Hugging Face's logo

crumb
/
test-00-switchllama-i3b-f10b-e4-init

Text Generation
Transformers
PyTorch
switchllama
custom_code
Model card Files Community
crumb commited on
Commit
fbf4420
•
1 Parent(s): dd80804

Upload SwitchLlamaForCausalLM

Browse files
Files changed (7) hide show
  1. config.json +30 -0
  2. generation_config.json +6 -0
  3. pytorch_model-00001-of-00004.bin +3 -0
  4. pytorch_model-00002-of-00004.bin +3 -0
  5. pytorch_model-00003-of-00004.bin +3 -0
  6. pytorch_model-00004-of-00004.bin +3 -0
  7. pytorch_model.bin.index.json +504 -0
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SwitchLlamaForCausalLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "eos_token_id": 2,
7
+ "expert_capacity": 64,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3200,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 8640,
12
+ "max_position_embeddings": 2048,
13
+ "model_type": "switchllama",
14
+ "num_attention_heads": 32,
15
+ "num_experts": 4,
16
+ "num_hidden_layers": 26,
17
+ "num_key_value_heads": 32,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 10000.0,
22
+ "router_bias": false,
23
+ "router_ignore_padding_tokens": false,
24
+ "router_jitter_noise": 0.01,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.32.0.dev0",
28
+ "use_cache": true,
29
+ "vocab_size": 32000
30
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.32.0.dev0"
6
+ }
pytorch_model-00001-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50d13e0ef64acf2c0d428a5de8df93c7f4da1d3fa5a1495308d8054dd5d6ce1e
3
+ size 9962027807
pytorch_model-00002-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8338eb8c8af3baec54f45083be9b261e70cc05ccd1f2a5193308f82ca7d4bb07
3
+ size 9994823194
pytorch_model-00003-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41dc8d2a129b0edf63646b6d89071e2aa2f477ee2b282f7ab9db1237ec91b8c4
3
+ size 9941496388
pytorch_model-00004-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a1cbf01b74492d2043456d855f1e7df215c7bf64b9cc068b0a955b82ee423b7
3
+ size 9687582030
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,504 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 39585753600
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00004-of-00004.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
9
+ "model.layers.0.mlp.experts.expert_0.down_proj.weight": "pytorch_model-00001-of-00004.bin",
10
+ "model.layers.0.mlp.experts.expert_0.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
11
+ "model.layers.0.mlp.experts.expert_0.up_proj.weight": "pytorch_model-00001-of-00004.bin",
12
+ "model.layers.0.mlp.experts.expert_1.down_proj.weight": "pytorch_model-00001-of-00004.bin",
13
+ "model.layers.0.mlp.experts.expert_1.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
14
+ "model.layers.0.mlp.experts.expert_1.up_proj.weight": "pytorch_model-00001-of-00004.bin",
15
+ "model.layers.0.mlp.experts.expert_2.down_proj.weight": "pytorch_model-00001-of-00004.bin",
16
+ "model.layers.0.mlp.experts.expert_2.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
17
+ "model.layers.0.mlp.experts.expert_2.up_proj.weight": "pytorch_model-00001-of-00004.bin",
18
+ "model.layers.0.mlp.experts.expert_3.down_proj.weight": "pytorch_model-00001-of-00004.bin",
19
+ "model.layers.0.mlp.experts.expert_3.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
20
+ "model.layers.0.mlp.experts.expert_3.up_proj.weight": "pytorch_model-00001-of-00004.bin",
21
+ "model.layers.0.mlp.router.classifier.weight": "pytorch_model-00001-of-00004.bin",
22
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
23
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
24
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
25
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
26
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
27
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
28
+ "model.layers.1.mlp.experts.expert_0.down_proj.weight": "pytorch_model-00001-of-00004.bin",
29
+ "model.layers.1.mlp.experts.expert_0.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
30
+ "model.layers.1.mlp.experts.expert_0.up_proj.weight": "pytorch_model-00001-of-00004.bin",
31
+ "model.layers.1.mlp.experts.expert_1.down_proj.weight": "pytorch_model-00001-of-00004.bin",
32
+ "model.layers.1.mlp.experts.expert_1.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
33
+ "model.layers.1.mlp.experts.expert_1.up_proj.weight": "pytorch_model-00001-of-00004.bin",
34
+ "model.layers.1.mlp.experts.expert_2.down_proj.weight": "pytorch_model-00001-of-00004.bin",
35
+ "model.layers.1.mlp.experts.expert_2.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
36
+ "model.layers.1.mlp.experts.expert_2.up_proj.weight": "pytorch_model-00001-of-00004.bin",
37
+ "model.layers.1.mlp.experts.expert_3.down_proj.weight": "pytorch_model-00001-of-00004.bin",
38
+ "model.layers.1.mlp.experts.expert_3.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
39
+ "model.layers.1.mlp.experts.expert_3.up_proj.weight": "pytorch_model-00001-of-00004.bin",
40
+ "model.layers.1.mlp.router.classifier.weight": "pytorch_model-00001-of-00004.bin",
41
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
42
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
43
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
44
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
45
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
46
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
47
+ "model.layers.10.mlp.experts.expert_0.down_proj.weight": "pytorch_model-00002-of-00004.bin",
48
+ "model.layers.10.mlp.experts.expert_0.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
49
+ "model.layers.10.mlp.experts.expert_0.up_proj.weight": "pytorch_model-00002-of-00004.bin",
50
+ "model.layers.10.mlp.experts.expert_1.down_proj.weight": "pytorch_model-00002-of-00004.bin",
51
+ "model.layers.10.mlp.experts.expert_1.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
52
+ "model.layers.10.mlp.experts.expert_1.up_proj.weight": "pytorch_model-00002-of-00004.bin",
53
+ "model.layers.10.mlp.experts.expert_2.down_proj.weight": "pytorch_model-00002-of-00004.bin",
54
+ "model.layers.10.mlp.experts.expert_2.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
55
+ "model.layers.10.mlp.experts.expert_2.up_proj.weight": "pytorch_model-00002-of-00004.bin",
56
+ "model.layers.10.mlp.experts.expert_3.down_proj.weight": "pytorch_model-00002-of-00004.bin",
57
+ "model.layers.10.mlp.experts.expert_3.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
58
+ "model.layers.10.mlp.experts.expert_3.up_proj.weight": "pytorch_model-00002-of-00004.bin",
59
+ "model.layers.10.mlp.router.classifier.weight": "pytorch_model-00002-of-00004.bin",
60
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
61
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
62
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
63
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
64
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
65
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
66
+ "model.layers.11.mlp.experts.expert_0.down_proj.weight": "pytorch_model-00002-of-00004.bin",
67
+ "model.layers.11.mlp.experts.expert_0.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
68
+ "model.layers.11.mlp.experts.expert_0.up_proj.weight": "pytorch_model-00002-of-00004.bin",
69
+ "model.layers.11.mlp.experts.expert_1.down_proj.weight": "pytorch_model-00002-of-00004.bin",
70
+ "model.layers.11.mlp.experts.expert_1.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
71
+ "model.layers.11.mlp.experts.expert_1.up_proj.weight": "pytorch_model-00002-of-00004.bin",
72
+ "model.layers.11.mlp.experts.expert_2.down_proj.weight": "pytorch_model-00002-of-00004.bin",
73
+ "model.layers.11.mlp.experts.expert_2.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
74
+ "model.layers.11.mlp.experts.expert_2.up_proj.weight": "pytorch_model-00002-of-00004.bin",
75
+ "model.layers.11.mlp.experts.expert_3.down_proj.weight": "pytorch_model-00002-of-00004.bin",
76
+ "model.layers.11.mlp.experts.expert_3.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
77
+ "model.layers.11.mlp.experts.expert_3.up_proj.weight": "pytorch_model-00002-of-00004.bin",
78
+ "model.layers.11.mlp.router.classifier.weight": "pytorch_model-00002-of-00004.bin",
79
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
80
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
81
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
82
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
83
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
84
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
85
+ "model.layers.12.mlp.experts.expert_0.down_proj.weight": "pytorch_model-00002-of-00004.bin",
86
+ "model.layers.12.mlp.experts.expert_0.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
87
+ "model.layers.12.mlp.experts.expert_0.up_proj.weight": "pytorch_model-00002-of-00004.bin",
88
+ "model.layers.12.mlp.experts.expert_1.down_proj.weight": "pytorch_model-00002-of-00004.bin",
89
+ "model.layers.12.mlp.experts.expert_1.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
90
+ "model.layers.12.mlp.experts.expert_1.up_proj.weight": "pytorch_model-00002-of-00004.bin",
91
+ "model.layers.12.mlp.experts.expert_2.down_proj.weight": "pytorch_model-00002-of-00004.bin",
92
+ "model.layers.12.mlp.experts.expert_2.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
93
+ "model.layers.12.mlp.experts.expert_2.up_proj.weight": "pytorch_model-00002-of-00004.bin",
94
+ "model.layers.12.mlp.experts.expert_3.down_proj.weight": "pytorch_model-00002-of-00004.bin",
95
+ "model.layers.12.mlp.experts.expert_3.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
96
+ "model.layers.12.mlp.experts.expert_3.up_proj.weight": "pytorch_model-00002-of-00004.bin",
97
+ "model.layers.12.mlp.router.classifier.weight": "pytorch_model-00002-of-00004.bin",
98
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
99
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
100
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
101
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
102
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
103
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
104
+ "model.layers.13.mlp.experts.expert_0.down_proj.weight": "pytorch_model-00003-of-00004.bin",
105
+ "model.layers.13.mlp.experts.expert_0.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
106
+ "model.layers.13.mlp.experts.expert_0.up_proj.weight": "pytorch_model-00003-of-00004.bin",
107
+ "model.layers.13.mlp.experts.expert_1.down_proj.weight": "pytorch_model-00003-of-00004.bin",
108
+ "model.layers.13.mlp.experts.expert_1.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
109
+ "model.layers.13.mlp.experts.expert_1.up_proj.weight": "pytorch_model-00003-of-00004.bin",
110
+ "model.layers.13.mlp.experts.expert_2.down_proj.weight": "pytorch_model-00003-of-00004.bin",
111
+ "model.layers.13.mlp.experts.expert_2.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
112
+ "model.layers.13.mlp.experts.expert_2.up_proj.weight": "pytorch_model-00003-of-00004.bin",
113
+ "model.layers.13.mlp.experts.expert_3.down_proj.weight": "pytorch_model-00003-of-00004.bin",
114
+ "model.layers.13.mlp.experts.expert_3.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
115
+ "model.layers.13.mlp.experts.expert_3.up_proj.weight": "pytorch_model-00003-of-00004.bin",
116
+ "model.layers.13.mlp.router.classifier.weight": "pytorch_model-00002-of-00004.bin",
117
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
118
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
119
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
120
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
121
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
122
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
123
+ "model.layers.14.mlp.experts.expert_0.down_proj.weight": "pytorch_model-00003-of-00004.bin",
124
+ "model.layers.14.mlp.experts.expert_0.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
125
+ "model.layers.14.mlp.experts.expert_0.up_proj.weight": "pytorch_model-00003-of-00004.bin",
126
+ "model.layers.14.mlp.experts.expert_1.down_proj.weight": "pytorch_model-00003-of-00004.bin",
127
+ "model.layers.14.mlp.experts.expert_1.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
128
+ "model.layers.14.mlp.experts.expert_1.up_proj.weight": "pytorch_model-00003-of-00004.bin",
129
+ "model.layers.14.mlp.experts.expert_2.down_proj.weight": "pytorch_model-00003-of-00004.bin",
130
+ "model.layers.14.mlp.experts.expert_2.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
131
+ "model.layers.14.mlp.experts.expert_2.up_proj.weight": "pytorch_model-00003-of-00004.bin",
132
+ "model.layers.14.mlp.experts.expert_3.down_proj.weight": "pytorch_model-00003-of-00004.bin",
133
+ "model.layers.14.mlp.experts.expert_3.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
134
+ "model.layers.14.mlp.experts.expert_3.up_proj.weight": "pytorch_model-00003-of-00004.bin",
135
+ "model.layers.14.mlp.router.classifier.weight": "pytorch_model-00003-of-00004.bin",
136
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
137
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
138
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
139
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
140
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
141
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
142
+ "model.layers.15.mlp.experts.expert_0.down_proj.weight": "pytorch_model-00003-of-00004.bin",
143
+ "model.layers.15.mlp.experts.expert_0.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
144
+ "model.layers.15.mlp.experts.expert_0.up_proj.weight": "pytorch_model-00003-of-00004.bin",
145
+ "model.layers.15.mlp.experts.expert_1.down_proj.weight": "pytorch_model-00003-of-00004.bin",
146
+ "model.layers.15.mlp.experts.expert_1.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
147
+ "model.layers.15.mlp.experts.expert_1.up_proj.weight": "pytorch_model-00003-of-00004.bin",
148
+ "model.layers.15.mlp.experts.expert_2.down_proj.weight": "pytorch_model-00003-of-00004.bin",
149
+ "model.layers.15.mlp.experts.expert_2.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
150
+ "model.layers.15.mlp.experts.expert_2.up_proj.weight": "pytorch_model-00003-of-00004.bin",
151
+ "model.layers.15.mlp.experts.expert_3.down_proj.weight": "pytorch_model-00003-of-00004.bin",
152
+ "model.layers.15.mlp.experts.expert_3.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
153
+ "model.layers.15.mlp.experts.expert_3.up_proj.weight": "pytorch_model-00003-of-00004.bin",
154
+ "model.layers.15.mlp.router.classifier.weight": "pytorch_model-00003-of-00004.bin",
155
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
156
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
157
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
158
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
159
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
160
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
161
+ "model.layers.16.mlp.experts.expert_0.down_proj.weight": "pytorch_model-00003-of-00004.bin",
162
+ "model.layers.16.mlp.experts.expert_0.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
163
+ "model.layers.16.mlp.experts.expert_0.up_proj.weight": "pytorch_model-00003-of-00004.bin",
164
+ "model.layers.16.mlp.experts.expert_1.down_proj.weight": "pytorch_model-00003-of-00004.bin",
165
+ "model.layers.16.mlp.experts.expert_1.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
166
+ "model.layers.16.mlp.experts.expert_1.up_proj.weight": "pytorch_model-00003-of-00004.bin",
167
+ "model.layers.16.mlp.experts.expert_2.down_proj.weight": "pytorch_model-00003-of-00004.bin",
168
+ "model.layers.16.mlp.experts.expert_2.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
169
+ "model.layers.16.mlp.experts.expert_2.up_proj.weight": "pytorch_model-00003-of-00004.bin",
170
+ "model.layers.16.mlp.experts.expert_3.down_proj.weight": "pytorch_model-00003-of-00004.bin",
171
+ "model.layers.16.mlp.experts.expert_3.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
172
+ "model.layers.16.mlp.experts.expert_3.up_proj.weight": "pytorch_model-00003-of-00004.bin",
173
+ "model.layers.16.mlp.router.classifier.weight": "pytorch_model-00003-of-00004.bin",
174
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
175
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
176
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
177
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
178
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
179
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
180
+ "model.layers.17.mlp.experts.expert_0.down_proj.weight": "pytorch_model-00003-of-00004.bin",
181
+ "model.layers.17.mlp.experts.expert_0.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
182
+ "model.layers.17.mlp.experts.expert_0.up_proj.weight": "pytorch_model-00003-of-00004.bin",
183
+ "model.layers.17.mlp.experts.expert_1.down_proj.weight": "pytorch_model-00003-of-00004.bin",
184
+ "model.layers.17.mlp.experts.expert_1.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
185
+ "model.layers.17.mlp.experts.expert_1.up_proj.weight": "pytorch_model-00003-of-00004.bin",
186
+ "model.layers.17.mlp.experts.expert_2.down_proj.weight": "pytorch_model-00003-of-00004.bin",
187
+ "model.layers.17.mlp.experts.expert_2.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
188
+ "model.layers.17.mlp.experts.expert_2.up_proj.weight": "pytorch_model-00003-of-00004.bin",
189
+ "model.layers.17.mlp.experts.expert_3.down_proj.weight": "pytorch_model-00003-of-00004.bin",
190
+ "model.layers.17.mlp.experts.expert_3.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
191
+ "model.layers.17.mlp.experts.expert_3.up_proj.weight": "pytorch_model-00003-of-00004.bin",
192
+ "model.layers.17.mlp.router.classifier.weight": "pytorch_model-00003-of-00004.bin",
193
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
194
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
195
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
196
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
197
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
198
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
199
+ "model.layers.18.mlp.experts.expert_0.down_proj.weight": "pytorch_model-00003-of-00004.bin",
200
+ "model.layers.18.mlp.experts.expert_0.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
201
+ "model.layers.18.mlp.experts.expert_0.up_proj.weight": "pytorch_model-00003-of-00004.bin",
202
+ "model.layers.18.mlp.experts.expert_1.down_proj.weight": "pytorch_model-00003-of-00004.bin",
203
+ "model.layers.18.mlp.experts.expert_1.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
204
+ "model.layers.18.mlp.experts.expert_1.up_proj.weight": "pytorch_model-00003-of-00004.bin",
205
+ "model.layers.18.mlp.experts.expert_2.down_proj.weight": "pytorch_model-00003-of-00004.bin",
206
+ "model.layers.18.mlp.experts.expert_2.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
207
+ "model.layers.18.mlp.experts.expert_2.up_proj.weight": "pytorch_model-00003-of-00004.bin",
208
+ "model.layers.18.mlp.experts.expert_3.down_proj.weight": "pytorch_model-00003-of-00004.bin",
209
+ "model.layers.18.mlp.experts.expert_3.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
210
+ "model.layers.18.mlp.experts.expert_3.up_proj.weight": "pytorch_model-00003-of-00004.bin",
211
+ "model.layers.18.mlp.router.classifier.weight": "pytorch_model-00003-of-00004.bin",
212
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
213
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
214
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
215
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
216
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
217
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
218
+ "model.layers.19.mlp.experts.expert_0.down_proj.weight": "pytorch_model-00003-of-00004.bin",
219
+ "model.layers.19.mlp.experts.expert_0.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
220
+ "model.layers.19.mlp.experts.expert_0.up_proj.weight": "pytorch_model-00003-of-00004.bin",
221
+ "model.layers.19.mlp.experts.expert_1.down_proj.weight": "pytorch_model-00003-of-00004.bin",
222
+ "model.layers.19.mlp.experts.expert_1.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
223
+ "model.layers.19.mlp.experts.expert_1.up_proj.weight": "pytorch_model-00003-of-00004.bin",
224
+ "model.layers.19.mlp.experts.expert_2.down_proj.weight": "pytorch_model-00003-of-00004.bin",
225
+ "model.layers.19.mlp.experts.expert_2.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
226
+ "model.layers.19.mlp.experts.expert_2.up_proj.weight": "pytorch_model-00003-of-00004.bin",
227
+ "model.layers.19.mlp.experts.expert_3.down_proj.weight": "pytorch_model-00004-of-00004.bin",
228
+ "model.layers.19.mlp.experts.expert_3.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
229
+ "model.layers.19.mlp.experts.expert_3.up_proj.weight": "pytorch_model-00004-of-00004.bin",
230
+ "model.layers.19.mlp.router.classifier.weight": "pytorch_model-00003-of-00004.bin",
231
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
232
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
233
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
234
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
235
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
236
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
237
+ "model.layers.2.mlp.experts.expert_0.down_proj.weight": "pytorch_model-00001-of-00004.bin",
238
+ "model.layers.2.mlp.experts.expert_0.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
239
+ "model.layers.2.mlp.experts.expert_0.up_proj.weight": "pytorch_model-00001-of-00004.bin",
240
+ "model.layers.2.mlp.experts.expert_1.down_proj.weight": "pytorch_model-00001-of-00004.bin",
241
+ "model.layers.2.mlp.experts.expert_1.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
242
+ "model.layers.2.mlp.experts.expert_1.up_proj.weight": "pytorch_model-00001-of-00004.bin",
243
+ "model.layers.2.mlp.experts.expert_2.down_proj.weight": "pytorch_model-00001-of-00004.bin",
244
+ "model.layers.2.mlp.experts.expert_2.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
245
+ "model.layers.2.mlp.experts.expert_2.up_proj.weight": "pytorch_model-00001-of-00004.bin",
246
+ "model.layers.2.mlp.experts.expert_3.down_proj.weight": "pytorch_model-00001-of-00004.bin",
247
+ "model.layers.2.mlp.experts.expert_3.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
248
+ "model.layers.2.mlp.experts.expert_3.up_proj.weight": "pytorch_model-00001-of-00004.bin",
249
+ "model.layers.2.mlp.router.classifier.weight": "pytorch_model-00001-of-00004.bin",
250
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
251
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
252
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
253
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
254
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
255
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
256
+ "model.layers.20.mlp.experts.expert_0.down_proj.weight": "pytorch_model-00004-of-00004.bin",
257
+ "model.layers.20.mlp.experts.expert_0.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
258
+ "model.layers.20.mlp.experts.expert_0.up_proj.weight": "pytorch_model-00004-of-00004.bin",
259
+ "model.layers.20.mlp.experts.expert_1.down_proj.weight": "pytorch_model-00004-of-00004.bin",
260
+ "model.layers.20.mlp.experts.expert_1.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
261
+ "model.layers.20.mlp.experts.expert_1.up_proj.weight": "pytorch_model-00004-of-00004.bin",
262
+ "model.layers.20.mlp.experts.expert_2.down_proj.weight": "pytorch_model-00004-of-00004.bin",
263
+ "model.layers.20.mlp.experts.expert_2.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
264
+ "model.layers.20.mlp.experts.expert_2.up_proj.weight": "pytorch_model-00004-of-00004.bin",
265
+ "model.layers.20.mlp.experts.expert_3.down_proj.weight": "pytorch_model-00004-of-00004.bin",
266
+ "model.layers.20.mlp.experts.expert_3.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
267
+ "model.layers.20.mlp.experts.expert_3.up_proj.weight": "pytorch_model-00004-of-00004.bin",
268
+ "model.layers.20.mlp.router.classifier.weight": "pytorch_model-00004-of-00004.bin",
269
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
270
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
271
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
272
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
273
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
274
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
275
+ "model.layers.21.mlp.experts.expert_0.down_proj.weight": "pytorch_model-00004-of-00004.bin",
276
+ "model.layers.21.mlp.experts.expert_0.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
277
+ "model.layers.21.mlp.experts.expert_0.up_proj.weight": "pytorch_model-00004-of-00004.bin",
278
+ "model.layers.21.mlp.experts.expert_1.down_proj.weight": "pytorch_model-00004-of-00004.bin",
279
+ "model.layers.21.mlp.experts.expert_1.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
280
+ "model.layers.21.mlp.experts.expert_1.up_proj.weight": "pytorch_model-00004-of-00004.bin",
281
+ "model.layers.21.mlp.experts.expert_2.down_proj.weight": "pytorch_model-00004-of-00004.bin",
282
+ "model.layers.21.mlp.experts.expert_2.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
283
+ "model.layers.21.mlp.experts.expert_2.up_proj.weight": "pytorch_model-00004-of-00004.bin",
284
+ "model.layers.21.mlp.experts.expert_3.down_proj.weight": "pytorch_model-00004-of-00004.bin",
285
+ "model.layers.21.mlp.experts.expert_3.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
286
+ "model.layers.21.mlp.experts.expert_3.up_proj.weight": "pytorch_model-00004-of-00004.bin",
287
+ "model.layers.21.mlp.router.classifier.weight": "pytorch_model-00004-of-00004.bin",
288
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
289
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
290
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
291
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
292
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
293
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
294
+ "model.layers.22.mlp.experts.expert_0.down_proj.weight": "pytorch_model-00004-of-00004.bin",
295
+ "model.layers.22.mlp.experts.expert_0.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
296
+ "model.layers.22.mlp.experts.expert_0.up_proj.weight": "pytorch_model-00004-of-00004.bin",
297
+ "model.layers.22.mlp.experts.expert_1.down_proj.weight": "pytorch_model-00004-of-00004.bin",
298
+ "model.layers.22.mlp.experts.expert_1.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
299
+ "model.layers.22.mlp.experts.expert_1.up_proj.weight": "pytorch_model-00004-of-00004.bin",
300
+ "model.layers.22.mlp.experts.expert_2.down_proj.weight": "pytorch_model-00004-of-00004.bin",
301
+ "model.layers.22.mlp.experts.expert_2.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
302
+ "model.layers.22.mlp.experts.expert_2.up_proj.weight": "pytorch_model-00004-of-00004.bin",
303
+ "model.layers.22.mlp.experts.expert_3.down_proj.weight": "pytorch_model-00004-of-00004.bin",
304
+ "model.layers.22.mlp.experts.expert_3.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
305
+ "model.layers.22.mlp.experts.expert_3.up_proj.weight": "pytorch_model-00004-of-00004.bin",
306
+ "model.layers.22.mlp.router.classifier.weight": "pytorch_model-00004-of-00004.bin",
307
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
308
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
309
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
310
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
311
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
312
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
313
+ "model.layers.23.mlp.experts.expert_0.down_proj.weight": "pytorch_model-00004-of-00004.bin",
314
+ "model.layers.23.mlp.experts.expert_0.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
315
+ "model.layers.23.mlp.experts.expert_0.up_proj.weight": "pytorch_model-00004-of-00004.bin",
316
+ "model.layers.23.mlp.experts.expert_1.down_proj.weight": "pytorch_model-00004-of-00004.bin",
317
+ "model.layers.23.mlp.experts.expert_1.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
318
+ "model.layers.23.mlp.experts.expert_1.up_proj.weight": "pytorch_model-00004-of-00004.bin",
319
+ "model.layers.23.mlp.experts.expert_2.down_proj.weight": "pytorch_model-00004-of-00004.bin",
320
+ "model.layers.23.mlp.experts.expert_2.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
321
+ "model.layers.23.mlp.experts.expert_2.up_proj.weight": "pytorch_model-00004-of-00004.bin",
322
+ "model.layers.23.mlp.experts.expert_3.down_proj.weight": "pytorch_model-00004-of-00004.bin",
323
+ "model.layers.23.mlp.experts.expert_3.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
324
+ "model.layers.23.mlp.experts.expert_3.up_proj.weight": "pytorch_model-00004-of-00004.bin",
325
+ "model.layers.23.mlp.router.classifier.weight": "pytorch_model-00004-of-00004.bin",
326
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
327
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
328
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
329
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
330
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
331
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
332
+ "model.layers.24.mlp.experts.expert_0.down_proj.weight": "pytorch_model-00004-of-00004.bin",
333
+ "model.layers.24.mlp.experts.expert_0.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
334
+ "model.layers.24.mlp.experts.expert_0.up_proj.weight": "pytorch_model-00004-of-00004.bin",
335
+ "model.layers.24.mlp.experts.expert_1.down_proj.weight": "pytorch_model-00004-of-00004.bin",
336
+ "model.layers.24.mlp.experts.expert_1.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
337
+ "model.layers.24.mlp.experts.expert_1.up_proj.weight": "pytorch_model-00004-of-00004.bin",
338
+ "model.layers.24.mlp.experts.expert_2.down_proj.weight": "pytorch_model-00004-of-00004.bin",
339
+ "model.layers.24.mlp.experts.expert_2.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
340
+ "model.layers.24.mlp.experts.expert_2.up_proj.weight": "pytorch_model-00004-of-00004.bin",
341
+ "model.layers.24.mlp.experts.expert_3.down_proj.weight": "pytorch_model-00004-of-00004.bin",
342
+ "model.layers.24.mlp.experts.expert_3.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
343
+ "model.layers.24.mlp.experts.expert_3.up_proj.weight": "pytorch_model-00004-of-00004.bin",
344
+ "model.layers.24.mlp.router.classifier.weight": "pytorch_model-00004-of-00004.bin",
345
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
346
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
347
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
348
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
349
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
350
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
351
+ "model.layers.25.mlp.experts.expert_0.down_proj.weight": "pytorch_model-00004-of-00004.bin",
352
+ "model.layers.25.mlp.experts.expert_0.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
353
+ "model.layers.25.mlp.experts.expert_0.up_proj.weight": "pytorch_model-00004-of-00004.bin",
354
+ "model.layers.25.mlp.experts.expert_1.down_proj.weight": "pytorch_model-00004-of-00004.bin",
355
+ "model.layers.25.mlp.experts.expert_1.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
356
+ "model.layers.25.mlp.experts.expert_1.up_proj.weight": "pytorch_model-00004-of-00004.bin",
357
+ "model.layers.25.mlp.experts.expert_2.down_proj.weight": "pytorch_model-00004-of-00004.bin",
358
+ "model.layers.25.mlp.experts.expert_2.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
359
+ "model.layers.25.mlp.experts.expert_2.up_proj.weight": "pytorch_model-00004-of-00004.bin",
360
+ "model.layers.25.mlp.experts.expert_3.down_proj.weight": "pytorch_model-00004-of-00004.bin",
361
+ "model.layers.25.mlp.experts.expert_3.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
362
+ "model.layers.25.mlp.experts.expert_3.up_proj.weight": "pytorch_model-00004-of-00004.bin",
363
+ "model.layers.25.mlp.router.classifier.weight": "pytorch_model-00004-of-00004.bin",
364
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
365
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
366
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
367
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
368
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
369
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
370
+ "model.layers.3.mlp.experts.expert_0.down_proj.weight": "pytorch_model-00001-of-00004.bin",
371
+ "model.layers.3.mlp.experts.expert_0.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
372
+ "model.layers.3.mlp.experts.expert_0.up_proj.weight": "pytorch_model-00001-of-00004.bin",
373
+ "model.layers.3.mlp.experts.expert_1.down_proj.weight": "pytorch_model-00001-of-00004.bin",
374
+ "model.layers.3.mlp.experts.expert_1.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
375
+ "model.layers.3.mlp.experts.expert_1.up_proj.weight": "pytorch_model-00001-of-00004.bin",
376
+ "model.layers.3.mlp.experts.expert_2.down_proj.weight": "pytorch_model-00001-of-00004.bin",
377
+ "model.layers.3.mlp.experts.expert_2.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
378
+ "model.layers.3.mlp.experts.expert_2.up_proj.weight": "pytorch_model-00001-of-00004.bin",
379
+ "model.layers.3.mlp.experts.expert_3.down_proj.weight": "pytorch_model-00001-of-00004.bin",
380
+ "model.layers.3.mlp.experts.expert_3.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
381
+ "model.layers.3.mlp.experts.expert_3.up_proj.weight": "pytorch_model-00001-of-00004.bin",
382
+ "model.layers.3.mlp.router.classifier.weight": "pytorch_model-00001-of-00004.bin",
383
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
384
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
385
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
386
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
387
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
388
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
389
+ "model.layers.4.mlp.experts.expert_0.down_proj.weight": "pytorch_model-00001-of-00004.bin",
390
+ "model.layers.4.mlp.experts.expert_0.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
391
+ "model.layers.4.mlp.experts.expert_0.up_proj.weight": "pytorch_model-00001-of-00004.bin",
392
+ "model.layers.4.mlp.experts.expert_1.down_proj.weight": "pytorch_model-00001-of-00004.bin",
393
+ "model.layers.4.mlp.experts.expert_1.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
394
+ "model.layers.4.mlp.experts.expert_1.up_proj.weight": "pytorch_model-00001-of-00004.bin",
395
+ "model.layers.4.mlp.experts.expert_2.down_proj.weight": "pytorch_model-00001-of-00004.bin",
396
+ "model.layers.4.mlp.experts.expert_2.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
397
+ "model.layers.4.mlp.experts.expert_2.up_proj.weight": "pytorch_model-00001-of-00004.bin",
398
+ "model.layers.4.mlp.experts.expert_3.down_proj.weight": "pytorch_model-00001-of-00004.bin",
399
+ "model.layers.4.mlp.experts.expert_3.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
400
+ "model.layers.4.mlp.experts.expert_3.up_proj.weight": "pytorch_model-00001-of-00004.bin",
401
+ "model.layers.4.mlp.router.classifier.weight": "pytorch_model-00001-of-00004.bin",
402
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
403
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
404
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
405
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
406
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
407
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
408
+ "model.layers.5.mlp.experts.expert_0.down_proj.weight": "pytorch_model-00001-of-00004.bin",
409
+ "model.layers.5.mlp.experts.expert_0.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
410
+ "model.layers.5.mlp.experts.expert_0.up_proj.weight": "pytorch_model-00001-of-00004.bin",
411
+ "model.layers.5.mlp.experts.expert_1.down_proj.weight": "pytorch_model-00001-of-00004.bin",
412
+ "model.layers.5.mlp.experts.expert_1.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
413
+ "model.layers.5.mlp.experts.expert_1.up_proj.weight": "pytorch_model-00001-of-00004.bin",
414
+ "model.layers.5.mlp.experts.expert_2.down_proj.weight": "pytorch_model-00001-of-00004.bin",
415
+ "model.layers.5.mlp.experts.expert_2.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
416
+ "model.layers.5.mlp.experts.expert_2.up_proj.weight": "pytorch_model-00001-of-00004.bin",
417
+ "model.layers.5.mlp.experts.expert_3.down_proj.weight": "pytorch_model-00001-of-00004.bin",
418
+ "model.layers.5.mlp.experts.expert_3.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
419
+ "model.layers.5.mlp.experts.expert_3.up_proj.weight": "pytorch_model-00001-of-00004.bin",
420
+ "model.layers.5.mlp.router.classifier.weight": "pytorch_model-00001-of-00004.bin",
421
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
422
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
423
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
424
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
425
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
426
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
427
+ "model.layers.6.mlp.experts.expert_0.down_proj.weight": "pytorch_model-00001-of-00004.bin",
428
+ "model.layers.6.mlp.experts.expert_0.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
429
+ "model.layers.6.mlp.experts.expert_0.up_proj.weight": "pytorch_model-00001-of-00004.bin",
430
+ "model.layers.6.mlp.experts.expert_1.down_proj.weight": "pytorch_model-00002-of-00004.bin",
431
+ "model.layers.6.mlp.experts.expert_1.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
432
+ "model.layers.6.mlp.experts.expert_1.up_proj.weight": "pytorch_model-00002-of-00004.bin",
433
+ "model.layers.6.mlp.experts.expert_2.down_proj.weight": "pytorch_model-00002-of-00004.bin",
434
+ "model.layers.6.mlp.experts.expert_2.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
435
+ "model.layers.6.mlp.experts.expert_2.up_proj.weight": "pytorch_model-00002-of-00004.bin",
436
+ "model.layers.6.mlp.experts.expert_3.down_proj.weight": "pytorch_model-00002-of-00004.bin",
437
+ "model.layers.6.mlp.experts.expert_3.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
438
+ "model.layers.6.mlp.experts.expert_3.up_proj.weight": "pytorch_model-00002-of-00004.bin",
439
+ "model.layers.6.mlp.router.classifier.weight": "pytorch_model-00001-of-00004.bin",
440
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
441
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
442
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
443
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
444
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
445
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
446
+ "model.layers.7.mlp.experts.expert_0.down_proj.weight": "pytorch_model-00002-of-00004.bin",
447
+ "model.layers.7.mlp.experts.expert_0.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
448
+ "model.layers.7.mlp.experts.expert_0.up_proj.weight": "pytorch_model-00002-of-00004.bin",
449
+ "model.layers.7.mlp.experts.expert_1.down_proj.weight": "pytorch_model-00002-of-00004.bin",
450
+ "model.layers.7.mlp.experts.expert_1.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
451
+ "model.layers.7.mlp.experts.expert_1.up_proj.weight": "pytorch_model-00002-of-00004.bin",
452
+ "model.layers.7.mlp.experts.expert_2.down_proj.weight": "pytorch_model-00002-of-00004.bin",
453
+ "model.layers.7.mlp.experts.expert_2.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
454
+ "model.layers.7.mlp.experts.expert_2.up_proj.weight": "pytorch_model-00002-of-00004.bin",
455
+ "model.layers.7.mlp.experts.expert_3.down_proj.weight": "pytorch_model-00002-of-00004.bin",
456
+ "model.layers.7.mlp.experts.expert_3.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
457
+ "model.layers.7.mlp.experts.expert_3.up_proj.weight": "pytorch_model-00002-of-00004.bin",
458
+ "model.layers.7.mlp.router.classifier.weight": "pytorch_model-00002-of-00004.bin",
459
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
460
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
461
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
462
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
463
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
464
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
465
+ "model.layers.8.mlp.experts.expert_0.down_proj.weight": "pytorch_model-00002-of-00004.bin",
466
+ "model.layers.8.mlp.experts.expert_0.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
467
+ "model.layers.8.mlp.experts.expert_0.up_proj.weight": "pytorch_model-00002-of-00004.bin",
468
+ "model.layers.8.mlp.experts.expert_1.down_proj.weight": "pytorch_model-00002-of-00004.bin",
469
+ "model.layers.8.mlp.experts.expert_1.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
470
+ "model.layers.8.mlp.experts.expert_1.up_proj.weight": "pytorch_model-00002-of-00004.bin",
471
+ "model.layers.8.mlp.experts.expert_2.down_proj.weight": "pytorch_model-00002-of-00004.bin",
472
+ "model.layers.8.mlp.experts.expert_2.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
473
+ "model.layers.8.mlp.experts.expert_2.up_proj.weight": "pytorch_model-00002-of-00004.bin",
474
+ "model.layers.8.mlp.experts.expert_3.down_proj.weight": "pytorch_model-00002-of-00004.bin",
475
+ "model.layers.8.mlp.experts.expert_3.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
476
+ "model.layers.8.mlp.experts.expert_3.up_proj.weight": "pytorch_model-00002-of-00004.bin",
477
+ "model.layers.8.mlp.router.classifier.weight": "pytorch_model-00002-of-00004.bin",
478
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
479
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
480
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
481
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
482
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
483
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
484
+ "model.layers.9.mlp.experts.expert_0.down_proj.weight": "pytorch_model-00002-of-00004.bin",
485
+ "model.layers.9.mlp.experts.expert_0.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
486
+ "model.layers.9.mlp.experts.expert_0.up_proj.weight": "pytorch_model-00002-of-00004.bin",
487
+ "model.layers.9.mlp.experts.expert_1.down_proj.weight": "pytorch_model-00002-of-00004.bin",
488
+ "model.layers.9.mlp.experts.expert_1.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
489
+ "model.layers.9.mlp.experts.expert_1.up_proj.weight": "pytorch_model-00002-of-00004.bin",
490
+ "model.layers.9.mlp.experts.expert_2.down_proj.weight": "pytorch_model-00002-of-00004.bin",
491
+ "model.layers.9.mlp.experts.expert_2.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
492
+ "model.layers.9.mlp.experts.expert_2.up_proj.weight": "pytorch_model-00002-of-00004.bin",
493
+ "model.layers.9.mlp.experts.expert_3.down_proj.weight": "pytorch_model-00002-of-00004.bin",
494
+ "model.layers.9.mlp.experts.expert_3.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
495
+ "model.layers.9.mlp.experts.expert_3.up_proj.weight": "pytorch_model-00002-of-00004.bin",
496
+ "model.layers.9.mlp.router.classifier.weight": "pytorch_model-00002-of-00004.bin",
497
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
498
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
499
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
500
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
501
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
502
+ "model.norm.weight": "pytorch_model-00004-of-00004.bin"
503
+ }
504
+ }