1TuanPham commited on
Commit
14848b6
1 Parent(s): 4c44b46

Upload LlamaForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "1TuanPham/bkai-vietnamese-llama2-7b-sharded",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 11008,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 32,
18
+ "pad_token_id": 2,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float16",
25
+ "transformers_version": "4.35.0",
26
+ "use_cache": true,
27
+ "vocab_size": 46303
28
+ }
generation_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "do_sample": true,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "max_memory": {
7
+ "cpu": 329543315456
8
+ },
9
+ "no_split_module_classes": [
10
+ "LlamaDecoderLayer"
11
+ ],
12
+ "pad_token_id": 0,
13
+ "special_dtypes": {},
14
+ "temperature": 0.6,
15
+ "top_p": 0.9,
16
+ "transformers_version": "4.35.0"
17
+ }
model-00001-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f8336437aa71ab210635cb1756a1ce6345cce271dc92fd29b9ee4a510c99338
3
+ size 884745688
model-00002-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24fbd8353c603d9827cca89f04ed1f2f0402657bfcdd6423d166d0ddcc53466d
3
+ size 843090040
model-00003-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:109c41d848c7ec2a87bf99e0eead4d84cb3bbf8b4df6dbafa9fc8ba97e832cce
3
+ size 899713144
model-00004-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5625fb92647c94e20db9b13c4f9a0b65b89cf351b609af8a8421dc325396312c
3
+ size 899713136
model-00005-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c4837968bf1829db4001f695d6d7d6d84462e597610a5d3a74a09b1340dc37c
3
+ size 899729744
model-00006-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c032358a337c0edeaad55b14be3b6efe462e598b68ddb3cc96c01c3dcf01d01d
3
+ size 876644608
model-00007-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0515cd0d26461b413a194f19a4ff025a55d180a443ddbdd7076cc7b2b13349a4
3
+ size 876644608
model-00008-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f2364402d715b5c2efeebba2be5e01b8f2b8cb05abdd0c29d2397e84135800f
3
+ size 899713160
model-00009-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6131a646224fe4b33e0e5d26d733ea0ebd8f9660c13f22d66bf00e4cc09e9ffd
3
+ size 899713160
model-00010-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f19a3e1eb7090f5aa36dd09f6a1dbd4b79c85e7b6328e61f060a61e31b51bc06
3
+ size 899729768
model-00011-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af5413068a31ea47ab2be34ab449d1a7d29ef62df65622fc072cb8d06eedb97a
3
+ size 876644608
model-00012-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b6ceebfa0d184b18ef5001ba15561ead6557a9feefb958912c8604c7259ccff
3
+ size 876644608
model-00013-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:039bc808f783862c11c71765f214e98800f66a3706b08e209d0d0ab75fb72709
3
+ size 899713160
model-00014-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d45b4e42ba6bca2b01916ffab1060944a93a4d25a43bb6a9f60f484221955f8f
3
+ size 899713160
model-00015-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fb7b235f9f4f6ce840a740e30f75c68d68e28c9279e3fd4159859d36a1742f1
3
+ size 899738048
model-00016-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0377e3bba33c05ccd7c4683b701ace424f2f6cddaee2800c8115b9d3199fd6ed
3
+ size 379314304
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13711171584
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00016-of-00016.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00016.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00016.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00016.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00016.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00016.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00016.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00016.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00016.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00016.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00016.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00002-of-00016.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00002-of-00016.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00016.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00002-of-00016.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00016.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00016.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00016.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00016.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00016.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00006-of-00016.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00006-of-00016.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00006-of-00016.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00006-of-00016.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00016.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00016.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00016.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00016.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00016.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00006-of-00016.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00006-of-00016.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00016.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00006-of-00016.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00016.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00016.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00016.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00016.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00016.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00007-of-00016.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00007-of-00016.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00007-of-00016.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00007-of-00016.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00016.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00016.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00016.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00016.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00016.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00007-of-00016.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00007-of-00016.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00016.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00007-of-00016.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00016.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00016.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00016.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00016.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00016.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00008-of-00016.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00008-of-00016.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00008-of-00016.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00008-of-00016.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00016.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00016.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00016.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00016.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00016.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00008-of-00016.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00008-of-00016.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00016.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00008-of-00016.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00016.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00016.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00016.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00016.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00016.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00009-of-00016.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00009-of-00016.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00016.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00009-of-00016.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00016.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00016.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00016.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00016.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00016.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00009-of-00016.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00009-of-00016.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00009-of-00016.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00009-of-00016.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00016.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00016.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00016.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00016.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00016.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00010-of-00016.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00010-of-00016.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00009-of-00016.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00009-of-00016.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00016.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00016.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00016.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00016.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00016.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00010-of-00016.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00010-of-00016.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00010-of-00016.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00010-of-00016.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00016.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00016.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00010-of-00016.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00016.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00010-of-00016.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00016.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00002-of-00016.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00016.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00002-of-00016.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00016.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00016.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00016.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00016.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00016.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00010-of-00016.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00010-of-00016.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00016.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00010-of-00016.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00016.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00016.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00016.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00016.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00016.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00011-of-00016.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00011-of-00016.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00011-of-00016.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00011-of-00016.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00016.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00016.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00016.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00016.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00016.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00011-of-00016.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00011-of-00016.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00016.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00011-of-00016.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00016.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00016.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00011-of-00016.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00011-of-00016.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00011-of-00016.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00012-of-00016.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00012-of-00016.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00012-of-00016.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00012-of-00016.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00016.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00011-of-00016.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00016.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00016.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00016.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00012-of-00016.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00012-of-00016.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00012-of-00016.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00012-of-00016.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00012-of-00016.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00012-of-00016.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00012-of-00016.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00012-of-00016.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00012-of-00016.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00013-of-00016.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00013-of-00016.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00013-of-00016.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00013-of-00016.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00013-of-00016.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00016.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00016.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00012-of-00016.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00016.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00013-of-00016.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00013-of-00016.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00013-of-00016.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00013-of-00016.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00013-of-00016.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00013-of-00016.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00013-of-00016.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00013-of-00016.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00013-of-00016.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00014-of-00016.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00014-of-00016.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00013-of-00016.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00014-of-00016.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00014-of-00016.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00016.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00013-of-00016.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00013-of-00016.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00013-of-00016.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00014-of-00016.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00014-of-00016.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00014-of-00016.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00014-of-00016.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00014-of-00016.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00014-of-00016.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00014-of-00016.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00014-of-00016.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00014-of-00016.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00015-of-00016.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00015-of-00016.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00014-of-00016.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00014-of-00016.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00015-of-00016.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00014-of-00016.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00014-of-00016.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00014-of-00016.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00014-of-00016.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00003-of-00016.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00003-of-00016.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00016.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00003-of-00016.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00016.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00016.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00016.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00016.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00016.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00015-of-00016.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00015-of-00016.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00015-of-00016.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00015-of-00016.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00015-of-00016.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00015-of-00016.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00015-of-00016.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00015-of-00016.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00015-of-00016.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00015-of-00016.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00015-of-00016.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00015-of-00016.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00015-of-00016.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00015-of-00016.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00015-of-00016.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00015-of-00016.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00015-of-00016.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00015-of-00016.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00003-of-00016.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00003-of-00016.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00016.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00003-of-00016.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00016.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00016.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00016.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00016.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00016.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00004-of-00016.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00004-of-00016.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00016.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00004-of-00016.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00016.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00016.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00016.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00016.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00016.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00004-of-00016.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00004-of-00016.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00016.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00004-of-00016.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00016.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00016.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00016.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00016.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00016.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00005-of-00016.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00005-of-00016.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00016.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00004-of-00016.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00016.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00016.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00016.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00016.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00016.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00005-of-00016.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00005-of-00016.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00016.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00005-of-00016.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00016.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00016.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00016.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00016.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00016.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00005-of-00016.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00005-of-00016.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00016.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00005-of-00016.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00016.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00016.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00016.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00016.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00016.safetensors",
296
+ "model.norm.weight": "model-00015-of-00016.safetensors"
297
+ }
298
+ }