Hugging Face's logo

OrionZheng
/
openmoe-8b-400B

Text Generation
Transformers
PyTorch
llama
custom_code
text-generation-inference
Inference Endpoints
Model card Files Community
OrionZheng commited on
Commit
6e8ef8a
•
1 Parent(s): 7cd5904

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. config.json +54 -0
  2. generation_config.json +7 -0
  3. pytorch_model-00001-of-00006.bin +3 -0
  4. pytorch_model-00002-of-00006.bin +3 -0
  5. pytorch_model-00003-of-00006.bin +3 -0
  6. pytorch_model-00004-of-00006.bin +3 -0
  7. pytorch_model-00005-of-00006.bin +3 -0
  8. pytorch_model-00006-of-00006.bin +3 -0
  9. pytorch_model.bin.index.json +246 -0
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "OpenMoeForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "auto_map": {
7
+ "AutoModelForCausalLM": "modeling_openmoe.OpenMoeForCausalLM"
8
+ },
9
+ "bos_token_id": 0,
10
+ "dropout_rate": 0.0,
11
+ "enable_comm_overlap": false,
12
+ "enable_hierarchical_alltoall": false,
13
+ "enable_kernel": false,
14
+ "enable_load_balance": false,
15
+ "eos_token_id": 1,
16
+ "expert_parallel": null,
17
+ "head_dim": 128,
18
+ "hidden_act": "swiglu",
19
+ "hidden_size": 2048,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 8192,
22
+ "label_smoothing": 0.001,
23
+ "layer_norm_epsilon": 1e-06,
24
+ "load_balance_beam_width": 8,
25
+ "load_balance_group_swap_factor": 0.4,
26
+ "load_balance_tolerance": 0.1,
27
+ "max_position_embeddings": 2048,
28
+ "mlp_gated": true,
29
+ "model_type": "llama",
30
+ "moe_layer_interval": 6,
31
+ "num_attention_heads": 24,
32
+ "num_experts": 32,
33
+ "num_hidden_layers": 24,
34
+ "num_key_value_heads": 24,
35
+ "pad_token_id": 0,
36
+ "pretraining_tp": 1,
37
+ "rms_norm_eps": 1e-06,
38
+ "rope_scaling": null,
39
+ "rope_theta": 10000.0,
40
+ "router_aux_loss_factor": 0.01,
41
+ "router_capacity_factor_eval": 2.0,
42
+ "router_capacity_factor_train": 1.25,
43
+ "router_drop_tks": true,
44
+ "router_min_capacity": 4,
45
+ "router_noisy_policy": null,
46
+ "router_topk": 2,
47
+ "router_z_loss_factor": 0.0001,
48
+ "tie_word_embeddings": false,
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.34.0",
51
+ "use_cache": true,
52
+ "vocab_size": 256384,
53
+ "z_loss_factor": 0.01
54
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.34.0"
7
+ }
pytorch_model-00001-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75eb7e91e720600ea72340a24f0eb1ba5006916f79cf321ab75f238a22488476
3
+ size 8341801178
pytorch_model-00002-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a39a5366677598d5fc6685cb4f15d28980f6a4e6735188e0e55658e489a17fa0
3
+ size 6509949054
pytorch_model-00003-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91ceffe337b507ea1e84a4500a6f99a651c75e99a2a4b82bac759112bd270014
3
+ size 9990902124
pytorch_model-00004-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bd3ceac602d19a60bf6d62932b576f1373c2501cf52c32b7c7855e77710e672
3
+ size 9974404632
pytorch_model-00005-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c37c4973e1295385a80823eacc0914897ac0cc576a0399853427e2c4a8f4a1b
3
+ size 8086978210
pytorch_model-00006-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69d343cf72e8bfc2553898516dd5c7726e1ad3b7adbfe4062b693f4c4931b5b1
3
+ size 4516236491
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,246 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 47420186624
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00006-of-00006.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
16
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
17
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
18
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
19
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
20
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
22
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
23
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
24
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
25
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
26
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
27
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
28
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
29
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
30
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
31
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
32
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
33
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
34
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
35
+ "model.layers.11.extra_mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
36
+ "model.layers.11.extra_mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
37
+ "model.layers.11.extra_mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
38
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
39
+ "model.layers.11.mlp.experts.wi_gate": "pytorch_model-00003-of-00006.bin",
40
+ "model.layers.11.mlp.experts.wi_up": "pytorch_model-00003-of-00006.bin",
41
+ "model.layers.11.mlp.experts.wo": "pytorch_model-00003-of-00006.bin",
42
+ "model.layers.11.mlp.gate_weight": "pytorch_model-00002-of-00006.bin",
43
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
44
+ "model.layers.11.pre_extra_mlp_layernorm.weight": "pytorch_model-00003-of-00006.bin",
45
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
46
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
47
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
48
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
49
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
50
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
51
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
52
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
53
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
54
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
55
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
56
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
57
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
58
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
59
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
60
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
61
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
62
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
63
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
64
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
65
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
66
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
67
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
68
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
69
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
70
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
71
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
72
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
73
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
74
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
75
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
76
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
77
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
78
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
79
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
80
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
81
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
82
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
83
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
84
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
85
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
86
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
87
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
88
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
89
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
90
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
91
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
92
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
93
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
94
+ "model.layers.17.extra_mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
95
+ "model.layers.17.extra_mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
96
+ "model.layers.17.extra_mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
97
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
98
+ "model.layers.17.mlp.experts.wi_gate": "pytorch_model-00004-of-00006.bin",
99
+ "model.layers.17.mlp.experts.wi_up": "pytorch_model-00004-of-00006.bin",
100
+ "model.layers.17.mlp.experts.wo": "pytorch_model-00004-of-00006.bin",
101
+ "model.layers.17.mlp.gate_weight": "pytorch_model-00004-of-00006.bin",
102
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
103
+ "model.layers.17.pre_extra_mlp_layernorm.weight": "pytorch_model-00004-of-00006.bin",
104
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
105
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
106
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
107
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
108
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
109
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
110
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
111
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
112
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
113
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
114
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
115
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
116
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
117
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
118
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
119
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
120
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
121
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
122
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
123
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
124
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
125
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
126
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
127
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
128
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
129
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
130
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
131
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
132
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
133
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
134
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
135
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
136
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
137
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
138
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
139
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
140
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
141
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
142
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
143
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
144
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
145
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
146
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
147
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
148
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
149
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
150
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
151
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
152
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
153
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
154
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
155
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
156
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
157
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
158
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
159
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
160
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
161
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
162
+ "model.layers.23.extra_mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
163
+ "model.layers.23.extra_mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
164
+ "model.layers.23.extra_mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
165
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
166
+ "model.layers.23.mlp.experts.wi_gate": "pytorch_model-00005-of-00006.bin",
167
+ "model.layers.23.mlp.experts.wi_up": "pytorch_model-00005-of-00006.bin",
168
+ "model.layers.23.mlp.experts.wo": "pytorch_model-00006-of-00006.bin",
169
+ "model.layers.23.mlp.gate_weight": "pytorch_model-00005-of-00006.bin",
170
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
171
+ "model.layers.23.pre_extra_mlp_layernorm.weight": "pytorch_model-00006-of-00006.bin",
172
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
173
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
174
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
175
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
176
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
177
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
178
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
179
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
180
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
181
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
182
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
183
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
184
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
185
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
186
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
187
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
188
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
189
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
190
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
191
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
192
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
193
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
194
+ "model.layers.5.extra_mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
195
+ "model.layers.5.extra_mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
196
+ "model.layers.5.extra_mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
197
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
198
+ "model.layers.5.mlp.experts.wi_gate": "pytorch_model-00001-of-00006.bin",
199
+ "model.layers.5.mlp.experts.wi_up": "pytorch_model-00002-of-00006.bin",
200
+ "model.layers.5.mlp.experts.wo": "pytorch_model-00002-of-00006.bin",
201
+ "model.layers.5.mlp.gate_weight": "pytorch_model-00001-of-00006.bin",
202
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
203
+ "model.layers.5.pre_extra_mlp_layernorm.weight": "pytorch_model-00002-of-00006.bin",
204
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
205
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
206
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
207
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
208
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
209
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
210
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
211
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
212
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
213
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
214
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
215
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
216
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
217
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
218
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
219
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
220
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
221
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
222
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
223
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
224
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
225
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
226
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
227
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
228
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
229
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
230
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
231
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
232
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
233
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
234
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
235
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
236
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
237
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
238
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
239
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
240
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
241
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
242
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
243
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
244
+ "model.norm.weight": "pytorch_model-00006-of-00006.bin"
245
+ }
246
+ }