sharpbai commited on
Commit
3580522
1 Parent(s): 1f35e7a

Upload LlamaForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sharpbai/vicuna-7b-v1.3",
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
+ "pad_token_id": 0,
17
+ "rms_norm_eps": 1e-06,
18
+ "tie_word_embeddings": false,
19
+ "torch_dtype": "float16",
20
+ "transformers_version": "4.30.1",
21
+ "use_cache": false,
22
+ "vocab_size": 32000
23
+ }
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": "4.30.1"
7
+ }
pytorch_model-00001-of-00034.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:560c45c33ca77a0c0cd34bfe2d57a8dcf1d4d1ed8dcb8af8f34e42cb2b5aaf18
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:ccfdfcd8be316440a295b0022d20ebe4d313724580bf32dd676c390a0e953b11
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:ed2c90c76c331de50537df61e0b1e20cdbfdeb3402bd869725b6c64c15ff6bf5
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 sha256:290dc11d6c82fadf9a2d1e22d2ec29833c672a6e7a949fdf5105a0fb78d1ddad
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 sha256:024a0466d17bdd33b8a87254989717645bdf4a5c911e69f09256c10b1d614dea
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 sha256:49fe6bd85f27d0a3283e1db9da5f8e5a1da446aaa60fbc0424eb18146274c797
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 sha256:4d83947aeb6905b95736f6748053bd989d21e51bf1c8e46b8bf6e84f4a81498e
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 sha256:5bbdc524468ee07065cdd25c704045b7d0d20177f3f8997d832290c9e02c2dab
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 sha256:319ef1afe42cfedbcb35bce32e9e28cf15d1742cc3144dec947b24e8f1819247
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:e2e5c18c2cd232c6459940f354e867cf49d8175c2db799871697827274dba4a2
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 sha256:47b3f766fa648b9ce63c8f7ace1d6230e899f5927a79c095fc771773913f3f10
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 sha256:77f1869b856208ef80f97cba95ce9b871267ed528fcdf31f7ce449a7add92139
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 sha256:487a764aa3c4b8b735495a3c205968ba445abd34ea0ecc86a8d22784b83cad98
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:ca20d57b7e3c67335f042b99f696323eaa5c0d887283a1b9e3a9cdc3f0cd018c
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 sha256:983cbeef476d346fd2592bd0d6b05e8dc54c9b6fd6c8eb13f99c81050d38e35d
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 sha256:07bd02fd23ac26c8f66056c414693f2acee68cbcd99cb613fa536b1e185315dc
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 sha256:06169da9f541a0adfb16ee5edbf5b988cd0b34cec996ddff5c0eccb69cc0e81b
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 sha256:59cbafb0b951227bbdbba1a59294a3eb334366f70579f4fd4ba49d2e755bc07c
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:a58fbd9c5afe389044dc492393b2e84629dbd2c9b43f7f9a86787ec630194544
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 sha256:4bd70c752be7fa99f710304a2c279c5c1cb4968fdce44de2de4371d012b1116e
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 sha256:6d00ba178330c7cb8e1bc7084180402a4fe0fd188c2c7bdb515361d9865688e3
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 sha256:121983258ca54bb8b2d185bd33aeb6ea2427910824b7a3638cd761d79e63b882
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 sha256:5fdc6868375fdd821e243da0ee1dbcb1a6d6f26bf9ed0c0c21746023faf45c31
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 sha256:39dd38094e2dc125f5963d90315cedbff7dd48397fa411b8daa7b750e4d8c53a
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 sha256:680a1c8d2b8fcdd861df704897f73ddd5ea8382ce3c95b3fbe2c417e935e5971
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 sha256:7d03aee6b09b76720b4ec5d6ebd7fde124e9df99151a9d281f366c404d7fb363
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 sha256:8db9ec0dccedf998b840d0d1fa3f1f4a80af7e12e85a64d268363427ee7ab2d1
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 sha256:7b54afe5ae004c1fa993544424b7215ffe8af9ffcdddce2429b33cf1684bf892
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:cf08c1a35c5bfc3cfd5bdecf4974e2f3290308bcc348863ead27d8b96df67fea
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 sha256:9439581428345d432828c5c408faffd50e0df81023d67a69fe6cf60e4983fdb7
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 sha256:54e56b813612ca808d5c34c73dae34496d9751e9358da2fa9adb79da27fb2c85
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 sha256:9b2f072cf49e8e412c2f8d55971e63c95676b706eccd833c514928036be9c343
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 sha256:11c5679e209ea9e4c834223b014a907d68d1423aa53736969883e30a6bc3a769
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 sha256:0f59408d46374795cd0c8b1683fcd7bee08485ce425e3b0a9c5c2174c6c0624a
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
+ }