SE6446 commited on
Commit
7a8b105
1 Parent(s): 2d24d88

Upload MixtralForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "moe_out",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5632,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "mixtral",
16
+ "num_attention_heads": 32,
17
+ "num_experts_per_tok": 2,
18
+ "num_hidden_layers": 22,
19
+ "num_key_value_heads": 4,
20
+ "num_local_experts": 2,
21
+ "output_router_logits": false,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000.0,
26
+ "router_aux_loss_coef": 0.001,
27
+ "sliding_window": null,
28
+ "tie_word_embeddings": false,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.37.0.dev0",
31
+ "use_cache": true,
32
+ "vocab_size": 32000
33
+ }
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": "4.37.0.dev0"
6
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57becce5941a368dcc12ed4158b88aa8177a791a811b934a3751a013351ba6d0
3
+ size 4998028744
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:462083cbfbbe739ac4af5bea044c438c256841eb430354e33171d7e98771a348
3
+ size 2447625168
model.safetensors.index.json ADDED
@@ -0,0 +1,296 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 7445618688
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.11.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.12.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.13.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.14.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors",
100
+ "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors",
101
+ "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors",
102
+ "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors",
103
+ "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors",
104
+ "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
105
+ "model.layers.15.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors",
106
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
107
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
108
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
109
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
110
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
112
+ "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors",
113
+ "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors",
114
+ "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors",
115
+ "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors",
116
+ "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors",
117
+ "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
118
+ "model.layers.16.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors",
119
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
120
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
121
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
122
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
123
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
124
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
125
+ "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors",
126
+ "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors",
127
+ "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors",
128
+ "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors",
129
+ "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors",
130
+ "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
131
+ "model.layers.17.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors",
132
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
133
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
134
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
135
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
136
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
137
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
138
+ "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors",
139
+ "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors",
140
+ "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors",
141
+ "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors",
142
+ "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors",
143
+ "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
144
+ "model.layers.18.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors",
145
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
146
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
147
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
148
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
149
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
150
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
151
+ "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors",
152
+ "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors",
154
+ "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors",
155
+ "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors",
156
+ "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
157
+ "model.layers.19.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors",
158
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
159
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
160
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
161
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
162
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.20.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
185
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
186
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.21.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors",
197
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
198
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
199
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
200
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
201
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
202
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
203
+ "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
206
+ "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
208
+ "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
210
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
212
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
226
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
228
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
232
+ "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
234
+ "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
236
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
238
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
240
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
242
+ "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.6.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
260
+ "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
261
+ "model.layers.7.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
262
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
264
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
266
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
268
+ "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
270
+ "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
272
+ "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
274
+ "model.layers.8.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
275
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
276
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
278
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
279
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
280
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
282
+ "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
283
+ "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
284
+ "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.9.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
290
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
292
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
294
+ "model.norm.weight": "model-00002-of-00002.safetensors"
295
+ }
296
+ }