beomi commited on
Commit
bcf1c4f
1 Parent(s): f249c70

Upload models

Browse files
README.md ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-sa-4.0
3
+ ---
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "eos_token_id": 2,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 4096,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 14336,
11
+ "max_position_embeddings": 2048,
12
+ "model_type": "llama",
13
+ "num_attention_heads": 32,
14
+ "num_hidden_layers": 48,
15
+ "num_key_value_heads": 8,
16
+ "pad_token_id": 0,
17
+ "pretraining_tp": 1,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_scaling": null,
20
+ "tie_word_embeddings": false,
21
+ "torch_dtype": "bfloat16",
22
+ "transformers_version": "4.31.0",
23
+ "use_cache": true,
24
+ "vocab_size": 46336
25
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.31.0"
7
+ }
model-00001-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:612c50a67a7e878080fdb46a86cd7850e0d47d658299a2ebf4159b627bb6a637
3
+ size 899696928
model-00002-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fb4543d80c3873ce9bc230832ce3919e422b2e5e2dbec1f9798f75b4cdd68a2
3
+ size 989891416
model-00003-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83a6132afc3095ce9be46b217962663c56dccf59c6d1b84fff0c60f15764483b
3
+ size 989891408
model-00004-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ae894011ebe8cc21975512088e9b25f412f196ded9c050002e8c1ba170d6756
3
+ size 989908024
model-00005-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4369713dffc6d163a2dcd723d581d11c753a8038d90c3508df207170920a0507
3
+ size 956337688
model-00006-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:330cc3171df6bb7b8981a68c56380ffa287c1e95ada5f36755c83ded7bcb0298
3
+ size 989891432
model-00007-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52d68f2ff76244ad2b01054222f3c7b92a171bc63d1de93c4df5ec76a8b37833
3
+ size 989891432
model-00008-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:425a4d1a1bc859358c90a8f3903336fd8f6f3499274b87cda2e677fc92dd5b07
3
+ size 989908048
model-00009-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7c933d9dd80f64a27712eb91574b68a960ef01e4b2d72b219c0fbdb8d96afdb
3
+ size 956337712
model-00010-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8103b3fdf3f58eae6fb6f7eaf5f522735dae542f2a6406ce807db731dbe17b6a
3
+ size 989891432
model-00011-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d5bcdceb83145eb0312fdfcd497545db6fa8ba16f5930b040f97ff7a115ea08
3
+ size 989891432
model-00012-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7759b558496fb422ade87ef481d15379436c38994480646fb52fef5ae40fc3a
3
+ size 989908048
model-00013-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bfd6cbc0beff1ce6c1ec9ff46f1d22ed28489d18ff53cb589b86512512eba8c
3
+ size 956337712
model-00014-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73ebf1f3ff6221b2bdfeccde5c1984940fa7cfa25c485523311791c2899cadca
3
+ size 989891432
model-00015-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:716c83f70bd21abcc97b70cd99fedfe805351e87ee011c741973644ca8967fac
3
+ size 989891432
model-00016-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d2f99831d1fd4b25346958913561f79b8a8163888f7159d748dd5a9f990d50e
3
+ size 989908048
model-00017-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a7dfa95155eceef1fc53883bf75cd0fbc4f8359457674042a6eac729854785f
3
+ size 956337712
model-00018-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b043b63f6f35ddf1be8142079648c7e1445007bfcf702896aa7582a005d27e1
3
+ size 989891432
model-00019-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cae0dd5c187145212cc44b07dc789edae86d6e53454190dd1aa97d5b07647e7d
3
+ size 989891432
model-00020-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aa68f12298a97ce87df378fedd558bec4f2e9be81ed4e0fe4945a62d90b72f4
3
+ size 989908048
model-00021-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16668c88c1287db05b6ea11b4994b37198a2d88d09af9c880af4c5fcb01cea07
3
+ size 956337712
model-00022-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3f42ddf453f1f78e3a810a21d3cdf0e164670c3e0ad8ca9e09fc5dccbcf2f4f
3
+ size 788572184
model-00023-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4b1af75755e5eb4d7a08ad92a274b0b8ed1d59190dd7ee24cf3726bcc44e408
3
+ size 379584640
model.safetensors.index.json ADDED
@@ -0,0 +1,490 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 21697941504
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00023-of-00023.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00023.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00023.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00023.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00023.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00023.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00023.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00023.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00023.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00023.safetensors",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00023.safetensors",
17
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00023.safetensors",
18
+ "model.layers.1.input_layernorm.weight": "model-00002-of-00023.safetensors",
19
+ "model.layers.1.mlp.down_proj.weight": "model-00002-of-00023.safetensors",
20
+ "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00023.safetensors",
21
+ "model.layers.1.mlp.up_proj.weight": "model-00002-of-00023.safetensors",
22
+ "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00023.safetensors",
23
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00023.safetensors",
24
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00023.safetensors",
25
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00023.safetensors",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00023.safetensors",
27
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00023.safetensors",
28
+ "model.layers.10.input_layernorm.weight": "model-00006-of-00023.safetensors",
29
+ "model.layers.10.mlp.down_proj.weight": "model-00006-of-00023.safetensors",
30
+ "model.layers.10.mlp.gate_proj.weight": "model-00006-of-00023.safetensors",
31
+ "model.layers.10.mlp.up_proj.weight": "model-00006-of-00023.safetensors",
32
+ "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00023.safetensors",
33
+ "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00023.safetensors",
34
+ "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00023.safetensors",
35
+ "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00023.safetensors",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00005-of-00023.safetensors",
37
+ "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00023.safetensors",
38
+ "model.layers.11.input_layernorm.weight": "model-00006-of-00023.safetensors",
39
+ "model.layers.11.mlp.down_proj.weight": "model-00006-of-00023.safetensors",
40
+ "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00023.safetensors",
41
+ "model.layers.11.mlp.up_proj.weight": "model-00006-of-00023.safetensors",
42
+ "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00023.safetensors",
43
+ "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00023.safetensors",
44
+ "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00023.safetensors",
45
+ "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00023.safetensors",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00006-of-00023.safetensors",
47
+ "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00023.safetensors",
48
+ "model.layers.12.input_layernorm.weight": "model-00007-of-00023.safetensors",
49
+ "model.layers.12.mlp.down_proj.weight": "model-00007-of-00023.safetensors",
50
+ "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00023.safetensors",
51
+ "model.layers.12.mlp.up_proj.weight": "model-00007-of-00023.safetensors",
52
+ "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00023.safetensors",
53
+ "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00023.safetensors",
54
+ "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00023.safetensors",
55
+ "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00023.safetensors",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00006-of-00023.safetensors",
57
+ "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00023.safetensors",
58
+ "model.layers.13.input_layernorm.weight": "model-00007-of-00023.safetensors",
59
+ "model.layers.13.mlp.down_proj.weight": "model-00007-of-00023.safetensors",
60
+ "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00023.safetensors",
61
+ "model.layers.13.mlp.up_proj.weight": "model-00007-of-00023.safetensors",
62
+ "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00023.safetensors",
63
+ "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00023.safetensors",
64
+ "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00023.safetensors",
65
+ "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00023.safetensors",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00007-of-00023.safetensors",
67
+ "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00023.safetensors",
68
+ "model.layers.14.input_layernorm.weight": "model-00008-of-00023.safetensors",
69
+ "model.layers.14.mlp.down_proj.weight": "model-00008-of-00023.safetensors",
70
+ "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00023.safetensors",
71
+ "model.layers.14.mlp.up_proj.weight": "model-00007-of-00023.safetensors",
72
+ "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00023.safetensors",
73
+ "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00023.safetensors",
74
+ "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00023.safetensors",
75
+ "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00023.safetensors",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00007-of-00023.safetensors",
77
+ "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00023.safetensors",
78
+ "model.layers.15.input_layernorm.weight": "model-00008-of-00023.safetensors",
79
+ "model.layers.15.mlp.down_proj.weight": "model-00008-of-00023.safetensors",
80
+ "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00023.safetensors",
81
+ "model.layers.15.mlp.up_proj.weight": "model-00008-of-00023.safetensors",
82
+ "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00023.safetensors",
83
+ "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00023.safetensors",
84
+ "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00023.safetensors",
85
+ "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00023.safetensors",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00008-of-00023.safetensors",
87
+ "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00023.safetensors",
88
+ "model.layers.16.input_layernorm.weight": "model-00008-of-00023.safetensors",
89
+ "model.layers.16.mlp.down_proj.weight": "model-00008-of-00023.safetensors",
90
+ "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00023.safetensors",
91
+ "model.layers.16.mlp.up_proj.weight": "model-00008-of-00023.safetensors",
92
+ "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00023.safetensors",
93
+ "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00023.safetensors",
94
+ "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00023.safetensors",
95
+ "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00023.safetensors",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00008-of-00023.safetensors",
97
+ "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00023.safetensors",
98
+ "model.layers.17.input_layernorm.weight": "model-00009-of-00023.safetensors",
99
+ "model.layers.17.mlp.down_proj.weight": "model-00009-of-00023.safetensors",
100
+ "model.layers.17.mlp.gate_proj.weight": "model-00009-of-00023.safetensors",
101
+ "model.layers.17.mlp.up_proj.weight": "model-00009-of-00023.safetensors",
102
+ "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00023.safetensors",
103
+ "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00023.safetensors",
104
+ "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00023.safetensors",
105
+ "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00023.safetensors",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00009-of-00023.safetensors",
107
+ "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00023.safetensors",
108
+ "model.layers.18.input_layernorm.weight": "model-00009-of-00023.safetensors",
109
+ "model.layers.18.mlp.down_proj.weight": "model-00009-of-00023.safetensors",
110
+ "model.layers.18.mlp.gate_proj.weight": "model-00009-of-00023.safetensors",
111
+ "model.layers.18.mlp.up_proj.weight": "model-00009-of-00023.safetensors",
112
+ "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00023.safetensors",
113
+ "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00023.safetensors",
114
+ "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00023.safetensors",
115
+ "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00023.safetensors",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00009-of-00023.safetensors",
117
+ "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00023.safetensors",
118
+ "model.layers.19.input_layernorm.weight": "model-00010-of-00023.safetensors",
119
+ "model.layers.19.mlp.down_proj.weight": "model-00010-of-00023.safetensors",
120
+ "model.layers.19.mlp.gate_proj.weight": "model-00010-of-00023.safetensors",
121
+ "model.layers.19.mlp.up_proj.weight": "model-00010-of-00023.safetensors",
122
+ "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00023.safetensors",
123
+ "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00023.safetensors",
124
+ "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00023.safetensors",
125
+ "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00023.safetensors",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00009-of-00023.safetensors",
127
+ "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00023.safetensors",
128
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00023.safetensors",
129
+ "model.layers.2.mlp.down_proj.weight": "model-00002-of-00023.safetensors",
130
+ "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00023.safetensors",
131
+ "model.layers.2.mlp.up_proj.weight": "model-00002-of-00023.safetensors",
132
+ "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00023.safetensors",
133
+ "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00023.safetensors",
134
+ "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00023.safetensors",
135
+ "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00023.safetensors",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00002-of-00023.safetensors",
137
+ "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00023.safetensors",
138
+ "model.layers.20.input_layernorm.weight": "model-00010-of-00023.safetensors",
139
+ "model.layers.20.mlp.down_proj.weight": "model-00010-of-00023.safetensors",
140
+ "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00023.safetensors",
141
+ "model.layers.20.mlp.up_proj.weight": "model-00010-of-00023.safetensors",
142
+ "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00023.safetensors",
143
+ "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00023.safetensors",
144
+ "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00023.safetensors",
145
+ "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00023.safetensors",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00010-of-00023.safetensors",
147
+ "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00023.safetensors",
148
+ "model.layers.21.input_layernorm.weight": "model-00011-of-00023.safetensors",
149
+ "model.layers.21.mlp.down_proj.weight": "model-00011-of-00023.safetensors",
150
+ "model.layers.21.mlp.gate_proj.weight": "model-00010-of-00023.safetensors",
151
+ "model.layers.21.mlp.up_proj.weight": "model-00011-of-00023.safetensors",
152
+ "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00023.safetensors",
153
+ "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00023.safetensors",
154
+ "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00023.safetensors",
155
+ "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00023.safetensors",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00010-of-00023.safetensors",
157
+ "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00023.safetensors",
158
+ "model.layers.22.input_layernorm.weight": "model-00011-of-00023.safetensors",
159
+ "model.layers.22.mlp.down_proj.weight": "model-00011-of-00023.safetensors",
160
+ "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00023.safetensors",
161
+ "model.layers.22.mlp.up_proj.weight": "model-00011-of-00023.safetensors",
162
+ "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00023.safetensors",
163
+ "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00023.safetensors",
164
+ "model.layers.22.self_attn.o_proj.weight": "model-00011-of-00023.safetensors",
165
+ "model.layers.22.self_attn.q_proj.weight": "model-00011-of-00023.safetensors",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00011-of-00023.safetensors",
167
+ "model.layers.22.self_attn.v_proj.weight": "model-00011-of-00023.safetensors",
168
+ "model.layers.23.input_layernorm.weight": "model-00012-of-00023.safetensors",
169
+ "model.layers.23.mlp.down_proj.weight": "model-00012-of-00023.safetensors",
170
+ "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00023.safetensors",
171
+ "model.layers.23.mlp.up_proj.weight": "model-00011-of-00023.safetensors",
172
+ "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00023.safetensors",
173
+ "model.layers.23.self_attn.k_proj.weight": "model-00011-of-00023.safetensors",
174
+ "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00023.safetensors",
175
+ "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00023.safetensors",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00011-of-00023.safetensors",
177
+ "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00023.safetensors",
178
+ "model.layers.24.input_layernorm.weight": "model-00012-of-00023.safetensors",
179
+ "model.layers.24.mlp.down_proj.weight": "model-00012-of-00023.safetensors",
180
+ "model.layers.24.mlp.gate_proj.weight": "model-00012-of-00023.safetensors",
181
+ "model.layers.24.mlp.up_proj.weight": "model-00012-of-00023.safetensors",
182
+ "model.layers.24.post_attention_layernorm.weight": "model-00012-of-00023.safetensors",
183
+ "model.layers.24.self_attn.k_proj.weight": "model-00012-of-00023.safetensors",
184
+ "model.layers.24.self_attn.o_proj.weight": "model-00012-of-00023.safetensors",
185
+ "model.layers.24.self_attn.q_proj.weight": "model-00012-of-00023.safetensors",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00012-of-00023.safetensors",
187
+ "model.layers.24.self_attn.v_proj.weight": "model-00012-of-00023.safetensors",
188
+ "model.layers.25.input_layernorm.weight": "model-00012-of-00023.safetensors",
189
+ "model.layers.25.mlp.down_proj.weight": "model-00012-of-00023.safetensors",
190
+ "model.layers.25.mlp.gate_proj.weight": "model-00012-of-00023.safetensors",
191
+ "model.layers.25.mlp.up_proj.weight": "model-00012-of-00023.safetensors",
192
+ "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00023.safetensors",
193
+ "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00023.safetensors",
194
+ "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00023.safetensors",
195
+ "model.layers.25.self_attn.q_proj.weight": "model-00012-of-00023.safetensors",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00012-of-00023.safetensors",
197
+ "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00023.safetensors",
198
+ "model.layers.26.input_layernorm.weight": "model-00013-of-00023.safetensors",
199
+ "model.layers.26.mlp.down_proj.weight": "model-00013-of-00023.safetensors",
200
+ "model.layers.26.mlp.gate_proj.weight": "model-00013-of-00023.safetensors",
201
+ "model.layers.26.mlp.up_proj.weight": "model-00013-of-00023.safetensors",
202
+ "model.layers.26.post_attention_layernorm.weight": "model-00013-of-00023.safetensors",
203
+ "model.layers.26.self_attn.k_proj.weight": "model-00013-of-00023.safetensors",
204
+ "model.layers.26.self_attn.o_proj.weight": "model-00013-of-00023.safetensors",
205
+ "model.layers.26.self_attn.q_proj.weight": "model-00013-of-00023.safetensors",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "model-00013-of-00023.safetensors",
207
+ "model.layers.26.self_attn.v_proj.weight": "model-00013-of-00023.safetensors",
208
+ "model.layers.27.input_layernorm.weight": "model-00013-of-00023.safetensors",
209
+ "model.layers.27.mlp.down_proj.weight": "model-00013-of-00023.safetensors",
210
+ "model.layers.27.mlp.gate_proj.weight": "model-00013-of-00023.safetensors",
211
+ "model.layers.27.mlp.up_proj.weight": "model-00013-of-00023.safetensors",
212
+ "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00023.safetensors",
213
+ "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00023.safetensors",
214
+ "model.layers.27.self_attn.o_proj.weight": "model-00013-of-00023.safetensors",
215
+ "model.layers.27.self_attn.q_proj.weight": "model-00013-of-00023.safetensors",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "model-00013-of-00023.safetensors",
217
+ "model.layers.27.self_attn.v_proj.weight": "model-00013-of-00023.safetensors",
218
+ "model.layers.28.input_layernorm.weight": "model-00014-of-00023.safetensors",
219
+ "model.layers.28.mlp.down_proj.weight": "model-00014-of-00023.safetensors",
220
+ "model.layers.28.mlp.gate_proj.weight": "model-00014-of-00023.safetensors",
221
+ "model.layers.28.mlp.up_proj.weight": "model-00014-of-00023.safetensors",
222
+ "model.layers.28.post_attention_layernorm.weight": "model-00014-of-00023.safetensors",
223
+ "model.layers.28.self_attn.k_proj.weight": "model-00013-of-00023.safetensors",
224
+ "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00023.safetensors",
225
+ "model.layers.28.self_attn.q_proj.weight": "model-00013-of-00023.safetensors",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "model-00013-of-00023.safetensors",
227
+ "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00023.safetensors",
228
+ "model.layers.29.input_layernorm.weight": "model-00014-of-00023.safetensors",
229
+ "model.layers.29.mlp.down_proj.weight": "model-00014-of-00023.safetensors",
230
+ "model.layers.29.mlp.gate_proj.weight": "model-00014-of-00023.safetensors",
231
+ "model.layers.29.mlp.up_proj.weight": "model-00014-of-00023.safetensors",
232
+ "model.layers.29.post_attention_layernorm.weight": "model-00014-of-00023.safetensors",
233
+ "model.layers.29.self_attn.k_proj.weight": "model-00014-of-00023.safetensors",
234
+ "model.layers.29.self_attn.o_proj.weight": "model-00014-of-00023.safetensors",
235
+ "model.layers.29.self_attn.q_proj.weight": "model-00014-of-00023.safetensors",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "model-00014-of-00023.safetensors",
237
+ "model.layers.29.self_attn.v_proj.weight": "model-00014-of-00023.safetensors",
238
+ "model.layers.3.input_layernorm.weight": "model-00003-of-00023.safetensors",
239
+ "model.layers.3.mlp.down_proj.weight": "model-00003-of-00023.safetensors",
240
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00023.safetensors",
241
+ "model.layers.3.mlp.up_proj.weight": "model-00003-of-00023.safetensors",
242
+ "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00023.safetensors",
243
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00023.safetensors",
244
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00023.safetensors",
245
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00023.safetensors",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00002-of-00023.safetensors",
247
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00023.safetensors",
248
+ "model.layers.30.input_layernorm.weight": "model-00015-of-00023.safetensors",
249
+ "model.layers.30.mlp.down_proj.weight": "model-00015-of-00023.safetensors",
250
+ "model.layers.30.mlp.gate_proj.weight": "model-00014-of-00023.safetensors",
251
+ "model.layers.30.mlp.up_proj.weight": "model-00015-of-00023.safetensors",
252
+ "model.layers.30.post_attention_layernorm.weight": "model-00015-of-00023.safetensors",
253
+ "model.layers.30.self_attn.k_proj.weight": "model-00014-of-00023.safetensors",
254
+ "model.layers.30.self_attn.o_proj.weight": "model-00014-of-00023.safetensors",
255
+ "model.layers.30.self_attn.q_proj.weight": "model-00014-of-00023.safetensors",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "model-00014-of-00023.safetensors",
257
+ "model.layers.30.self_attn.v_proj.weight": "model-00014-of-00023.safetensors",
258
+ "model.layers.31.input_layernorm.weight": "model-00015-of-00023.safetensors",
259
+ "model.layers.31.mlp.down_proj.weight": "model-00015-of-00023.safetensors",
260
+ "model.layers.31.mlp.gate_proj.weight": "model-00015-of-00023.safetensors",
261
+ "model.layers.31.mlp.up_proj.weight": "model-00015-of-00023.safetensors",
262
+ "model.layers.31.post_attention_layernorm.weight": "model-00015-of-00023.safetensors",
263
+ "model.layers.31.self_attn.k_proj.weight": "model-00015-of-00023.safetensors",
264
+ "model.layers.31.self_attn.o_proj.weight": "model-00015-of-00023.safetensors",
265
+ "model.layers.31.self_attn.q_proj.weight": "model-00015-of-00023.safetensors",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "model-00015-of-00023.safetensors",
267
+ "model.layers.31.self_attn.v_proj.weight": "model-00015-of-00023.safetensors",
268
+ "model.layers.32.input_layernorm.weight": "model-00016-of-00023.safetensors",
269
+ "model.layers.32.mlp.down_proj.weight": "model-00016-of-00023.safetensors",
270
+ "model.layers.32.mlp.gate_proj.weight": "model-00015-of-00023.safetensors",
271
+ "model.layers.32.mlp.up_proj.weight": "model-00015-of-00023.safetensors",
272
+ "model.layers.32.post_attention_layernorm.weight": "model-00016-of-00023.safetensors",
273
+ "model.layers.32.self_attn.k_proj.weight": "model-00015-of-00023.safetensors",
274
+ "model.layers.32.self_attn.o_proj.weight": "model-00015-of-00023.safetensors",
275
+ "model.layers.32.self_attn.q_proj.weight": "model-00015-of-00023.safetensors",
276
+ "model.layers.32.self_attn.rotary_emb.inv_freq": "model-00015-of-00023.safetensors",
277
+ "model.layers.32.self_attn.v_proj.weight": "model-00015-of-00023.safetensors",
278
+ "model.layers.33.input_layernorm.weight": "model-00016-of-00023.safetensors",
279
+ "model.layers.33.mlp.down_proj.weight": "model-00016-of-00023.safetensors",
280
+ "model.layers.33.mlp.gate_proj.weight": "model-00016-of-00023.safetensors",
281
+ "model.layers.33.mlp.up_proj.weight": "model-00016-of-00023.safetensors",
282
+ "model.layers.33.post_attention_layernorm.weight": "model-00016-of-00023.safetensors",
283
+ "model.layers.33.self_attn.k_proj.weight": "model-00016-of-00023.safetensors",
284
+ "model.layers.33.self_attn.o_proj.weight": "model-00016-of-00023.safetensors",
285
+ "model.layers.33.self_attn.q_proj.weight": "model-00016-of-00023.safetensors",
286
+ "model.layers.33.self_attn.rotary_emb.inv_freq": "model-00016-of-00023.safetensors",
287
+ "model.layers.33.self_attn.v_proj.weight": "model-00016-of-00023.safetensors",
288
+ "model.layers.34.input_layernorm.weight": "model-00016-of-00023.safetensors",
289
+ "model.layers.34.mlp.down_proj.weight": "model-00016-of-00023.safetensors",
290
+ "model.layers.34.mlp.gate_proj.weight": "model-00016-of-00023.safetensors",
291
+ "model.layers.34.mlp.up_proj.weight": "model-00016-of-00023.safetensors",
292
+ "model.layers.34.post_attention_layernorm.weight": "model-00016-of-00023.safetensors",
293
+ "model.layers.34.self_attn.k_proj.weight": "model-00016-of-00023.safetensors",
294
+ "model.layers.34.self_attn.o_proj.weight": "model-00016-of-00023.safetensors",
295
+ "model.layers.34.self_attn.q_proj.weight": "model-00016-of-00023.safetensors",
296
+ "model.layers.34.self_attn.rotary_emb.inv_freq": "model-00016-of-00023.safetensors",
297
+ "model.layers.34.self_attn.v_proj.weight": "model-00016-of-00023.safetensors",
298
+ "model.layers.35.input_layernorm.weight": "model-00017-of-00023.safetensors",
299
+ "model.layers.35.mlp.down_proj.weight": "model-00017-of-00023.safetensors",
300
+ "model.layers.35.mlp.gate_proj.weight": "model-00017-of-00023.safetensors",
301
+ "model.layers.35.mlp.up_proj.weight": "model-00017-of-00023.safetensors",
302
+ "model.layers.35.post_attention_layernorm.weight": "model-00017-of-00023.safetensors",
303
+ "model.layers.35.self_attn.k_proj.weight": "model-00017-of-00023.safetensors",
304
+ "model.layers.35.self_attn.o_proj.weight": "model-00017-of-00023.safetensors",
305
+ "model.layers.35.self_attn.q_proj.weight": "model-00017-of-00023.safetensors",
306
+ "model.layers.35.self_attn.rotary_emb.inv_freq": "model-00017-of-00023.safetensors",
307
+ "model.layers.35.self_attn.v_proj.weight": "model-00017-of-00023.safetensors",
308
+ "model.layers.36.input_layernorm.weight": "model-00017-of-00023.safetensors",
309
+ "model.layers.36.mlp.down_proj.weight": "model-00017-of-00023.safetensors",
310
+ "model.layers.36.mlp.gate_proj.weight": "model-00017-of-00023.safetensors",
311
+ "model.layers.36.mlp.up_proj.weight": "model-00017-of-00023.safetensors",
312
+ "model.layers.36.post_attention_layernorm.weight": "model-00017-of-00023.safetensors",
313
+ "model.layers.36.self_attn.k_proj.weight": "model-00017-of-00023.safetensors",
314
+ "model.layers.36.self_attn.o_proj.weight": "model-00017-of-00023.safetensors",
315
+ "model.layers.36.self_attn.q_proj.weight": "model-00017-of-00023.safetensors",
316
+ "model.layers.36.self_attn.rotary_emb.inv_freq": "model-00017-of-00023.safetensors",
317
+ "model.layers.36.self_attn.v_proj.weight": "model-00017-of-00023.safetensors",
318
+ "model.layers.37.input_layernorm.weight": "model-00018-of-00023.safetensors",
319
+ "model.layers.37.mlp.down_proj.weight": "model-00018-of-00023.safetensors",
320
+ "model.layers.37.mlp.gate_proj.weight": "model-00018-of-00023.safetensors",
321
+ "model.layers.37.mlp.up_proj.weight": "model-00018-of-00023.safetensors",
322
+ "model.layers.37.post_attention_layernorm.weight": "model-00018-of-00023.safetensors",
323
+ "model.layers.37.self_attn.k_proj.weight": "model-00017-of-00023.safetensors",
324
+ "model.layers.37.self_attn.o_proj.weight": "model-00017-of-00023.safetensors",
325
+ "model.layers.37.self_attn.q_proj.weight": "model-00017-of-00023.safetensors",
326
+ "model.layers.37.self_attn.rotary_emb.inv_freq": "model-00017-of-00023.safetensors",
327
+ "model.layers.37.self_attn.v_proj.weight": "model-00017-of-00023.safetensors",
328
+ "model.layers.38.input_layernorm.weight": "model-00018-of-00023.safetensors",
329
+ "model.layers.38.mlp.down_proj.weight": "model-00018-of-00023.safetensors",
330
+ "model.layers.38.mlp.gate_proj.weight": "model-00018-of-00023.safetensors",
331
+ "model.layers.38.mlp.up_proj.weight": "model-00018-of-00023.safetensors",
332
+ "model.layers.38.post_attention_layernorm.weight": "model-00018-of-00023.safetensors",
333
+ "model.layers.38.self_attn.k_proj.weight": "model-00018-of-00023.safetensors",
334
+ "model.layers.38.self_attn.o_proj.weight": "model-00018-of-00023.safetensors",
335
+ "model.layers.38.self_attn.q_proj.weight": "model-00018-of-00023.safetensors",
336
+ "model.layers.38.self_attn.rotary_emb.inv_freq": "model-00018-of-00023.safetensors",
337
+ "model.layers.38.self_attn.v_proj.weight": "model-00018-of-00023.safetensors",
338
+ "model.layers.39.input_layernorm.weight": "model-00019-of-00023.safetensors",
339
+ "model.layers.39.mlp.down_proj.weight": "model-00019-of-00023.safetensors",
340
+ "model.layers.39.mlp.gate_proj.weight": "model-00018-of-00023.safetensors",
341
+ "model.layers.39.mlp.up_proj.weight": "model-00019-of-00023.safetensors",
342
+ "model.layers.39.post_attention_layernorm.weight": "model-00019-of-00023.safetensors",
343
+ "model.layers.39.self_attn.k_proj.weight": "model-00018-of-00023.safetensors",
344
+ "model.layers.39.self_attn.o_proj.weight": "model-00018-of-00023.safetensors",
345
+ "model.layers.39.self_attn.q_proj.weight": "model-00018-of-00023.safetensors",
346
+ "model.layers.39.self_attn.rotary_emb.inv_freq": "model-00018-of-00023.safetensors",
347
+ "model.layers.39.self_attn.v_proj.weight": "model-00018-of-00023.safetensors",
348
+ "model.layers.4.input_layernorm.weight": "model-00003-of-00023.safetensors",
349
+ "model.layers.4.mlp.down_proj.weight": "model-00003-of-00023.safetensors",
350
+ "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00023.safetensors",
351
+ "model.layers.4.mlp.up_proj.weight": "model-00003-of-00023.safetensors",
352
+ "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00023.safetensors",
353
+ "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00023.safetensors",
354
+ "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00023.safetensors",
355
+ "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00023.safetensors",
356
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00003-of-00023.safetensors",
357
+ "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00023.safetensors",
358
+ "model.layers.40.input_layernorm.weight": "model-00019-of-00023.safetensors",
359
+ "model.layers.40.mlp.down_proj.weight": "model-00019-of-00023.safetensors",
360
+ "model.layers.40.mlp.gate_proj.weight": "model-00019-of-00023.safetensors",
361
+ "model.layers.40.mlp.up_proj.weight": "model-00019-of-00023.safetensors",
362
+ "model.layers.40.post_attention_layernorm.weight": "model-00019-of-00023.safetensors",
363
+ "model.layers.40.self_attn.k_proj.weight": "model-00019-of-00023.safetensors",
364
+ "model.layers.40.self_attn.o_proj.weight": "model-00019-of-00023.safetensors",
365
+ "model.layers.40.self_attn.q_proj.weight": "model-00019-of-00023.safetensors",
366
+ "model.layers.40.self_attn.rotary_emb.inv_freq": "model-00019-of-00023.safetensors",
367
+ "model.layers.40.self_attn.v_proj.weight": "model-00019-of-00023.safetensors",
368
+ "model.layers.41.input_layernorm.weight": "model-00020-of-00023.safetensors",
369
+ "model.layers.41.mlp.down_proj.weight": "model-00020-of-00023.safetensors",
370
+ "model.layers.41.mlp.gate_proj.weight": "model-00019-of-00023.safetensors",
371
+ "model.layers.41.mlp.up_proj.weight": "model-00019-of-00023.safetensors",
372
+ "model.layers.41.post_attention_layernorm.weight": "model-00020-of-00023.safetensors",
373
+ "model.layers.41.self_attn.k_proj.weight": "model-00019-of-00023.safetensors",
374
+ "model.layers.41.self_attn.o_proj.weight": "model-00019-of-00023.safetensors",
375
+ "model.layers.41.self_attn.q_proj.weight": "model-00019-of-00023.safetensors",
376
+ "model.layers.41.self_attn.rotary_emb.inv_freq": "model-00019-of-00023.safetensors",
377
+ "model.layers.41.self_attn.v_proj.weight": "model-00019-of-00023.safetensors",
378
+ "model.layers.42.input_layernorm.weight": "model-00020-of-00023.safetensors",
379
+ "model.layers.42.mlp.down_proj.weight": "model-00020-of-00023.safetensors",
380
+ "model.layers.42.mlp.gate_proj.weight": "model-00020-of-00023.safetensors",
381
+ "model.layers.42.mlp.up_proj.weight": "model-00020-of-00023.safetensors",
382
+ "model.layers.42.post_attention_layernorm.weight": "model-00020-of-00023.safetensors",
383
+ "model.layers.42.self_attn.k_proj.weight": "model-00020-of-00023.safetensors",
384
+ "model.layers.42.self_attn.o_proj.weight": "model-00020-of-00023.safetensors",
385
+ "model.layers.42.self_attn.q_proj.weight": "model-00020-of-00023.safetensors",
386
+ "model.layers.42.self_attn.rotary_emb.inv_freq": "model-00020-of-00023.safetensors",
387
+ "model.layers.42.self_attn.v_proj.weight": "model-00020-of-00023.safetensors",
388
+ "model.layers.43.input_layernorm.weight": "model-00020-of-00023.safetensors",
389
+ "model.layers.43.mlp.down_proj.weight": "model-00020-of-00023.safetensors",
390
+ "model.layers.43.mlp.gate_proj.weight": "model-00020-of-00023.safetensors",
391
+ "model.layers.43.mlp.up_proj.weight": "model-00020-of-00023.safetensors",
392
+ "model.layers.43.post_attention_layernorm.weight": "model-00020-of-00023.safetensors",
393
+ "model.layers.43.self_attn.k_proj.weight": "model-00020-of-00023.safetensors",
394
+ "model.layers.43.self_attn.o_proj.weight": "model-00020-of-00023.safetensors",
395
+ "model.layers.43.self_attn.q_proj.weight": "model-00020-of-00023.safetensors",
396
+ "model.layers.43.self_attn.rotary_emb.inv_freq": "model-00020-of-00023.safetensors",
397
+ "model.layers.43.self_attn.v_proj.weight": "model-00020-of-00023.safetensors",
398
+ "model.layers.44.input_layernorm.weight": "model-00021-of-00023.safetensors",
399
+ "model.layers.44.mlp.down_proj.weight": "model-00021-of-00023.safetensors",
400
+ "model.layers.44.mlp.gate_proj.weight": "model-00021-of-00023.safetensors",
401
+ "model.layers.44.mlp.up_proj.weight": "model-00021-of-00023.safetensors",
402
+ "model.layers.44.post_attention_layernorm.weight": "model-00021-of-00023.safetensors",
403
+ "model.layers.44.self_attn.k_proj.weight": "model-00021-of-00023.safetensors",
404
+ "model.layers.44.self_attn.o_proj.weight": "model-00021-of-00023.safetensors",
405
+ "model.layers.44.self_attn.q_proj.weight": "model-00021-of-00023.safetensors",
406
+ "model.layers.44.self_attn.rotary_emb.inv_freq": "model-00021-of-00023.safetensors",
407
+ "model.layers.44.self_attn.v_proj.weight": "model-00021-of-00023.safetensors",
408
+ "model.layers.45.input_layernorm.weight": "model-00021-of-00023.safetensors",
409
+ "model.layers.45.mlp.down_proj.weight": "model-00021-of-00023.safetensors",
410
+ "model.layers.45.mlp.gate_proj.weight": "model-00021-of-00023.safetensors",
411
+ "model.layers.45.mlp.up_proj.weight": "model-00021-of-00023.safetensors",
412
+ "model.layers.45.post_attention_layernorm.weight": "model-00021-of-00023.safetensors",
413
+ "model.layers.45.self_attn.k_proj.weight": "model-00021-of-00023.safetensors",
414
+ "model.layers.45.self_attn.o_proj.weight": "model-00021-of-00023.safetensors",
415
+ "model.layers.45.self_attn.q_proj.weight": "model-00021-of-00023.safetensors",
416
+ "model.layers.45.self_attn.rotary_emb.inv_freq": "model-00021-of-00023.safetensors",
417
+ "model.layers.45.self_attn.v_proj.weight": "model-00021-of-00023.safetensors",
418
+ "model.layers.46.input_layernorm.weight": "model-00022-of-00023.safetensors",
419
+ "model.layers.46.mlp.down_proj.weight": "model-00022-of-00023.safetensors",
420
+ "model.layers.46.mlp.gate_proj.weight": "model-00022-of-00023.safetensors",
421
+ "model.layers.46.mlp.up_proj.weight": "model-00022-of-00023.safetensors",
422
+ "model.layers.46.post_attention_layernorm.weight": "model-00022-of-00023.safetensors",
423
+ "model.layers.46.self_attn.k_proj.weight": "model-00021-of-00023.safetensors",
424
+ "model.layers.46.self_attn.o_proj.weight": "model-00021-of-00023.safetensors",
425
+ "model.layers.46.self_attn.q_proj.weight": "model-00021-of-00023.safetensors",
426
+ "model.layers.46.self_attn.rotary_emb.inv_freq": "model-00021-of-00023.safetensors",
427
+ "model.layers.46.self_attn.v_proj.weight": "model-00021-of-00023.safetensors",
428
+ "model.layers.47.input_layernorm.weight": "model-00022-of-00023.safetensors",
429
+ "model.layers.47.mlp.down_proj.weight": "model-00022-of-00023.safetensors",
430
+ "model.layers.47.mlp.gate_proj.weight": "model-00022-of-00023.safetensors",
431
+ "model.layers.47.mlp.up_proj.weight": "model-00022-of-00023.safetensors",
432
+ "model.layers.47.post_attention_layernorm.weight": "model-00022-of-00023.safetensors",
433
+ "model.layers.47.self_attn.k_proj.weight": "model-00022-of-00023.safetensors",
434
+ "model.layers.47.self_attn.o_proj.weight": "model-00022-of-00023.safetensors",
435
+ "model.layers.47.self_attn.q_proj.weight": "model-00022-of-00023.safetensors",
436
+ "model.layers.47.self_attn.rotary_emb.inv_freq": "model-00022-of-00023.safetensors",
437
+ "model.layers.47.self_attn.v_proj.weight": "model-00022-of-00023.safetensors",
438
+ "model.layers.5.input_layernorm.weight": "model-00004-of-00023.safetensors",
439
+ "model.layers.5.mlp.down_proj.weight": "model-00004-of-00023.safetensors",
440
+ "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00023.safetensors",
441
+ "model.layers.5.mlp.up_proj.weight": "model-00003-of-00023.safetensors",
442
+ "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00023.safetensors",
443
+ "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00023.safetensors",
444
+ "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00023.safetensors",
445
+ "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00023.safetensors",
446
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00003-of-00023.safetensors",
447
+ "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00023.safetensors",
448
+ "model.layers.6.input_layernorm.weight": "model-00004-of-00023.safetensors",
449
+ "model.layers.6.mlp.down_proj.weight": "model-00004-of-00023.safetensors",
450
+ "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00023.safetensors",
451
+ "model.layers.6.mlp.up_proj.weight": "model-00004-of-00023.safetensors",
452
+ "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00023.safetensors",
453
+ "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00023.safetensors",
454
+ "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00023.safetensors",
455
+ "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00023.safetensors",
456
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00004-of-00023.safetensors",
457
+ "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00023.safetensors",
458
+ "model.layers.7.input_layernorm.weight": "model-00004-of-00023.safetensors",
459
+ "model.layers.7.mlp.down_proj.weight": "model-00004-of-00023.safetensors",
460
+ "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00023.safetensors",
461
+ "model.layers.7.mlp.up_proj.weight": "model-00004-of-00023.safetensors",
462
+ "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00023.safetensors",
463
+ "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00023.safetensors",
464
+ "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00023.safetensors",
465
+ "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00023.safetensors",
466
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00004-of-00023.safetensors",
467
+ "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00023.safetensors",
468
+ "model.layers.8.input_layernorm.weight": "model-00005-of-00023.safetensors",
469
+ "model.layers.8.mlp.down_proj.weight": "model-00005-of-00023.safetensors",
470
+ "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00023.safetensors",
471
+ "model.layers.8.mlp.up_proj.weight": "model-00005-of-00023.safetensors",
472
+ "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00023.safetensors",
473
+ "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00023.safetensors",
474
+ "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00023.safetensors",
475
+ "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00023.safetensors",
476
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00005-of-00023.safetensors",
477
+ "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00023.safetensors",
478
+ "model.layers.9.input_layernorm.weight": "model-00005-of-00023.safetensors",
479
+ "model.layers.9.mlp.down_proj.weight": "model-00005-of-00023.safetensors",
480
+ "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00023.safetensors",
481
+ "model.layers.9.mlp.up_proj.weight": "model-00005-of-00023.safetensors",
482
+ "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00023.safetensors",
483
+ "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00023.safetensors",
484
+ "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00023.safetensors",
485
+ "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00023.safetensors",
486
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00005-of-00023.safetensors",
487
+ "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00023.safetensors",
488
+ "model.norm.weight": "model-00022-of-00023.safetensors"
489
+ }
490
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff