beomi commited on
Commit
31cffe3
1 Parent(s): cc64905

Add ckpt with 76800 steps

Browse files
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "eos_token_id": 2,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 7168,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 20480,
11
+ "max_position_embeddings": 2048,
12
+ "model_type": "llama",
13
+ "num_attention_heads": 56,
14
+ "num_hidden_layers": 60,
15
+ "num_key_value_heads": 8,
16
+ "pad_token_id": 2,
17
+ "pretraining_tp": 1,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_scaling": null,
20
+ "rope_theta": 10000.0,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.33.1",
24
+ "use_cache": true,
25
+ "vocab_size": 78464
26
+ }
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": 2,
6
+ "transformers_version": "4.33.1"
7
+ }
model-00001-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1945c1b426f49203d814d9c5ee9c42483066dd1d884988eee846dcb76d74442a
3
+ size 2769057512
model-00002-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e27bc00577fc17b868f17471a31c207a67d26b49620975b435f5ca3099bada48
3
+ size 2950781792
model-00003-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13b1f6827fee0f1b8184d1de1ef579b92c1dbc852f6d6f5f48c665eee7c544c9
3
+ size 2921392520
model-00004-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05c419155c1b520ee63360cfe5568ce7ca4ce1b2c7680a26bd3b3758ef7ca5d9
3
+ size 2759940960
model-00005-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb6246908ae797a6b9a7b7d21633d55a9501cabf0c09088289ae6c61c1b202eb
3
+ size 2818631968
model-00006-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b407de4d9dee95574fcf24082d8c7ecae75210c1280a84757352820d317a87ef
3
+ size 2759940984
model-00007-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3be1faec7730ba23ccfff43f4878578f5a45510ada2b6854c144fe973055b95d
3
+ size 2818631976
model-00008-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d80f311eb946e7e4b5ce5d03b9a0358ec21fa9e8470f192588a15b44e01117e
3
+ size 2759940984
model-00009-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70e214943ed9e2274df4a5c0388f51674986f0077aa2838da2f8fe596290bc16
3
+ size 2818631976
model-00010-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:808ec7a58de8c116d1db141de1231e1e2bbed8baf9860122000ba8430e1b2c82
3
+ size 2759940984
model-00011-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d163d17ec72da8edfd68603cdb43e7bd63ded9101ab8d08334b18a2ef3061a91
3
+ size 2818631976
model-00012-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:925156fb45b9a7db976d8064abcc6f31db24f71db91dd9e646733e12960fb1b5
3
+ size 2759940984
model-00013-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da1d189a6eecfa651c51668f0d6736c8b43f425b7601e1076f18796c6c68089b
3
+ size 2818631976
model-00014-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc88c5c72e98c59d98344bd869b15badd2eec20c2ee431f91faff6168b367cfa
3
+ size 2759940984
model-00015-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fec055fbe8e4f9867be1679c363f2be1295bd76a2ada5bcec679003d73e0d801
3
+ size 2818631976
model-00016-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9914f703ef10680bf3c0d024f91a43a8031a473cb96be234adedfe9f5c03dbd
3
+ size 2759940984
model-00017-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57716cd2cd59c768deb68bf37883c398bb81c2be1b3a4c49233346279e6bfb54
3
+ size 2818631976
model-00018-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44547d91ba51c4f36693ccc09f14dacdc494f71b449819a09feb46e98b86b045
3
+ size 2759940984
model-00019-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93f65ad7014514ab2ff6270aa7f3974c4b0bd6c89412e669c3258b85689ddae5
3
+ size 2818631976
model-00020-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:053e05d50e671859fd6401fead129e0e81715e6cb41fecd7109ac40cbbdadf47
3
+ size 2759940984
model-00021-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2aaf9fd58edf4be649b7fc72e6f4b067307993aa58bc4178170cae568df101de
3
+ size 2818631976
model-00022-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20d18d7224977580cedcf7270e7d291e1cf3c76c2597a647196e692c15126dfd
3
+ size 2759940984
model-00023-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7c5df1e65e2570274d572c7426315461efa30026eb0c07e87db0e1422c454c4
3
+ size 2818631976
model-00024-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:053ae68d59a6b8ae4efca9f5629456c2e9e09e241c4042549ecf1f05b02cd01d
3
+ size 2759940984
model-00025-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9082862881fb0382e5ba3115794e6f749aa557a79ffb63405d6f42e5facc6427
3
+ size 2005707552
model.safetensors.index.json ADDED
@@ -0,0 +1,550 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 69192546304
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00025-of-00025.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00025.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00025.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00025.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00025.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00025.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00025.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00025.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00025.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00025.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00025.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00002-of-00025.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00002-of-00025.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00025.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00002-of-00025.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00025.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00025.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00025.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00025.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00025.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00005-of-00025.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00005-of-00025.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00025.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00005-of-00025.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00025.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00025.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00025.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00025.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00025.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00006-of-00025.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00006-of-00025.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00025.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00005-of-00025.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00025.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00025.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00025.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00025.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00025.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00006-of-00025.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00006-of-00025.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00025.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00006-of-00025.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00025.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00025.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00025.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00025.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00025.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00006-of-00025.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00006-of-00025.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00025.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00006-of-00025.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00025.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00025.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00025.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00025.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00025.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00007-of-00025.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00007-of-00025.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00025.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00007-of-00025.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00025.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00025.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00025.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00025.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00025.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00007-of-00025.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00007-of-00025.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00025.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00007-of-00025.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00025.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00025.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00025.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00025.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00025.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00008-of-00025.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00008-of-00025.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00025.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00007-of-00025.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00025.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00025.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00025.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00025.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00025.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00008-of-00025.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00008-of-00025.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00025.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00008-of-00025.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00025.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00025.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00025.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00025.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00025.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00008-of-00025.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00008-of-00025.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00025.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00008-of-00025.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00025.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00025.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00025.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00025.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00025.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00009-of-00025.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00009-of-00025.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00025.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00009-of-00025.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00025.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00025.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00025.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00025.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00025.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00025.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00002-of-00025.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00025.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00002-of-00025.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00025.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00025.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00025.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00025.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00025.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00009-of-00025.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00009-of-00025.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00009-of-00025.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00009-of-00025.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00025.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00025.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00025.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00025.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00025.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00010-of-00025.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00010-of-00025.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00025.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00009-of-00025.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00025.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00025.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00025.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00025.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00025.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00010-of-00025.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00010-of-00025.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00010-of-00025.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00010-of-00025.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00025.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00025.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00025.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00025.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00025.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00010-of-00025.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00010-of-00025.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00010-of-00025.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00010-of-00025.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00025.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00025.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00025.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00025.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00025.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00011-of-00025.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00011-of-00025.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00011-of-00025.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00011-of-00025.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00025.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00025.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00025.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00025.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00025.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00011-of-00025.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00011-of-00025.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00011-of-00025.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00011-of-00025.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00011-of-00025.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00011-of-00025.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00011-of-00025.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00011-of-00025.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00011-of-00025.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00012-of-00025.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00012-of-00025.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00011-of-00025.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00011-of-00025.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00025.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00011-of-00025.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00025.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00011-of-00025.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00011-of-00025.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00012-of-00025.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00012-of-00025.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00012-of-00025.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00012-of-00025.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00012-of-00025.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00012-of-00025.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00012-of-00025.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00012-of-00025.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00025.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00012-of-00025.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00012-of-00025.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00012-of-00025.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00012-of-00025.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00012-of-00025.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00012-of-00025.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00012-of-00025.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00012-of-00025.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00012-of-00025.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00013-of-00025.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00013-of-00025.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00013-of-00025.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00013-of-00025.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00013-of-00025.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00012-of-00025.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00012-of-00025.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00012-of-00025.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00012-of-00025.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00025.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00025.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00025.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00025.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00025.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00025.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00025.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00025.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00025.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00013-of-00025.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00013-of-00025.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00013-of-00025.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00013-of-00025.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00013-of-00025.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00013-of-00025.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00013-of-00025.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00013-of-00025.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00013-of-00025.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00014-of-00025.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00014-of-00025.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00013-of-00025.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00013-of-00025.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00014-of-00025.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00013-of-00025.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00025.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00025.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00025.safetensors",
242
+ "model.layers.32.input_layernorm.weight": "model-00014-of-00025.safetensors",
243
+ "model.layers.32.mlp.down_proj.weight": "model-00014-of-00025.safetensors",
244
+ "model.layers.32.mlp.gate_proj.weight": "model-00014-of-00025.safetensors",
245
+ "model.layers.32.mlp.up_proj.weight": "model-00014-of-00025.safetensors",
246
+ "model.layers.32.post_attention_layernorm.weight": "model-00014-of-00025.safetensors",
247
+ "model.layers.32.self_attn.k_proj.weight": "model-00014-of-00025.safetensors",
248
+ "model.layers.32.self_attn.o_proj.weight": "model-00014-of-00025.safetensors",
249
+ "model.layers.32.self_attn.q_proj.weight": "model-00014-of-00025.safetensors",
250
+ "model.layers.32.self_attn.v_proj.weight": "model-00014-of-00025.safetensors",
251
+ "model.layers.33.input_layernorm.weight": "model-00014-of-00025.safetensors",
252
+ "model.layers.33.mlp.down_proj.weight": "model-00014-of-00025.safetensors",
253
+ "model.layers.33.mlp.gate_proj.weight": "model-00014-of-00025.safetensors",
254
+ "model.layers.33.mlp.up_proj.weight": "model-00014-of-00025.safetensors",
255
+ "model.layers.33.post_attention_layernorm.weight": "model-00014-of-00025.safetensors",
256
+ "model.layers.33.self_attn.k_proj.weight": "model-00014-of-00025.safetensors",
257
+ "model.layers.33.self_attn.o_proj.weight": "model-00014-of-00025.safetensors",
258
+ "model.layers.33.self_attn.q_proj.weight": "model-00014-of-00025.safetensors",
259
+ "model.layers.33.self_attn.v_proj.weight": "model-00014-of-00025.safetensors",
260
+ "model.layers.34.input_layernorm.weight": "model-00015-of-00025.safetensors",
261
+ "model.layers.34.mlp.down_proj.weight": "model-00015-of-00025.safetensors",
262
+ "model.layers.34.mlp.gate_proj.weight": "model-00015-of-00025.safetensors",
263
+ "model.layers.34.mlp.up_proj.weight": "model-00015-of-00025.safetensors",
264
+ "model.layers.34.post_attention_layernorm.weight": "model-00015-of-00025.safetensors",
265
+ "model.layers.34.self_attn.k_proj.weight": "model-00014-of-00025.safetensors",
266
+ "model.layers.34.self_attn.o_proj.weight": "model-00014-of-00025.safetensors",
267
+ "model.layers.34.self_attn.q_proj.weight": "model-00014-of-00025.safetensors",
268
+ "model.layers.34.self_attn.v_proj.weight": "model-00014-of-00025.safetensors",
269
+ "model.layers.35.input_layernorm.weight": "model-00015-of-00025.safetensors",
270
+ "model.layers.35.mlp.down_proj.weight": "model-00015-of-00025.safetensors",
271
+ "model.layers.35.mlp.gate_proj.weight": "model-00015-of-00025.safetensors",
272
+ "model.layers.35.mlp.up_proj.weight": "model-00015-of-00025.safetensors",
273
+ "model.layers.35.post_attention_layernorm.weight": "model-00015-of-00025.safetensors",
274
+ "model.layers.35.self_attn.k_proj.weight": "model-00015-of-00025.safetensors",
275
+ "model.layers.35.self_attn.o_proj.weight": "model-00015-of-00025.safetensors",
276
+ "model.layers.35.self_attn.q_proj.weight": "model-00015-of-00025.safetensors",
277
+ "model.layers.35.self_attn.v_proj.weight": "model-00015-of-00025.safetensors",
278
+ "model.layers.36.input_layernorm.weight": "model-00016-of-00025.safetensors",
279
+ "model.layers.36.mlp.down_proj.weight": "model-00016-of-00025.safetensors",
280
+ "model.layers.36.mlp.gate_proj.weight": "model-00015-of-00025.safetensors",
281
+ "model.layers.36.mlp.up_proj.weight": "model-00015-of-00025.safetensors",
282
+ "model.layers.36.post_attention_layernorm.weight": "model-00016-of-00025.safetensors",
283
+ "model.layers.36.self_attn.k_proj.weight": "model-00015-of-00025.safetensors",
284
+ "model.layers.36.self_attn.o_proj.weight": "model-00015-of-00025.safetensors",
285
+ "model.layers.36.self_attn.q_proj.weight": "model-00015-of-00025.safetensors",
286
+ "model.layers.36.self_attn.v_proj.weight": "model-00015-of-00025.safetensors",
287
+ "model.layers.37.input_layernorm.weight": "model-00016-of-00025.safetensors",
288
+ "model.layers.37.mlp.down_proj.weight": "model-00016-of-00025.safetensors",
289
+ "model.layers.37.mlp.gate_proj.weight": "model-00016-of-00025.safetensors",
290
+ "model.layers.37.mlp.up_proj.weight": "model-00016-of-00025.safetensors",
291
+ "model.layers.37.post_attention_layernorm.weight": "model-00016-of-00025.safetensors",
292
+ "model.layers.37.self_attn.k_proj.weight": "model-00016-of-00025.safetensors",
293
+ "model.layers.37.self_attn.o_proj.weight": "model-00016-of-00025.safetensors",
294
+ "model.layers.37.self_attn.q_proj.weight": "model-00016-of-00025.safetensors",
295
+ "model.layers.37.self_attn.v_proj.weight": "model-00016-of-00025.safetensors",
296
+ "model.layers.38.input_layernorm.weight": "model-00016-of-00025.safetensors",
297
+ "model.layers.38.mlp.down_proj.weight": "model-00016-of-00025.safetensors",
298
+ "model.layers.38.mlp.gate_proj.weight": "model-00016-of-00025.safetensors",
299
+ "model.layers.38.mlp.up_proj.weight": "model-00016-of-00025.safetensors",
300
+ "model.layers.38.post_attention_layernorm.weight": "model-00016-of-00025.safetensors",
301
+ "model.layers.38.self_attn.k_proj.weight": "model-00016-of-00025.safetensors",
302
+ "model.layers.38.self_attn.o_proj.weight": "model-00016-of-00025.safetensors",
303
+ "model.layers.38.self_attn.q_proj.weight": "model-00016-of-00025.safetensors",
304
+ "model.layers.38.self_attn.v_proj.weight": "model-00016-of-00025.safetensors",
305
+ "model.layers.39.input_layernorm.weight": "model-00017-of-00025.safetensors",
306
+ "model.layers.39.mlp.down_proj.weight": "model-00017-of-00025.safetensors",
307
+ "model.layers.39.mlp.gate_proj.weight": "model-00017-of-00025.safetensors",
308
+ "model.layers.39.mlp.up_proj.weight": "model-00017-of-00025.safetensors",
309
+ "model.layers.39.post_attention_layernorm.weight": "model-00017-of-00025.safetensors",
310
+ "model.layers.39.self_attn.k_proj.weight": "model-00016-of-00025.safetensors",
311
+ "model.layers.39.self_attn.o_proj.weight": "model-00016-of-00025.safetensors",
312
+ "model.layers.39.self_attn.q_proj.weight": "model-00016-of-00025.safetensors",
313
+ "model.layers.39.self_attn.v_proj.weight": "model-00016-of-00025.safetensors",
314
+ "model.layers.4.input_layernorm.weight": "model-00003-of-00025.safetensors",
315
+ "model.layers.4.mlp.down_proj.weight": "model-00003-of-00025.safetensors",
316
+ "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00025.safetensors",
317
+ "model.layers.4.mlp.up_proj.weight": "model-00003-of-00025.safetensors",
318
+ "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00025.safetensors",
319
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00025.safetensors",
320
+ "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00025.safetensors",
321
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00025.safetensors",
322
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00025.safetensors",
323
+ "model.layers.40.input_layernorm.weight": "model-00017-of-00025.safetensors",
324
+ "model.layers.40.mlp.down_proj.weight": "model-00017-of-00025.safetensors",
325
+ "model.layers.40.mlp.gate_proj.weight": "model-00017-of-00025.safetensors",
326
+ "model.layers.40.mlp.up_proj.weight": "model-00017-of-00025.safetensors",
327
+ "model.layers.40.post_attention_layernorm.weight": "model-00017-of-00025.safetensors",
328
+ "model.layers.40.self_attn.k_proj.weight": "model-00017-of-00025.safetensors",
329
+ "model.layers.40.self_attn.o_proj.weight": "model-00017-of-00025.safetensors",
330
+ "model.layers.40.self_attn.q_proj.weight": "model-00017-of-00025.safetensors",
331
+ "model.layers.40.self_attn.v_proj.weight": "model-00017-of-00025.safetensors",
332
+ "model.layers.41.input_layernorm.weight": "model-00018-of-00025.safetensors",
333
+ "model.layers.41.mlp.down_proj.weight": "model-00018-of-00025.safetensors",
334
+ "model.layers.41.mlp.gate_proj.weight": "model-00017-of-00025.safetensors",
335
+ "model.layers.41.mlp.up_proj.weight": "model-00017-of-00025.safetensors",
336
+ "model.layers.41.post_attention_layernorm.weight": "model-00018-of-00025.safetensors",
337
+ "model.layers.41.self_attn.k_proj.weight": "model-00017-of-00025.safetensors",
338
+ "model.layers.41.self_attn.o_proj.weight": "model-00017-of-00025.safetensors",
339
+ "model.layers.41.self_attn.q_proj.weight": "model-00017-of-00025.safetensors",
340
+ "model.layers.41.self_attn.v_proj.weight": "model-00017-of-00025.safetensors",
341
+ "model.layers.42.input_layernorm.weight": "model-00018-of-00025.safetensors",
342
+ "model.layers.42.mlp.down_proj.weight": "model-00018-of-00025.safetensors",
343
+ "model.layers.42.mlp.gate_proj.weight": "model-00018-of-00025.safetensors",
344
+ "model.layers.42.mlp.up_proj.weight": "model-00018-of-00025.safetensors",
345
+ "model.layers.42.post_attention_layernorm.weight": "model-00018-of-00025.safetensors",
346
+ "model.layers.42.self_attn.k_proj.weight": "model-00018-of-00025.safetensors",
347
+ "model.layers.42.self_attn.o_proj.weight": "model-00018-of-00025.safetensors",
348
+ "model.layers.42.self_attn.q_proj.weight": "model-00018-of-00025.safetensors",
349
+ "model.layers.42.self_attn.v_proj.weight": "model-00018-of-00025.safetensors",
350
+ "model.layers.43.input_layernorm.weight": "model-00018-of-00025.safetensors",
351
+ "model.layers.43.mlp.down_proj.weight": "model-00018-of-00025.safetensors",
352
+ "model.layers.43.mlp.gate_proj.weight": "model-00018-of-00025.safetensors",
353
+ "model.layers.43.mlp.up_proj.weight": "model-00018-of-00025.safetensors",
354
+ "model.layers.43.post_attention_layernorm.weight": "model-00018-of-00025.safetensors",
355
+ "model.layers.43.self_attn.k_proj.weight": "model-00018-of-00025.safetensors",
356
+ "model.layers.43.self_attn.o_proj.weight": "model-00018-of-00025.safetensors",
357
+ "model.layers.43.self_attn.q_proj.weight": "model-00018-of-00025.safetensors",
358
+ "model.layers.43.self_attn.v_proj.weight": "model-00018-of-00025.safetensors",
359
+ "model.layers.44.input_layernorm.weight": "model-00019-of-00025.safetensors",
360
+ "model.layers.44.mlp.down_proj.weight": "model-00019-of-00025.safetensors",
361
+ "model.layers.44.mlp.gate_proj.weight": "model-00019-of-00025.safetensors",
362
+ "model.layers.44.mlp.up_proj.weight": "model-00019-of-00025.safetensors",
363
+ "model.layers.44.post_attention_layernorm.weight": "model-00019-of-00025.safetensors",
364
+ "model.layers.44.self_attn.k_proj.weight": "model-00018-of-00025.safetensors",
365
+ "model.layers.44.self_attn.o_proj.weight": "model-00018-of-00025.safetensors",
366
+ "model.layers.44.self_attn.q_proj.weight": "model-00018-of-00025.safetensors",
367
+ "model.layers.44.self_attn.v_proj.weight": "model-00018-of-00025.safetensors",
368
+ "model.layers.45.input_layernorm.weight": "model-00019-of-00025.safetensors",
369
+ "model.layers.45.mlp.down_proj.weight": "model-00019-of-00025.safetensors",
370
+ "model.layers.45.mlp.gate_proj.weight": "model-00019-of-00025.safetensors",
371
+ "model.layers.45.mlp.up_proj.weight": "model-00019-of-00025.safetensors",
372
+ "model.layers.45.post_attention_layernorm.weight": "model-00019-of-00025.safetensors",
373
+ "model.layers.45.self_attn.k_proj.weight": "model-00019-of-00025.safetensors",
374
+ "model.layers.45.self_attn.o_proj.weight": "model-00019-of-00025.safetensors",
375
+ "model.layers.45.self_attn.q_proj.weight": "model-00019-of-00025.safetensors",
376
+ "model.layers.45.self_attn.v_proj.weight": "model-00019-of-00025.safetensors",
377
+ "model.layers.46.input_layernorm.weight": "model-00020-of-00025.safetensors",
378
+ "model.layers.46.mlp.down_proj.weight": "model-00020-of-00025.safetensors",
379
+ "model.layers.46.mlp.gate_proj.weight": "model-00019-of-00025.safetensors",
380
+ "model.layers.46.mlp.up_proj.weight": "model-00019-of-00025.safetensors",
381
+ "model.layers.46.post_attention_layernorm.weight": "model-00020-of-00025.safetensors",
382
+ "model.layers.46.self_attn.k_proj.weight": "model-00019-of-00025.safetensors",
383
+ "model.layers.46.self_attn.o_proj.weight": "model-00019-of-00025.safetensors",
384
+ "model.layers.46.self_attn.q_proj.weight": "model-00019-of-00025.safetensors",
385
+ "model.layers.46.self_attn.v_proj.weight": "model-00019-of-00025.safetensors",
386
+ "model.layers.47.input_layernorm.weight": "model-00020-of-00025.safetensors",
387
+ "model.layers.47.mlp.down_proj.weight": "model-00020-of-00025.safetensors",
388
+ "model.layers.47.mlp.gate_proj.weight": "model-00020-of-00025.safetensors",
389
+ "model.layers.47.mlp.up_proj.weight": "model-00020-of-00025.safetensors",
390
+ "model.layers.47.post_attention_layernorm.weight": "model-00020-of-00025.safetensors",
391
+ "model.layers.47.self_attn.k_proj.weight": "model-00020-of-00025.safetensors",
392
+ "model.layers.47.self_attn.o_proj.weight": "model-00020-of-00025.safetensors",
393
+ "model.layers.47.self_attn.q_proj.weight": "model-00020-of-00025.safetensors",
394
+ "model.layers.47.self_attn.v_proj.weight": "model-00020-of-00025.safetensors",
395
+ "model.layers.48.input_layernorm.weight": "model-00020-of-00025.safetensors",
396
+ "model.layers.48.mlp.down_proj.weight": "model-00020-of-00025.safetensors",
397
+ "model.layers.48.mlp.gate_proj.weight": "model-00020-of-00025.safetensors",
398
+ "model.layers.48.mlp.up_proj.weight": "model-00020-of-00025.safetensors",
399
+ "model.layers.48.post_attention_layernorm.weight": "model-00020-of-00025.safetensors",
400
+ "model.layers.48.self_attn.k_proj.weight": "model-00020-of-00025.safetensors",
401
+ "model.layers.48.self_attn.o_proj.weight": "model-00020-of-00025.safetensors",
402
+ "model.layers.48.self_attn.q_proj.weight": "model-00020-of-00025.safetensors",
403
+ "model.layers.48.self_attn.v_proj.weight": "model-00020-of-00025.safetensors",
404
+ "model.layers.49.input_layernorm.weight": "model-00021-of-00025.safetensors",
405
+ "model.layers.49.mlp.down_proj.weight": "model-00021-of-00025.safetensors",
406
+ "model.layers.49.mlp.gate_proj.weight": "model-00021-of-00025.safetensors",
407
+ "model.layers.49.mlp.up_proj.weight": "model-00021-of-00025.safetensors",
408
+ "model.layers.49.post_attention_layernorm.weight": "model-00021-of-00025.safetensors",
409
+ "model.layers.49.self_attn.k_proj.weight": "model-00020-of-00025.safetensors",
410
+ "model.layers.49.self_attn.o_proj.weight": "model-00020-of-00025.safetensors",
411
+ "model.layers.49.self_attn.q_proj.weight": "model-00020-of-00025.safetensors",
412
+ "model.layers.49.self_attn.v_proj.weight": "model-00020-of-00025.safetensors",
413
+ "model.layers.5.input_layernorm.weight": "model-00003-of-00025.safetensors",
414
+ "model.layers.5.mlp.down_proj.weight": "model-00003-of-00025.safetensors",
415
+ "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00025.safetensors",
416
+ "model.layers.5.mlp.up_proj.weight": "model-00003-of-00025.safetensors",
417
+ "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00025.safetensors",
418
+ "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00025.safetensors",
419
+ "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00025.safetensors",
420
+ "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00025.safetensors",
421
+ "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00025.safetensors",
422
+ "model.layers.50.input_layernorm.weight": "model-00021-of-00025.safetensors",
423
+ "model.layers.50.mlp.down_proj.weight": "model-00021-of-00025.safetensors",
424
+ "model.layers.50.mlp.gate_proj.weight": "model-00021-of-00025.safetensors",
425
+ "model.layers.50.mlp.up_proj.weight": "model-00021-of-00025.safetensors",
426
+ "model.layers.50.post_attention_layernorm.weight": "model-00021-of-00025.safetensors",
427
+ "model.layers.50.self_attn.k_proj.weight": "model-00021-of-00025.safetensors",
428
+ "model.layers.50.self_attn.o_proj.weight": "model-00021-of-00025.safetensors",
429
+ "model.layers.50.self_attn.q_proj.weight": "model-00021-of-00025.safetensors",
430
+ "model.layers.50.self_attn.v_proj.weight": "model-00021-of-00025.safetensors",
431
+ "model.layers.51.input_layernorm.weight": "model-00022-of-00025.safetensors",
432
+ "model.layers.51.mlp.down_proj.weight": "model-00022-of-00025.safetensors",
433
+ "model.layers.51.mlp.gate_proj.weight": "model-00021-of-00025.safetensors",
434
+ "model.layers.51.mlp.up_proj.weight": "model-00021-of-00025.safetensors",
435
+ "model.layers.51.post_attention_layernorm.weight": "model-00022-of-00025.safetensors",
436
+ "model.layers.51.self_attn.k_proj.weight": "model-00021-of-00025.safetensors",
437
+ "model.layers.51.self_attn.o_proj.weight": "model-00021-of-00025.safetensors",
438
+ "model.layers.51.self_attn.q_proj.weight": "model-00021-of-00025.safetensors",
439
+ "model.layers.51.self_attn.v_proj.weight": "model-00021-of-00025.safetensors",
440
+ "model.layers.52.input_layernorm.weight": "model-00022-of-00025.safetensors",
441
+ "model.layers.52.mlp.down_proj.weight": "model-00022-of-00025.safetensors",
442
+ "model.layers.52.mlp.gate_proj.weight": "model-00022-of-00025.safetensors",
443
+ "model.layers.52.mlp.up_proj.weight": "model-00022-of-00025.safetensors",
444
+ "model.layers.52.post_attention_layernorm.weight": "model-00022-of-00025.safetensors",
445
+ "model.layers.52.self_attn.k_proj.weight": "model-00022-of-00025.safetensors",
446
+ "model.layers.52.self_attn.o_proj.weight": "model-00022-of-00025.safetensors",
447
+ "model.layers.52.self_attn.q_proj.weight": "model-00022-of-00025.safetensors",
448
+ "model.layers.52.self_attn.v_proj.weight": "model-00022-of-00025.safetensors",
449
+ "model.layers.53.input_layernorm.weight": "model-00022-of-00025.safetensors",
450
+ "model.layers.53.mlp.down_proj.weight": "model-00022-of-00025.safetensors",
451
+ "model.layers.53.mlp.gate_proj.weight": "model-00022-of-00025.safetensors",
452
+ "model.layers.53.mlp.up_proj.weight": "model-00022-of-00025.safetensors",
453
+ "model.layers.53.post_attention_layernorm.weight": "model-00022-of-00025.safetensors",
454
+ "model.layers.53.self_attn.k_proj.weight": "model-00022-of-00025.safetensors",
455
+ "model.layers.53.self_attn.o_proj.weight": "model-00022-of-00025.safetensors",
456
+ "model.layers.53.self_attn.q_proj.weight": "model-00022-of-00025.safetensors",
457
+ "model.layers.53.self_attn.v_proj.weight": "model-00022-of-00025.safetensors",
458
+ "model.layers.54.input_layernorm.weight": "model-00023-of-00025.safetensors",
459
+ "model.layers.54.mlp.down_proj.weight": "model-00023-of-00025.safetensors",
460
+ "model.layers.54.mlp.gate_proj.weight": "model-00023-of-00025.safetensors",
461
+ "model.layers.54.mlp.up_proj.weight": "model-00023-of-00025.safetensors",
462
+ "model.layers.54.post_attention_layernorm.weight": "model-00023-of-00025.safetensors",
463
+ "model.layers.54.self_attn.k_proj.weight": "model-00022-of-00025.safetensors",
464
+ "model.layers.54.self_attn.o_proj.weight": "model-00022-of-00025.safetensors",
465
+ "model.layers.54.self_attn.q_proj.weight": "model-00022-of-00025.safetensors",
466
+ "model.layers.54.self_attn.v_proj.weight": "model-00022-of-00025.safetensors",
467
+ "model.layers.55.input_layernorm.weight": "model-00023-of-00025.safetensors",
468
+ "model.layers.55.mlp.down_proj.weight": "model-00023-of-00025.safetensors",
469
+ "model.layers.55.mlp.gate_proj.weight": "model-00023-of-00025.safetensors",
470
+ "model.layers.55.mlp.up_proj.weight": "model-00023-of-00025.safetensors",
471
+ "model.layers.55.post_attention_layernorm.weight": "model-00023-of-00025.safetensors",
472
+ "model.layers.55.self_attn.k_proj.weight": "model-00023-of-00025.safetensors",
473
+ "model.layers.55.self_attn.o_proj.weight": "model-00023-of-00025.safetensors",
474
+ "model.layers.55.self_attn.q_proj.weight": "model-00023-of-00025.safetensors",
475
+ "model.layers.55.self_attn.v_proj.weight": "model-00023-of-00025.safetensors",
476
+ "model.layers.56.input_layernorm.weight": "model-00024-of-00025.safetensors",
477
+ "model.layers.56.mlp.down_proj.weight": "model-00024-of-00025.safetensors",
478
+ "model.layers.56.mlp.gate_proj.weight": "model-00023-of-00025.safetensors",
479
+ "model.layers.56.mlp.up_proj.weight": "model-00023-of-00025.safetensors",
480
+ "model.layers.56.post_attention_layernorm.weight": "model-00024-of-00025.safetensors",
481
+ "model.layers.56.self_attn.k_proj.weight": "model-00023-of-00025.safetensors",
482
+ "model.layers.56.self_attn.o_proj.weight": "model-00023-of-00025.safetensors",
483
+ "model.layers.56.self_attn.q_proj.weight": "model-00023-of-00025.safetensors",
484
+ "model.layers.56.self_attn.v_proj.weight": "model-00023-of-00025.safetensors",
485
+ "model.layers.57.input_layernorm.weight": "model-00024-of-00025.safetensors",
486
+ "model.layers.57.mlp.down_proj.weight": "model-00024-of-00025.safetensors",
487
+ "model.layers.57.mlp.gate_proj.weight": "model-00024-of-00025.safetensors",
488
+ "model.layers.57.mlp.up_proj.weight": "model-00024-of-00025.safetensors",
489
+ "model.layers.57.post_attention_layernorm.weight": "model-00024-of-00025.safetensors",
490
+ "model.layers.57.self_attn.k_proj.weight": "model-00024-of-00025.safetensors",
491
+ "model.layers.57.self_attn.o_proj.weight": "model-00024-of-00025.safetensors",
492
+ "model.layers.57.self_attn.q_proj.weight": "model-00024-of-00025.safetensors",
493
+ "model.layers.57.self_attn.v_proj.weight": "model-00024-of-00025.safetensors",
494
+ "model.layers.58.input_layernorm.weight": "model-00024-of-00025.safetensors",
495
+ "model.layers.58.mlp.down_proj.weight": "model-00024-of-00025.safetensors",
496
+ "model.layers.58.mlp.gate_proj.weight": "model-00024-of-00025.safetensors",
497
+ "model.layers.58.mlp.up_proj.weight": "model-00024-of-00025.safetensors",
498
+ "model.layers.58.post_attention_layernorm.weight": "model-00024-of-00025.safetensors",
499
+ "model.layers.58.self_attn.k_proj.weight": "model-00024-of-00025.safetensors",
500
+ "model.layers.58.self_attn.o_proj.weight": "model-00024-of-00025.safetensors",
501
+ "model.layers.58.self_attn.q_proj.weight": "model-00024-of-00025.safetensors",
502
+ "model.layers.58.self_attn.v_proj.weight": "model-00024-of-00025.safetensors",
503
+ "model.layers.59.input_layernorm.weight": "model-00025-of-00025.safetensors",
504
+ "model.layers.59.mlp.down_proj.weight": "model-00025-of-00025.safetensors",
505
+ "model.layers.59.mlp.gate_proj.weight": "model-00025-of-00025.safetensors",
506
+ "model.layers.59.mlp.up_proj.weight": "model-00025-of-00025.safetensors",
507
+ "model.layers.59.post_attention_layernorm.weight": "model-00025-of-00025.safetensors",
508
+ "model.layers.59.self_attn.k_proj.weight": "model-00024-of-00025.safetensors",
509
+ "model.layers.59.self_attn.o_proj.weight": "model-00024-of-00025.safetensors",
510
+ "model.layers.59.self_attn.q_proj.weight": "model-00024-of-00025.safetensors",
511
+ "model.layers.59.self_attn.v_proj.weight": "model-00024-of-00025.safetensors",
512
+ "model.layers.6.input_layernorm.weight": "model-00004-of-00025.safetensors",
513
+ "model.layers.6.mlp.down_proj.weight": "model-00004-of-00025.safetensors",
514
+ "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00025.safetensors",
515
+ "model.layers.6.mlp.up_proj.weight": "model-00003-of-00025.safetensors",
516
+ "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00025.safetensors",
517
+ "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00025.safetensors",
518
+ "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00025.safetensors",
519
+ "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00025.safetensors",
520
+ "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00025.safetensors",
521
+ "model.layers.7.input_layernorm.weight": "model-00004-of-00025.safetensors",
522
+ "model.layers.7.mlp.down_proj.weight": "model-00004-of-00025.safetensors",
523
+ "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00025.safetensors",
524
+ "model.layers.7.mlp.up_proj.weight": "model-00004-of-00025.safetensors",
525
+ "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00025.safetensors",
526
+ "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00025.safetensors",
527
+ "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00025.safetensors",
528
+ "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00025.safetensors",
529
+ "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00025.safetensors",
530
+ "model.layers.8.input_layernorm.weight": "model-00004-of-00025.safetensors",
531
+ "model.layers.8.mlp.down_proj.weight": "model-00004-of-00025.safetensors",
532
+ "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00025.safetensors",
533
+ "model.layers.8.mlp.up_proj.weight": "model-00004-of-00025.safetensors",
534
+ "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00025.safetensors",
535
+ "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00025.safetensors",
536
+ "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00025.safetensors",
537
+ "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00025.safetensors",
538
+ "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00025.safetensors",
539
+ "model.layers.9.input_layernorm.weight": "model-00005-of-00025.safetensors",
540
+ "model.layers.9.mlp.down_proj.weight": "model-00005-of-00025.safetensors",
541
+ "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00025.safetensors",
542
+ "model.layers.9.mlp.up_proj.weight": "model-00005-of-00025.safetensors",
543
+ "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00025.safetensors",
544
+ "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00025.safetensors",
545
+ "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00025.safetensors",
546
+ "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00025.safetensors",
547
+ "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00025.safetensors",
548
+ "model.norm.weight": "model-00025-of-00025.safetensors"
549
+ }
550
+ }