensors",
    "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
    "model.layers.12.self_attn.sinks": "model-00005-of-00008.safetensors",
    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
    "model.layers.12.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
    "model.layers.12.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
    "model.layers.12.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
    "model.layers.12.self_attn.o_proj.bias": "model-00005-of-00008.safetensors",
    "model.layers.12.mlp.router.weight": "model-00005-of-00008.safetensors",
    "model.layers.12.mlp.router.bias": "model-00005-of-00008.safetensors",
    "model.layers.12.mlp.experts.gate_up_proj": "model-00005-of-00008.safetensors",
    "model.layers.12.mlp.experts.gate_up_proj_bias": "model-00005-of-00008.safetensors",
    "model.layers.12.mlp.experts.down_proj": "model-00005-of-00008.safetensors",
    "model.layers.12.mlp.experts.down_proj_bias": "model-00005-of-00008.safetensors",
    "model.layers.12.input_layernorm.weight": "model-00005-of-00008.safetensors",
    "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
    "model.layers.13.self_attn.sinks": "model-00005-of-00008.safetensors",
    "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
    "model.layers.13.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
    "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
    "model.layers.13.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
    "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
    "model.layers.13.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
    "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
    "model.layers.13.self_attn.o_proj.bias": "model-00005-of-00008.safetensors",
    "model.layers.13.mlp.router.weight": "model-00005-of-00008.safetensors",
    "model.layers.13.mlp.router.bias": "model-00005-of-00008.safetensors",
    "model.layers.13.mlp.experts.gate_up_proj": "model-00005-of-00008.safetensors",
    "model.layers.13.mlp.experts.gate_up_proj_bias": "model-00005-of-00008.safetensors",
    "model.layers.13.mlp.experts.down_proj": "model-00005-of-00008.safetensors",
    "model.layers.13.mlp.experts.down_proj_bias": "model-00005-of-00008.safetensors",
    "model.layers.13.input_layernorm.weight": "model-00005-of-00008.safetensors",
    "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
    "model.layers.14.self_attn.sinks": "model-00005-of-00008.safetensors",
    "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
    "model.layers.14.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
    "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
    "model.layers.14.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
    "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
    "model.layers.14.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
    "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
    "model.layers.14.self_attn.o_proj.bias": "model-00005-of-00008.safetensors",
    "model.layers.14.mlp.router.weight": "model-00005-of-00008.safetensors",
    "model.layers.14.mlp.router.bias": "model-00005-of-00008.safetensors",
    "model.layers.14.mlp.experts.gate_up_proj": "model-00006-of-00008.safetensors",
    "model.layers.14.mlp.experts.gate_up_proj_bias": "model-00006-of-00008.safetensors",
    "model.layers.14.mlp.experts.down_proj": "model-00006-of-00008.safetensors",
    "model.layers.14.mlp.experts.down_proj_bias": "model-00006-of-00008.safetensors",
    "model.layers.14.input_layernorm.weight": "model-00006-of-00008.safetensors",
    "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
    "model.layers.15.self_attn.sinks": "model-00006-of-00008.safetensors",
    "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
    "model.layers.15.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
    "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
    "model.layers.15.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
    "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
    "model.layers.15.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
    "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
    "model.layers.15.self_attn.o_proj.bias": "model-00006-of-00008.safetensors",
    "model.layers.15.mlp.router.weight": "model-00006-of-00008.safetensors",
    "model.layers.15.mlp.router.bias": "model-00006-of-00008.safetensors",
    "model.layers.15.mlp.experts.gate_up_proj": "model-00006-of-00008.safetensors",
    "model.layers.15.mlp.experts.gate_up_proj_bias": "model-00006-of-00008.safetensors",
    "model.layers.15.mlp.experts.down_proj": "model-00006-of-00008.safetensors",
    "model.layers.15.mlp.experts.down_proj_bias": "model-00006-of-00008.safetensors",
    "model.layers.15.input_layernorm.weight": "model-00006-of-00008.safetensors",
    "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
    "model.layers.16.self_attn.sinks": "model-00006-of-00008.safetensors"
  },
  "shard_count": 3
}