idoru commited on
Commit
8271a85
1 Parent(s): e47b03a

Merged weights from jetmoe-8b-ultrainteract-sft-lora-v4

Browse files
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "jetmoe/jetmoe-8b",
3
+ "activation_function": "silu",
4
+ "architectures": [
5
+ "JetMoEForCausalLM"
6
+ ],
7
+ "bias": true,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "ffn_hidden_size": 5632,
11
+ "glu": true,
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.01,
14
+ "kv_channels": 128,
15
+ "layer_norm_epsilon": 1e-05,
16
+ "max_position_embeddings": 4096,
17
+ "model_type": "jetmoe",
18
+ "moe_num_experts": 8,
19
+ "moe_top_k": 2,
20
+ "n_positions": 4096,
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 24,
23
+ "num_key_value_heads": 16,
24
+ "num_layers": 24,
25
+ "rms_norm_eps": 1e-05,
26
+ "rope_theta": 10000.0,
27
+ "rotary_percent": 1.0,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.40.0.dev0",
30
+ "use_cache": true,
31
+ "vocab_size": 32000
32
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 2,
6
+ "transformers_version": "4.40.0.dev0"
7
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14e2033590c0488eff6318a05c5e6d313683a240f7291826e852bd3eccc0db66
3
+ size 4879573992
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e08abe8cae757733889f680e3e44e0433c6be08680d8e74cf49bf1c297a2e46
3
+ size 4933084288
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef7c25dc7fa42309e9105b57a6a2dce8a116f2e70215ce85a87223f4c0db20e6
3
+ size 4933084344
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcba9add38653bc71b9b6bede80ce2475f44b5734562408488f7abdfde29d525
3
+ size 2298765576
model.safetensors.index.json ADDED
@@ -0,0 +1,273 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 17044475904
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.mlp.bias": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.input_linear.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.output_linear.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.router.layer.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attention.experts.bias": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attention.experts.input_linear.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attention.experts.output_linear.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attention.experts.router.layer.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attention.kv_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.bias": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.input_linear.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.output_linear.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.router.layer.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attention.experts.bias": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attention.experts.input_linear.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attention.experts.output_linear.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attention.experts.router.layer.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attention.kv_proj.weight": "model-00001-of-00004.safetensors",
29
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.mlp.bias": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.mlp.input_linear.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.mlp.output_linear.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.mlp.router.layer.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.self_attention.experts.bias": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.self_attention.experts.input_linear.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.self_attention.experts.output_linear.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attention.experts.router.layer.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attention.kv_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.mlp.bias": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.mlp.input_linear.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.mlp.output_linear.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.mlp.router.layer.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.self_attention.experts.bias": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.self_attention.experts.input_linear.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.self_attention.experts.output_linear.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.self_attention.experts.router.layer.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attention.kv_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.mlp.bias": "model-00002-of-00004.safetensors",
53
+ "model.layers.12.mlp.input_linear.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.12.mlp.output_linear.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.12.mlp.router.layer.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.self_attention.experts.bias": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.self_attention.experts.input_linear.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.self_attention.experts.output_linear.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.self_attention.experts.router.layer.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.self_attention.kv_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.13.mlp.bias": "model-00002-of-00004.safetensors",
64
+ "model.layers.13.mlp.input_linear.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.13.mlp.output_linear.weight": "model-00003-of-00004.safetensors",
66
+ "model.layers.13.mlp.router.layer.weight": "model-00003-of-00004.safetensors",
67
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.13.self_attention.experts.bias": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.self_attention.experts.input_linear.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.self_attention.experts.output_linear.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.self_attention.experts.router.layer.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.self_attention.kv_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors",
74
+ "model.layers.14.mlp.bias": "model-00003-of-00004.safetensors",
75
+ "model.layers.14.mlp.input_linear.weight": "model-00003-of-00004.safetensors",
76
+ "model.layers.14.mlp.output_linear.weight": "model-00003-of-00004.safetensors",
77
+ "model.layers.14.mlp.router.layer.weight": "model-00003-of-00004.safetensors",
78
+ "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
79
+ "model.layers.14.self_attention.experts.bias": "model-00003-of-00004.safetensors",
80
+ "model.layers.14.self_attention.experts.input_linear.weight": "model-00003-of-00004.safetensors",
81
+ "model.layers.14.self_attention.experts.output_linear.weight": "model-00003-of-00004.safetensors",
82
+ "model.layers.14.self_attention.experts.router.layer.weight": "model-00003-of-00004.safetensors",
83
+ "model.layers.14.self_attention.kv_proj.weight": "model-00003-of-00004.safetensors",
84
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
85
+ "model.layers.15.mlp.bias": "model-00003-of-00004.safetensors",
86
+ "model.layers.15.mlp.input_linear.weight": "model-00003-of-00004.safetensors",
87
+ "model.layers.15.mlp.output_linear.weight": "model-00003-of-00004.safetensors",
88
+ "model.layers.15.mlp.router.layer.weight": "model-00003-of-00004.safetensors",
89
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
90
+ "model.layers.15.self_attention.experts.bias": "model-00003-of-00004.safetensors",
91
+ "model.layers.15.self_attention.experts.input_linear.weight": "model-00003-of-00004.safetensors",
92
+ "model.layers.15.self_attention.experts.output_linear.weight": "model-00003-of-00004.safetensors",
93
+ "model.layers.15.self_attention.experts.router.layer.weight": "model-00003-of-00004.safetensors",
94
+ "model.layers.15.self_attention.kv_proj.weight": "model-00003-of-00004.safetensors",
95
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
96
+ "model.layers.16.mlp.bias": "model-00003-of-00004.safetensors",
97
+ "model.layers.16.mlp.input_linear.weight": "model-00003-of-00004.safetensors",
98
+ "model.layers.16.mlp.output_linear.weight": "model-00003-of-00004.safetensors",
99
+ "model.layers.16.mlp.router.layer.weight": "model-00003-of-00004.safetensors",
100
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
101
+ "model.layers.16.self_attention.experts.bias": "model-00003-of-00004.safetensors",
102
+ "model.layers.16.self_attention.experts.input_linear.weight": "model-00003-of-00004.safetensors",
103
+ "model.layers.16.self_attention.experts.output_linear.weight": "model-00003-of-00004.safetensors",
104
+ "model.layers.16.self_attention.experts.router.layer.weight": "model-00003-of-00004.safetensors",
105
+ "model.layers.16.self_attention.kv_proj.weight": "model-00003-of-00004.safetensors",
106
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
107
+ "model.layers.17.mlp.bias": "model-00003-of-00004.safetensors",
108
+ "model.layers.17.mlp.input_linear.weight": "model-00003-of-00004.safetensors",
109
+ "model.layers.17.mlp.output_linear.weight": "model-00003-of-00004.safetensors",
110
+ "model.layers.17.mlp.router.layer.weight": "model-00003-of-00004.safetensors",
111
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
112
+ "model.layers.17.self_attention.experts.bias": "model-00003-of-00004.safetensors",
113
+ "model.layers.17.self_attention.experts.input_linear.weight": "model-00003-of-00004.safetensors",
114
+ "model.layers.17.self_attention.experts.output_linear.weight": "model-00003-of-00004.safetensors",
115
+ "model.layers.17.self_attention.experts.router.layer.weight": "model-00003-of-00004.safetensors",
116
+ "model.layers.17.self_attention.kv_proj.weight": "model-00003-of-00004.safetensors",
117
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
118
+ "model.layers.18.mlp.bias": "model-00003-of-00004.safetensors",
119
+ "model.layers.18.mlp.input_linear.weight": "model-00003-of-00004.safetensors",
120
+ "model.layers.18.mlp.output_linear.weight": "model-00003-of-00004.safetensors",
121
+ "model.layers.18.mlp.router.layer.weight": "model-00003-of-00004.safetensors",
122
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
123
+ "model.layers.18.self_attention.experts.bias": "model-00003-of-00004.safetensors",
124
+ "model.layers.18.self_attention.experts.input_linear.weight": "model-00003-of-00004.safetensors",
125
+ "model.layers.18.self_attention.experts.output_linear.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.18.self_attention.experts.router.layer.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.18.self_attention.kv_proj.weight": "model-00003-of-00004.safetensors",
128
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.19.mlp.bias": "model-00003-of-00004.safetensors",
130
+ "model.layers.19.mlp.input_linear.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.19.mlp.output_linear.weight": "model-00003-of-00004.safetensors",
132
+ "model.layers.19.mlp.router.layer.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
134
+ "model.layers.19.self_attention.experts.bias": "model-00003-of-00004.safetensors",
135
+ "model.layers.19.self_attention.experts.input_linear.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.19.self_attention.experts.output_linear.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.19.self_attention.experts.router.layer.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.19.self_attention.kv_proj.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
140
+ "model.layers.2.mlp.bias": "model-00001-of-00004.safetensors",
141
+ "model.layers.2.mlp.input_linear.weight": "model-00001-of-00004.safetensors",
142
+ "model.layers.2.mlp.output_linear.weight": "model-00001-of-00004.safetensors",
143
+ "model.layers.2.mlp.router.layer.weight": "model-00001-of-00004.safetensors",
144
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
145
+ "model.layers.2.self_attention.experts.bias": "model-00001-of-00004.safetensors",
146
+ "model.layers.2.self_attention.experts.input_linear.weight": "model-00001-of-00004.safetensors",
147
+ "model.layers.2.self_attention.experts.output_linear.weight": "model-00001-of-00004.safetensors",
148
+ "model.layers.2.self_attention.experts.router.layer.weight": "model-00001-of-00004.safetensors",
149
+ "model.layers.2.self_attention.kv_proj.weight": "model-00001-of-00004.safetensors",
150
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.20.mlp.bias": "model-00003-of-00004.safetensors",
152
+ "model.layers.20.mlp.input_linear.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.20.mlp.output_linear.weight": "model-00004-of-00004.safetensors",
154
+ "model.layers.20.mlp.router.layer.weight": "model-00004-of-00004.safetensors",
155
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.20.self_attention.experts.bias": "model-00003-of-00004.safetensors",
157
+ "model.layers.20.self_attention.experts.input_linear.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.20.self_attention.experts.output_linear.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.20.self_attention.experts.router.layer.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.20.self_attention.kv_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.21.input_layernorm.weight": "model-00004-of-00004.safetensors",
162
+ "model.layers.21.mlp.bias": "model-00004-of-00004.safetensors",
163
+ "model.layers.21.mlp.input_linear.weight": "model-00004-of-00004.safetensors",
164
+ "model.layers.21.mlp.output_linear.weight": "model-00004-of-00004.safetensors",
165
+ "model.layers.21.mlp.router.layer.weight": "model-00004-of-00004.safetensors",
166
+ "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
167
+ "model.layers.21.self_attention.experts.bias": "model-00004-of-00004.safetensors",
168
+ "model.layers.21.self_attention.experts.input_linear.weight": "model-00004-of-00004.safetensors",
169
+ "model.layers.21.self_attention.experts.output_linear.weight": "model-00004-of-00004.safetensors",
170
+ "model.layers.21.self_attention.experts.router.layer.weight": "model-00004-of-00004.safetensors",
171
+ "model.layers.21.self_attention.kv_proj.weight": "model-00004-of-00004.safetensors",
172
+ "model.layers.22.input_layernorm.weight": "model-00004-of-00004.safetensors",
173
+ "model.layers.22.mlp.bias": "model-00004-of-00004.safetensors",
174
+ "model.layers.22.mlp.input_linear.weight": "model-00004-of-00004.safetensors",
175
+ "model.layers.22.mlp.output_linear.weight": "model-00004-of-00004.safetensors",
176
+ "model.layers.22.mlp.router.layer.weight": "model-00004-of-00004.safetensors",
177
+ "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
178
+ "model.layers.22.self_attention.experts.bias": "model-00004-of-00004.safetensors",
179
+ "model.layers.22.self_attention.experts.input_linear.weight": "model-00004-of-00004.safetensors",
180
+ "model.layers.22.self_attention.experts.output_linear.weight": "model-00004-of-00004.safetensors",
181
+ "model.layers.22.self_attention.experts.router.layer.weight": "model-00004-of-00004.safetensors",
182
+ "model.layers.22.self_attention.kv_proj.weight": "model-00004-of-00004.safetensors",
183
+ "model.layers.23.input_layernorm.weight": "model-00004-of-00004.safetensors",
184
+ "model.layers.23.mlp.bias": "model-00004-of-00004.safetensors",
185
+ "model.layers.23.mlp.input_linear.weight": "model-00004-of-00004.safetensors",
186
+ "model.layers.23.mlp.output_linear.weight": "model-00004-of-00004.safetensors",
187
+ "model.layers.23.mlp.router.layer.weight": "model-00004-of-00004.safetensors",
188
+ "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
189
+ "model.layers.23.self_attention.experts.bias": "model-00004-of-00004.safetensors",
190
+ "model.layers.23.self_attention.experts.input_linear.weight": "model-00004-of-00004.safetensors",
191
+ "model.layers.23.self_attention.experts.output_linear.weight": "model-00004-of-00004.safetensors",
192
+ "model.layers.23.self_attention.experts.router.layer.weight": "model-00004-of-00004.safetensors",
193
+ "model.layers.23.self_attention.kv_proj.weight": "model-00004-of-00004.safetensors",
194
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
195
+ "model.layers.3.mlp.bias": "model-00001-of-00004.safetensors",
196
+ "model.layers.3.mlp.input_linear.weight": "model-00001-of-00004.safetensors",
197
+ "model.layers.3.mlp.output_linear.weight": "model-00001-of-00004.safetensors",
198
+ "model.layers.3.mlp.router.layer.weight": "model-00001-of-00004.safetensors",
199
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
200
+ "model.layers.3.self_attention.experts.bias": "model-00001-of-00004.safetensors",
201
+ "model.layers.3.self_attention.experts.input_linear.weight": "model-00001-of-00004.safetensors",
202
+ "model.layers.3.self_attention.experts.output_linear.weight": "model-00001-of-00004.safetensors",
203
+ "model.layers.3.self_attention.experts.router.layer.weight": "model-00001-of-00004.safetensors",
204
+ "model.layers.3.self_attention.kv_proj.weight": "model-00001-of-00004.safetensors",
205
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
206
+ "model.layers.4.mlp.bias": "model-00001-of-00004.safetensors",
207
+ "model.layers.4.mlp.input_linear.weight": "model-00001-of-00004.safetensors",
208
+ "model.layers.4.mlp.output_linear.weight": "model-00001-of-00004.safetensors",
209
+ "model.layers.4.mlp.router.layer.weight": "model-00001-of-00004.safetensors",
210
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
211
+ "model.layers.4.self_attention.experts.bias": "model-00001-of-00004.safetensors",
212
+ "model.layers.4.self_attention.experts.input_linear.weight": "model-00001-of-00004.safetensors",
213
+ "model.layers.4.self_attention.experts.output_linear.weight": "model-00001-of-00004.safetensors",
214
+ "model.layers.4.self_attention.experts.router.layer.weight": "model-00001-of-00004.safetensors",
215
+ "model.layers.4.self_attention.kv_proj.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.5.mlp.bias": "model-00001-of-00004.safetensors",
218
+ "model.layers.5.mlp.input_linear.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.5.mlp.output_linear.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.5.mlp.router.layer.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.5.self_attention.experts.bias": "model-00001-of-00004.safetensors",
223
+ "model.layers.5.self_attention.experts.input_linear.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.5.self_attention.experts.output_linear.weight": "model-00001-of-00004.safetensors",
225
+ "model.layers.5.self_attention.experts.router.layer.weight": "model-00001-of-00004.safetensors",
226
+ "model.layers.5.self_attention.kv_proj.weight": "model-00001-of-00004.safetensors",
227
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
228
+ "model.layers.6.mlp.bias": "model-00001-of-00004.safetensors",
229
+ "model.layers.6.mlp.input_linear.weight": "model-00001-of-00004.safetensors",
230
+ "model.layers.6.mlp.output_linear.weight": "model-00002-of-00004.safetensors",
231
+ "model.layers.6.mlp.router.layer.weight": "model-00002-of-00004.safetensors",
232
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
233
+ "model.layers.6.self_attention.experts.bias": "model-00001-of-00004.safetensors",
234
+ "model.layers.6.self_attention.experts.input_linear.weight": "model-00001-of-00004.safetensors",
235
+ "model.layers.6.self_attention.experts.output_linear.weight": "model-00001-of-00004.safetensors",
236
+ "model.layers.6.self_attention.experts.router.layer.weight": "model-00001-of-00004.safetensors",
237
+ "model.layers.6.self_attention.kv_proj.weight": "model-00001-of-00004.safetensors",
238
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
239
+ "model.layers.7.mlp.bias": "model-00002-of-00004.safetensors",
240
+ "model.layers.7.mlp.input_linear.weight": "model-00002-of-00004.safetensors",
241
+ "model.layers.7.mlp.output_linear.weight": "model-00002-of-00004.safetensors",
242
+ "model.layers.7.mlp.router.layer.weight": "model-00002-of-00004.safetensors",
243
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
244
+ "model.layers.7.self_attention.experts.bias": "model-00002-of-00004.safetensors",
245
+ "model.layers.7.self_attention.experts.input_linear.weight": "model-00002-of-00004.safetensors",
246
+ "model.layers.7.self_attention.experts.output_linear.weight": "model-00002-of-00004.safetensors",
247
+ "model.layers.7.self_attention.experts.router.layer.weight": "model-00002-of-00004.safetensors",
248
+ "model.layers.7.self_attention.kv_proj.weight": "model-00002-of-00004.safetensors",
249
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
250
+ "model.layers.8.mlp.bias": "model-00002-of-00004.safetensors",
251
+ "model.layers.8.mlp.input_linear.weight": "model-00002-of-00004.safetensors",
252
+ "model.layers.8.mlp.output_linear.weight": "model-00002-of-00004.safetensors",
253
+ "model.layers.8.mlp.router.layer.weight": "model-00002-of-00004.safetensors",
254
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
255
+ "model.layers.8.self_attention.experts.bias": "model-00002-of-00004.safetensors",
256
+ "model.layers.8.self_attention.experts.input_linear.weight": "model-00002-of-00004.safetensors",
257
+ "model.layers.8.self_attention.experts.output_linear.weight": "model-00002-of-00004.safetensors",
258
+ "model.layers.8.self_attention.experts.router.layer.weight": "model-00002-of-00004.safetensors",
259
+ "model.layers.8.self_attention.kv_proj.weight": "model-00002-of-00004.safetensors",
260
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
261
+ "model.layers.9.mlp.bias": "model-00002-of-00004.safetensors",
262
+ "model.layers.9.mlp.input_linear.weight": "model-00002-of-00004.safetensors",
263
+ "model.layers.9.mlp.output_linear.weight": "model-00002-of-00004.safetensors",
264
+ "model.layers.9.mlp.router.layer.weight": "model-00002-of-00004.safetensors",
265
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
266
+ "model.layers.9.self_attention.experts.bias": "model-00002-of-00004.safetensors",
267
+ "model.layers.9.self_attention.experts.input_linear.weight": "model-00002-of-00004.safetensors",
268
+ "model.layers.9.self_attention.experts.output_linear.weight": "model-00002-of-00004.safetensors",
269
+ "model.layers.9.self_attention.experts.router.layer.weight": "model-00002-of-00004.safetensors",
270
+ "model.layers.9.self_attention.kv_proj.weight": "model-00002-of-00004.safetensors",
271
+ "model.norm.weight": "model-00004-of-00004.safetensors"
272
+ }
273
+ }