sharpbai commited on
Commit
8e7c4de
1 Parent(s): 3cefb7f

Upload LlamaForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sharpbai/Llama-2-7b-hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "max_position_embeddings": 2048,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 32,
17
+ "pad_token_id": 0,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.30.2",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 32000,
6
+ "temperature": 0.9,
7
+ "top_p": 0.6,
8
+ "transformers_version": "4.30.2"
9
+ }
pytorch_model-00001-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd137c4b366035bf8ba5c800a15c715368526d7f698b282c5fccbc0f7d019932
3
+ size 396364479
pytorch_model-00002-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbcf4ff9589329687da8458d1ec7b00f9630b3df6878c54b8199051161661738
3
+ size 404770755
pytorch_model-00003-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4579e47e2e8687891cb4ce9c0e86d4f3a534ed4d3eabbf893f828c14a52ffa62
3
+ size 404770755
pytorch_model-00004-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cc7ddf261fe6160be16215277407219056df2a97bcad0011a784f2c6baee4ca
3
+ size 404770755
pytorch_model-00005-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94339ed610c62dce7fd8b92035f3b1e123be82631f98e6fd46fabf0be302067a
3
+ size 404770755
pytorch_model-00006-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92c18824989d247ed752a26aa23f1e146b33629c16a3dc8a300917c42488bf21
3
+ size 404770755
pytorch_model-00007-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab3fffe94d75394c10767d82ff4233510858f631251e71704f0b6859d8505761
3
+ size 404770755
pytorch_model-00008-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ec7ba704f41e22e02c1ba6bc0207af9889e480447ae73be603fc6d789b5ab2b
3
+ size 404770755
pytorch_model-00009-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dd06a1067ada7a09635147c7b760919c4363f92ef5f27e8248b843f5e53cb3d
3
+ size 404770755
pytorch_model-00010-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef98304ab3d1bd3c64ef0e3bed040d463ff4e1d9af31d09e412a53097c9d3ed5
3
+ size 404770755
pytorch_model-00011-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c7700f5d9591ff67280b71993ab38e1a57d74e850f770d5b161e8e5cc0dd3d0
3
+ size 404770755
pytorch_model-00012-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06f2c753edb6172a44283d9564616706aeb54918a0a1e8386e3eb8eba0098bbc
3
+ size 404770755
pytorch_model-00013-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b4ee502b66e378388c022863db8092297c43f0efe12105b322eeeac8e2a5000
3
+ size 404770755
pytorch_model-00014-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7f55f6f85d4df469ddc7183dec8a3394eceea80351e1bb304d4ee49ac73f334
3
+ size 404770755
pytorch_model-00015-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:148386ab188d0ae772aecf455d10eed0cd2b1e3d987b24207a400b329ebd6d50
3
+ size 404770755
pytorch_model-00016-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c04d01a2eaa06cd2cb3ee6da1d41f728267f999400aebd7a51f2cbf46e3f3626
3
+ size 404770755
pytorch_model-00017-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f02a362f1b6ca7b11776f738ab5d221f447104cbfb6346d2e417165de32e7218
3
+ size 404770755
pytorch_model-00018-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c183e94645e5b5a978b2aef350d1f9d19f11d4256778aff47d62bd5a908393f5
3
+ size 404770755
pytorch_model-00019-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e5101c1c5f7745110174c9ca3e72a36063d123e16cb6da7ab343bc987ffa685
3
+ size 404770755
pytorch_model-00020-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e816b815b5c92cfffc4e64f4254ccc5c259b5276325d4f3237799e7e95e3ba2
3
+ size 404770755
pytorch_model-00021-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d73caa4a421248e021275dae3e1edb0dabeafbdf06fdb49ed9ec9daecdcda2f6
3
+ size 404770755
pytorch_model-00022-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4875b7a4e347ec29a69abb21d3736169cca0642b2f53b7c48e91478125d625b
3
+ size 404770755
pytorch_model-00023-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e319a1cdb732f637869db7e2ac47d199cb89fbee75bca685881b0fefcf24cb60
3
+ size 404770755
pytorch_model-00024-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ee19332d171cc457222e4238bbab2d55e0e2f274d392791651d2a725903e5f9
3
+ size 404770755
pytorch_model-00025-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58a00b34d7bab83ec1e77e951e71f61d82991e5330fc6c39f40d05ad0e9f384e
3
+ size 404770755
pytorch_model-00026-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46d262f4293f9c1c537fc0c3461a931baec68346111df90cbd403dbafbad3ef9
3
+ size 404770755
pytorch_model-00027-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f0598857f28e247b06b0052dfcd4b148c52ede7d884f7257a61152e32a9046b
3
+ size 404770755
pytorch_model-00028-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2ccfe2d5dbbeb72bca794fa5af3eb5d3aab629920eb367ae3a953443ab5288e
3
+ size 404770755
pytorch_model-00029-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63a077208db0ed9f05a07ab109b9166784260a423ba2af22f96cf44779065774
3
+ size 404770755
pytorch_model-00030-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4582deba41c9225441fd2f8a38a24ce5dc4264da7844dd4f2d2fa909ef861f11
3
+ size 404770755
pytorch_model-00031-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8810e8ff49862287c9f6623c36b9e5cb1a89b96e8079e1c8953716dafa8b5dfb
3
+ size 404770755
pytorch_model-00032-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2efa1391cb8db878ef1cc19d7cdeaa46fca94b62b90b3ce69fe180c02c0810d
3
+ size 404770755
pytorch_model-00033-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca18314960dff61dfa1a7a68c8125bbc1a8f769eee190058a78ea823041709aa
3
+ size 270559679
pytorch_model-00034-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53646e6aa292965464a3c56efdbd06d0204fe41623d6f3a4c8abb6d7d7999dc9
3
+ size 262144938
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,330 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13476839424
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00034-of-00034.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00034.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00034.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00034.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00034.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00034.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00034.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00034.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00034.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00034.bin",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00034.bin",
17
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00034.bin",
18
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00003-of-00034.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00003-of-00034.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00003-of-00034.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00003-of-00034.bin",
22
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00003-of-00034.bin",
23
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00034.bin",
24
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00034.bin",
25
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00034.bin",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00034.bin",
27
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00034.bin",
28
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00012-of-00034.bin",
29
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00012-of-00034.bin",
30
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00012-of-00034.bin",
31
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00012-of-00034.bin",
32
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00012-of-00034.bin",
33
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00011-of-00034.bin",
34
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00011-of-00034.bin",
35
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00011-of-00034.bin",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00034.bin",
37
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00011-of-00034.bin",
38
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00013-of-00034.bin",
39
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00013-of-00034.bin",
40
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00013-of-00034.bin",
41
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00013-of-00034.bin",
42
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00013-of-00034.bin",
43
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00012-of-00034.bin",
44
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00012-of-00034.bin",
45
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00012-of-00034.bin",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00034.bin",
47
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00012-of-00034.bin",
48
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00014-of-00034.bin",
49
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00014-of-00034.bin",
50
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00014-of-00034.bin",
51
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00014-of-00034.bin",
52
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00014-of-00034.bin",
53
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00013-of-00034.bin",
54
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00013-of-00034.bin",
55
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00013-of-00034.bin",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00034.bin",
57
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00013-of-00034.bin",
58
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00015-of-00034.bin",
59
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00015-of-00034.bin",
60
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00015-of-00034.bin",
61
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00015-of-00034.bin",
62
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00015-of-00034.bin",
63
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00014-of-00034.bin",
64
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00014-of-00034.bin",
65
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00014-of-00034.bin",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00034.bin",
67
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00014-of-00034.bin",
68
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00016-of-00034.bin",
69
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00016-of-00034.bin",
70
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00016-of-00034.bin",
71
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00016-of-00034.bin",
72
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00016-of-00034.bin",
73
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00015-of-00034.bin",
74
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00015-of-00034.bin",
75
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00015-of-00034.bin",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00034.bin",
77
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00015-of-00034.bin",
78
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00017-of-00034.bin",
79
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00017-of-00034.bin",
80
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00017-of-00034.bin",
81
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00017-of-00034.bin",
82
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00017-of-00034.bin",
83
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00016-of-00034.bin",
84
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00016-of-00034.bin",
85
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00016-of-00034.bin",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00034.bin",
87
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00016-of-00034.bin",
88
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00018-of-00034.bin",
89
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00018-of-00034.bin",
90
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00018-of-00034.bin",
91
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00018-of-00034.bin",
92
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00018-of-00034.bin",
93
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00017-of-00034.bin",
94
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00017-of-00034.bin",
95
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00017-of-00034.bin",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00034.bin",
97
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00017-of-00034.bin",
98
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00019-of-00034.bin",
99
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00019-of-00034.bin",
100
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00019-of-00034.bin",
101
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00019-of-00034.bin",
102
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00019-of-00034.bin",
103
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00018-of-00034.bin",
104
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00018-of-00034.bin",
105
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00018-of-00034.bin",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00034.bin",
107
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00018-of-00034.bin",
108
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00020-of-00034.bin",
109
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00020-of-00034.bin",
110
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00020-of-00034.bin",
111
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00020-of-00034.bin",
112
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00020-of-00034.bin",
113
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00019-of-00034.bin",
114
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00019-of-00034.bin",
115
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00019-of-00034.bin",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00034.bin",
117
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00019-of-00034.bin",
118
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00021-of-00034.bin",
119
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00021-of-00034.bin",
120
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00021-of-00034.bin",
121
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00021-of-00034.bin",
122
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00021-of-00034.bin",
123
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00020-of-00034.bin",
124
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00020-of-00034.bin",
125
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00020-of-00034.bin",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00034.bin",
127
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00020-of-00034.bin",
128
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00004-of-00034.bin",
129
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00004-of-00034.bin",
130
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00004-of-00034.bin",
131
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00004-of-00034.bin",
132
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00004-of-00034.bin",
133
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00034.bin",
134
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00003-of-00034.bin",
135
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00034.bin",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00034.bin",
137
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00034.bin",
138
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00022-of-00034.bin",
139
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00022-of-00034.bin",
140
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00022-of-00034.bin",
141
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00022-of-00034.bin",
142
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00022-of-00034.bin",
143
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00021-of-00034.bin",
144
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00021-of-00034.bin",
145
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00021-of-00034.bin",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00034.bin",
147
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00021-of-00034.bin",
148
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00023-of-00034.bin",
149
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00023-of-00034.bin",
150
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00023-of-00034.bin",
151
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00023-of-00034.bin",
152
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00023-of-00034.bin",
153
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00022-of-00034.bin",
154
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00022-of-00034.bin",
155
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00022-of-00034.bin",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00034.bin",
157
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00022-of-00034.bin",
158
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00024-of-00034.bin",
159
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00024-of-00034.bin",
160
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00024-of-00034.bin",
161
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00024-of-00034.bin",
162
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00024-of-00034.bin",
163
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00023-of-00034.bin",
164
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00023-of-00034.bin",
165
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00023-of-00034.bin",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00034.bin",
167
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00023-of-00034.bin",
168
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00025-of-00034.bin",
169
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00025-of-00034.bin",
170
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00025-of-00034.bin",
171
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00025-of-00034.bin",
172
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00025-of-00034.bin",
173
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00024-of-00034.bin",
174
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00024-of-00034.bin",
175
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00024-of-00034.bin",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00034.bin",
177
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00024-of-00034.bin",
178
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00026-of-00034.bin",
179
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00026-of-00034.bin",
180
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00026-of-00034.bin",
181
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00026-of-00034.bin",
182
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00026-of-00034.bin",
183
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00025-of-00034.bin",
184
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00025-of-00034.bin",
185
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00025-of-00034.bin",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00034.bin",
187
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00025-of-00034.bin",
188
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00027-of-00034.bin",
189
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00027-of-00034.bin",
190
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00027-of-00034.bin",
191
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00027-of-00034.bin",
192
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00027-of-00034.bin",
193
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00026-of-00034.bin",
194
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00026-of-00034.bin",
195
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00026-of-00034.bin",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00034.bin",
197
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00026-of-00034.bin",
198
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00028-of-00034.bin",
199
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00028-of-00034.bin",
200
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00028-of-00034.bin",
201
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00028-of-00034.bin",
202
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00028-of-00034.bin",
203
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00027-of-00034.bin",
204
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00027-of-00034.bin",
205
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00027-of-00034.bin",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00034.bin",
207
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00027-of-00034.bin",
208
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00029-of-00034.bin",
209
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00029-of-00034.bin",
210
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00029-of-00034.bin",
211
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00029-of-00034.bin",
212
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00029-of-00034.bin",
213
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00028-of-00034.bin",
214
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00028-of-00034.bin",
215
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00028-of-00034.bin",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00028-of-00034.bin",
217
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00028-of-00034.bin",
218
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00030-of-00034.bin",
219
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00030-of-00034.bin",
220
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00030-of-00034.bin",
221
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00030-of-00034.bin",
222
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00030-of-00034.bin",
223
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00029-of-00034.bin",
224
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00029-of-00034.bin",
225
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00029-of-00034.bin",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00029-of-00034.bin",
227
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00029-of-00034.bin",
228
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00031-of-00034.bin",
229
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00031-of-00034.bin",
230
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00031-of-00034.bin",
231
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00031-of-00034.bin",
232
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00031-of-00034.bin",
233
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00030-of-00034.bin",
234
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00030-of-00034.bin",
235
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00030-of-00034.bin",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00030-of-00034.bin",
237
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00030-of-00034.bin",
238
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00005-of-00034.bin",
239
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00005-of-00034.bin",
240
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00005-of-00034.bin",
241
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00005-of-00034.bin",
242
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00005-of-00034.bin",
243
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00004-of-00034.bin",
244
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00004-of-00034.bin",
245
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00004-of-00034.bin",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00034.bin",
247
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00004-of-00034.bin",
248
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00032-of-00034.bin",
249
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00032-of-00034.bin",
250
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00032-of-00034.bin",
251
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00032-of-00034.bin",
252
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00032-of-00034.bin",
253
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00031-of-00034.bin",
254
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00031-of-00034.bin",
255
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00031-of-00034.bin",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00031-of-00034.bin",
257
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00031-of-00034.bin",
258
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00033-of-00034.bin",
259
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00033-of-00034.bin",
260
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00033-of-00034.bin",
261
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00033-of-00034.bin",
262
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00033-of-00034.bin",
263
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00032-of-00034.bin",
264
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00032-of-00034.bin",
265
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00032-of-00034.bin",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00032-of-00034.bin",
267
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00032-of-00034.bin",
268
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00006-of-00034.bin",
269
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00006-of-00034.bin",
270
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00006-of-00034.bin",
271
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00006-of-00034.bin",
272
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00006-of-00034.bin",
273
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00005-of-00034.bin",
274
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00005-of-00034.bin",
275
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00005-of-00034.bin",
276
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00034.bin",
277
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00005-of-00034.bin",
278
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00007-of-00034.bin",
279
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00007-of-00034.bin",
280
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00007-of-00034.bin",
281
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00007-of-00034.bin",
282
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00007-of-00034.bin",
283
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00006-of-00034.bin",
284
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00006-of-00034.bin",
285
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00006-of-00034.bin",
286
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00034.bin",
287
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00006-of-00034.bin",
288
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00008-of-00034.bin",
289
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00008-of-00034.bin",
290
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00008-of-00034.bin",
291
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00008-of-00034.bin",
292
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00008-of-00034.bin",
293
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00007-of-00034.bin",
294
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00007-of-00034.bin",
295
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00007-of-00034.bin",
296
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00034.bin",
297
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00007-of-00034.bin",
298
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00009-of-00034.bin",
299
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00009-of-00034.bin",
300
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00009-of-00034.bin",
301
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00009-of-00034.bin",
302
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00009-of-00034.bin",
303
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00008-of-00034.bin",
304
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00008-of-00034.bin",
305
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00008-of-00034.bin",
306
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00034.bin",
307
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00008-of-00034.bin",
308
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00010-of-00034.bin",
309
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00010-of-00034.bin",
310
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00010-of-00034.bin",
311
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00010-of-00034.bin",
312
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00010-of-00034.bin",
313
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00009-of-00034.bin",
314
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00009-of-00034.bin",
315
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00009-of-00034.bin",
316
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00034.bin",
317
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00009-of-00034.bin",
318
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00011-of-00034.bin",
319
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00011-of-00034.bin",
320
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00011-of-00034.bin",
321
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00011-of-00034.bin",
322
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00011-of-00034.bin",
323
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00010-of-00034.bin",
324
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00010-of-00034.bin",
325
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00010-of-00034.bin",
326
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00034.bin",
327
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00010-of-00034.bin",
328
+ "model.norm.weight": "pytorch_model-00033-of-00034.bin"
329
+ }
330
+ }