WHJ1998 commited on
Commit
3459c03
1 Parent(s): 7135c77

Upload BaichuanForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "_name_or_path": "baichuan-inc/Baichuan2-7B-Chat",
4
+ "architectures": [
5
+ "BaichuanForCausalLM"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "baichuan-inc/Baichuan2-7B-Chat--configuration_baichuan.BaichuanConfig",
9
+ "AutoModelForCausalLM": "baichuan-inc/Baichuan2-7B-Chat--modeling_baichuan.BaichuanForCausalLM"
10
+ },
11
+ "bos_token_id": 1,
12
+ "eos_token_id": 2,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 4096,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 11008,
17
+ "max_position_embeddings": 4096,
18
+ "model_max_length": 4096,
19
+ "model_type": "baichuan",
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 32,
22
+ "pad_token_id": 0,
23
+ "rms_norm_eps": 1e-06,
24
+ "tie_word_embeddings": false,
25
+ "tokenizer_class": "BaichuanTokenizer",
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.33.0",
28
+ "use_cache": true,
29
+ "vocab_size": 125696,
30
+ "z_loss_weight": 0
31
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "assistant_token_id": 196,
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": 2,
6
+ "max_new_tokens": 2048,
7
+ "pad_token_id": 0,
8
+ "repetition_penalty": 1.05,
9
+ "temperature": 0.3,
10
+ "top_k": 5,
11
+ "top_p": 0.85,
12
+ "transformers_version": "4.33.0",
13
+ "user_token_id": 195
14
+ }
pytorch_model-00001-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:300edab21117a6c0ec39cab6a107affdc366393fa3aab9133d375fb7f3ba907f
3
+ size 1029702570
pytorch_model-00002-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fed74be10e2f4d3ab2e61d15f6f776488bd163e7e7a2607c48693612cd4b485
3
+ size 943756783
pytorch_model-00003-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a415318296a149e3207d9abcdd1dc48a642669073059df91c352f2618d77208a
3
+ size 989894127
pytorch_model-00004-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0322436fe86aae257561a7c66e6955e19a3a115b8260dd691e981bc9d26907d6
3
+ size 899733249
pytorch_model-00005-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06379472cd2ef590cdf25c65c5139f1876a78be6e458ef3a37bfed0be359b991
3
+ size 943756783
pytorch_model-00006-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f66893733ede1282c698edc2a131fcdd731a6e015e135819df12b58d30b8ada0
3
+ size 989894127
pytorch_model-00007-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1705c689df8ec0719d049f3eea082448209ca5fca3b0d1562134d0a11c8e9f9
3
+ size 899733313
pytorch_model-00008-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:765262088d3bf7cb6d87e1a0e611005ab93cf07ff96b1d250af99c530eb1ea7e
3
+ size 943756783
pytorch_model-00009-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b96ba1dcbac32336fb3019ada5fca59479d47957dcf7e419e7e1fed4d294df2
3
+ size 989894127
pytorch_model-00010-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2efabe7ccf559b72dbe146787f018e8694e36521781f7996017b97cc332c01a2
3
+ size 899733313
pytorch_model-00011-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14c217684ed1e844f8720064114e8142c3249896bcada1a766ff9925092a676a
3
+ size 943756783
pytorch_model-00012-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29fe783e77dfa698fd4c73cdf93272820985c81cde5ff6d44d5fe42c0e8f6c6a
3
+ size 989894127
pytorch_model-00013-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a0dad598606bc3d3908736020e4a53bf43b57d5d58499e2cfaa74401e174c95
3
+ size 899733313
pytorch_model-00014-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e41a1c0695b2a343a9e00c02d75c921630d83651851da833b0d16a4a2dc4bdd
3
+ size 943756783
pytorch_model-00015-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68eae088643392d48fdcc424937ec3e8f8296d2dd7bf0fbc95cf6715caaeeea3
3
+ size 675328569
pytorch_model-00016-of-00016.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0e1f3618afc6e326936a9f7283c37b93d1ef68b9c918d7baea118b29263a0d2
3
+ size 1029702570
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,234 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15011946496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00016-of-00016.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00016.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00016.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00016.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00016.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00016.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00016.bin",
13
+ "model.layers.0.self_attn.W_pack.weight": "pytorch_model-00002-of-00016.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00002-of-00016.bin",
15
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00016.bin",
16
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00016.bin",
17
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00016.bin",
18
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00016.bin",
19
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00016.bin",
20
+ "model.layers.1.self_attn.W_pack.weight": "pytorch_model-00002-of-00016.bin",
21
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00016.bin",
22
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00006-of-00016.bin",
23
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00006-of-00016.bin",
24
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00006-of-00016.bin",
25
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00006-of-00016.bin",
26
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00006-of-00016.bin",
27
+ "model.layers.10.self_attn.W_pack.weight": "pytorch_model-00006-of-00016.bin",
28
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00006-of-00016.bin",
29
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00007-of-00016.bin",
30
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00006-of-00016.bin",
31
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00006-of-00016.bin",
32
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00007-of-00016.bin",
33
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00007-of-00016.bin",
34
+ "model.layers.11.self_attn.W_pack.weight": "pytorch_model-00006-of-00016.bin",
35
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00006-of-00016.bin",
36
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00007-of-00016.bin",
37
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00007-of-00016.bin",
38
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00007-of-00016.bin",
39
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00007-of-00016.bin",
40
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00007-of-00016.bin",
41
+ "model.layers.12.self_attn.W_pack.weight": "pytorch_model-00007-of-00016.bin",
42
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00007-of-00016.bin",
43
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00007-of-00016.bin",
44
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00007-of-00016.bin",
45
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00007-of-00016.bin",
46
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00007-of-00016.bin",
47
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00007-of-00016.bin",
48
+ "model.layers.13.self_attn.W_pack.weight": "pytorch_model-00007-of-00016.bin",
49
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00007-of-00016.bin",
50
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00008-of-00016.bin",
51
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00008-of-00016.bin",
52
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00008-of-00016.bin",
53
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00008-of-00016.bin",
54
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00008-of-00016.bin",
55
+ "model.layers.14.self_attn.W_pack.weight": "pytorch_model-00008-of-00016.bin",
56
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00008-of-00016.bin",
57
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00008-of-00016.bin",
58
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00008-of-00016.bin",
59
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00008-of-00016.bin",
60
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00008-of-00016.bin",
61
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00008-of-00016.bin",
62
+ "model.layers.15.self_attn.W_pack.weight": "pytorch_model-00008-of-00016.bin",
63
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00008-of-00016.bin",
64
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00009-of-00016.bin",
65
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00009-of-00016.bin",
66
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00009-of-00016.bin",
67
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00009-of-00016.bin",
68
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00009-of-00016.bin",
69
+ "model.layers.16.self_attn.W_pack.weight": "pytorch_model-00008-of-00016.bin",
70
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00008-of-00016.bin",
71
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00009-of-00016.bin",
72
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00009-of-00016.bin",
73
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00009-of-00016.bin",
74
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00009-of-00016.bin",
75
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00009-of-00016.bin",
76
+ "model.layers.17.self_attn.W_pack.weight": "pytorch_model-00009-of-00016.bin",
77
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00009-of-00016.bin",
78
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00010-of-00016.bin",
79
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00009-of-00016.bin",
80
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00009-of-00016.bin",
81
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00010-of-00016.bin",
82
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00010-of-00016.bin",
83
+ "model.layers.18.self_attn.W_pack.weight": "pytorch_model-00009-of-00016.bin",
84
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00009-of-00016.bin",
85
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00010-of-00016.bin",
86
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00010-of-00016.bin",
87
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00010-of-00016.bin",
88
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00010-of-00016.bin",
89
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00010-of-00016.bin",
90
+ "model.layers.19.self_attn.W_pack.weight": "pytorch_model-00010-of-00016.bin",
91
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00010-of-00016.bin",
92
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00003-of-00016.bin",
93
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00003-of-00016.bin",
94
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00003-of-00016.bin",
95
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00003-of-00016.bin",
96
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00003-of-00016.bin",
97
+ "model.layers.2.self_attn.W_pack.weight": "pytorch_model-00002-of-00016.bin",
98
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00016.bin",
99
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00010-of-00016.bin",
100
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00010-of-00016.bin",
101
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00010-of-00016.bin",
102
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00010-of-00016.bin",
103
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00010-of-00016.bin",
104
+ "model.layers.20.self_attn.W_pack.weight": "pytorch_model-00010-of-00016.bin",
105
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00010-of-00016.bin",
106
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00011-of-00016.bin",
107
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00011-of-00016.bin",
108
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00011-of-00016.bin",
109
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00011-of-00016.bin",
110
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00011-of-00016.bin",
111
+ "model.layers.21.self_attn.W_pack.weight": "pytorch_model-00011-of-00016.bin",
112
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00011-of-00016.bin",
113
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00011-of-00016.bin",
114
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00011-of-00016.bin",
115
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00011-of-00016.bin",
116
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00011-of-00016.bin",
117
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00011-of-00016.bin",
118
+ "model.layers.22.self_attn.W_pack.weight": "pytorch_model-00011-of-00016.bin",
119
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00011-of-00016.bin",
120
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00012-of-00016.bin",
121
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00012-of-00016.bin",
122
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00012-of-00016.bin",
123
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00012-of-00016.bin",
124
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00012-of-00016.bin",
125
+ "model.layers.23.self_attn.W_pack.weight": "pytorch_model-00011-of-00016.bin",
126
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00011-of-00016.bin",
127
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00012-of-00016.bin",
128
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00012-of-00016.bin",
129
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00012-of-00016.bin",
130
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00012-of-00016.bin",
131
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00012-of-00016.bin",
132
+ "model.layers.24.self_attn.W_pack.weight": "pytorch_model-00012-of-00016.bin",
133
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00012-of-00016.bin",
134
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00013-of-00016.bin",
135
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00012-of-00016.bin",
136
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00012-of-00016.bin",
137
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00013-of-00016.bin",
138
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00013-of-00016.bin",
139
+ "model.layers.25.self_attn.W_pack.weight": "pytorch_model-00012-of-00016.bin",
140
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00012-of-00016.bin",
141
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00013-of-00016.bin",
142
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00013-of-00016.bin",
143
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00013-of-00016.bin",
144
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00013-of-00016.bin",
145
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00013-of-00016.bin",
146
+ "model.layers.26.self_attn.W_pack.weight": "pytorch_model-00013-of-00016.bin",
147
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00013-of-00016.bin",
148
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00013-of-00016.bin",
149
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00013-of-00016.bin",
150
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00013-of-00016.bin",
151
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00013-of-00016.bin",
152
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00013-of-00016.bin",
153
+ "model.layers.27.self_attn.W_pack.weight": "pytorch_model-00013-of-00016.bin",
154
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00013-of-00016.bin",
155
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00014-of-00016.bin",
156
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00014-of-00016.bin",
157
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00014-of-00016.bin",
158
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00014-of-00016.bin",
159
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00014-of-00016.bin",
160
+ "model.layers.28.self_attn.W_pack.weight": "pytorch_model-00014-of-00016.bin",
161
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00014-of-00016.bin",
162
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00014-of-00016.bin",
163
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00014-of-00016.bin",
164
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00014-of-00016.bin",
165
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00014-of-00016.bin",
166
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00014-of-00016.bin",
167
+ "model.layers.29.self_attn.W_pack.weight": "pytorch_model-00014-of-00016.bin",
168
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00014-of-00016.bin",
169
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00003-of-00016.bin",
170
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00003-of-00016.bin",
171
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00003-of-00016.bin",
172
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00003-of-00016.bin",
173
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00003-of-00016.bin",
174
+ "model.layers.3.self_attn.W_pack.weight": "pytorch_model-00003-of-00016.bin",
175
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00003-of-00016.bin",
176
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00015-of-00016.bin",
177
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00015-of-00016.bin",
178
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00015-of-00016.bin",
179
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00015-of-00016.bin",
180
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00015-of-00016.bin",
181
+ "model.layers.30.self_attn.W_pack.weight": "pytorch_model-00014-of-00016.bin",
182
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00014-of-00016.bin",
183
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00015-of-00016.bin",
184
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00015-of-00016.bin",
185
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00015-of-00016.bin",
186
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00015-of-00016.bin",
187
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00015-of-00016.bin",
188
+ "model.layers.31.self_attn.W_pack.weight": "pytorch_model-00015-of-00016.bin",
189
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00015-of-00016.bin",
190
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00004-of-00016.bin",
191
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00003-of-00016.bin",
192
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00003-of-00016.bin",
193
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00004-of-00016.bin",
194
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00004-of-00016.bin",
195
+ "model.layers.4.self_attn.W_pack.weight": "pytorch_model-00003-of-00016.bin",
196
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00003-of-00016.bin",
197
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00004-of-00016.bin",
198
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00004-of-00016.bin",
199
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00004-of-00016.bin",
200
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00004-of-00016.bin",
201
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00004-of-00016.bin",
202
+ "model.layers.5.self_attn.W_pack.weight": "pytorch_model-00004-of-00016.bin",
203
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00004-of-00016.bin",
204
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00004-of-00016.bin",
205
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00004-of-00016.bin",
206
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00004-of-00016.bin",
207
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00004-of-00016.bin",
208
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00016.bin",
209
+ "model.layers.6.self_attn.W_pack.weight": "pytorch_model-00004-of-00016.bin",
210
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00004-of-00016.bin",
211
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00005-of-00016.bin",
212
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00005-of-00016.bin",
213
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00005-of-00016.bin",
214
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00005-of-00016.bin",
215
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00005-of-00016.bin",
216
+ "model.layers.7.self_attn.W_pack.weight": "pytorch_model-00005-of-00016.bin",
217
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00005-of-00016.bin",
218
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00005-of-00016.bin",
219
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00005-of-00016.bin",
220
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00005-of-00016.bin",
221
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00005-of-00016.bin",
222
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00005-of-00016.bin",
223
+ "model.layers.8.self_attn.W_pack.weight": "pytorch_model-00005-of-00016.bin",
224
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00005-of-00016.bin",
225
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00006-of-00016.bin",
226
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00006-of-00016.bin",
227
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00006-of-00016.bin",
228
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00006-of-00016.bin",
229
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00006-of-00016.bin",
230
+ "model.layers.9.self_attn.W_pack.weight": "pytorch_model-00005-of-00016.bin",
231
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00005-of-00016.bin",
232
+ "model.norm.weight": "pytorch_model-00015-of-00016.bin"
233
+ }
234
+ }