SFconvertbot commited on
Commit
4e270bb
1 Parent(s): b5a0d43

Adding `safetensors` variant of this model

Browse files

This is an automated PR created with https://huggingface.co/spaces/safetensors/convert

This new file is equivalent to `pytorch_model.bin` but safe in the sense that
no arbitrary code can be put into it.

These files also happen to load much faster than their pytorch counterpart:
https://colab.research.google.com/github/huggingface/notebooks/blob/main/safetensors_doc/en/speed.ipynb

The widgets on your model page will run using this model even if this is not merged
making sure the file actually works.

If you find any issues: please report here: https://huggingface.co/spaces/safetensors/convert/discussions

Feel free to ignore this PR.

model-00001-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60872ed9d159e4ae75ebd3ddfc2ce521eb9aa64bc7b274efb30b8ad50b75262f
3
+ size 809518344
model-00002-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:304c1442e324e8d5036f37c125ec482bbd61116a2c568b80477b1905b446cc74
3
+ size 809518344
model-00003-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41495cb1ee3c318294db56e6e76fd6e4693e4e265ab8e7b5701681e18548af56
3
+ size 809518344
model-00004-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6287124fd4c34a5f38c7e182d6c4b6d0ca8531e52a68609fa72d311773a6355b
3
+ size 809518344
model-00005-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00184a65fa786b10da702afec4a9a20df75e9b5045f2c9da5af95552244e1eb5
3
+ size 809518344
model-00006-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09c799a5735be1f80b64135b02741ad18214333770b6bebce5f892b740d1b713
3
+ size 809518344
model-00007-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:614b15cc0f914d86d2ba6787981b3bb4fe665f962f0e08b29ffc1a6ecae9bd6e
3
+ size 809518344
model-00008-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33eabab03e02bfc1ac39691bf650261f4a9b6813e60ddacc449077aaf995a41c
3
+ size 809518344
model-00009-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d0c4c2e4c5afeb981ec0dd0ef8281cfe1a9edf1098c6e375eddcdfbc951a022
3
+ size 809518344
model-00010-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b02bc8f67fae2173c043aafd51732f93124e1be0bebf82e68ba2d4e37d4d2d3
3
+ size 809518344
model-00011-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4740f7835e506b6950b097f040d8346f1b7192a519bfc5309f2ff4596f5820ac
3
+ size 809518360
model-00012-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53d7b85b06764e31dcfdd464ca41f7ae3f8fa3ae242c2879a78a75060cd9f0c8
3
+ size 809518360
model-00013-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfbc8162b6333c444a2ece66f379b260f3af23989a93acc1b13919c24eec26db
3
+ size 809518360
model-00014-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:129b7a3699d4e2a3c91d1f006d01eef39c086f3959907fb665de7936cec6257b
3
+ size 809518360
model-00015-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d55771c4ad545d3df908a93403bc3723c830a5d8b3aaae44788c4e9c2774b167
3
+ size 809518360
model-00016-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b00b73a9233e9b499b7ca744d5dd0666e28a801a743e116f1f09116d59bdb995
3
+ size 809518360
model-00017-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a66aac00a1da9893c3c637163c9c83b65dfef796246fb3caa6a99e52ea156a90
3
+ size 809518360
model-00018-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8c2d438a4cdbfcae4a90ee1fa2bed95461370527927fce8c116abc330be7c97
3
+ size 809518360
model-00019-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b67d8b2e0d9abc67ceac8e8ef61e790d8aa427ea028021241675b771884cc38
3
+ size 809518360
model-00020-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09749961cd77bb776cdb1b11a8dcecb070f28aba39a3b2dd309de10ba8ed9a33
3
+ size 809518360
model-00021-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7afc4035835817438d33855d79269bff15dbc2cf86568d68d7b79ecbfb453bfb
3
+ size 809518360
model-00022-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e44bca87e5f800719a39e779e386f071118926ba295b84504f1547230c5d41d6
3
+ size 809518360
model-00023-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e33a2f6936acaa8cfa7f7c9f366665b00e4547f2289c614722294bf14377d15
3
+ size 809518360
model-00024-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ecb0dddcf23fd779d36806e200e8a752e68de5d698cc5800679afa2a541fbfd
3
+ size 809518360
model-00025-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f03c4703ba8d771a30cfdac12920ad4f7ea67bf015be8a5ec45f2369e484bd41
3
+ size 809518360
model-00026-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ff91fc66d6c3e50d23e6110f60d82d846dbd428f88f1500e612545e40c576f7
3
+ size 809518360
model-00027-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c2f5a64330c05a4651a15b8797794db56e454c89b31173a0b7d821524250f13
3
+ size 809518360
model-00028-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afdaa62bf4fa08686856e17797e417304db5d806dc9623627ab76b35a2492235
3
+ size 809518360
model-00029-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0bcb04f381e4b1e5b21ac6fd7c86da005589bb98c7b48bc6bf72584065b8c84
3
+ size 809518360
model-00030-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c6eb54fe72016a630329142f1b6ece79cb111f36bacd7617733665721ea84da
3
+ size 809518360
model-00031-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f307b76ef41ec4ae56bd59bf24e9524c0cbb9addb50405881b643aa9123f308
3
+ size 809518360
model-00032-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:608e2cd2aace4944d9f9d52f0d397a9a336948398630506e78f5d10ccee98547
3
+ size 809518360
model-00033-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb1f269451964260be5acb2f589547582ab07024271d78f7f2e1ba6d8d98aafc
3
+ size 524312896
model.safetensors.index.json ADDED
@@ -0,0 +1,330 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "weight_map": {
3
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00033.safetensors",
4
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00033.safetensors",
5
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00033.safetensors",
6
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00033.safetensors",
7
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00033.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00033.safetensors",
9
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00033.safetensors",
10
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00033.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00033.safetensors",
12
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00033.safetensors",
13
+ "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00033.safetensors",
14
+ "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00033.safetensors",
15
+ "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00033.safetensors",
16
+ "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00033.safetensors",
17
+ "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00033.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00002-of-00033.safetensors",
19
+ "model.layers.1.mlp.up_proj.weight": "model-00002-of-00033.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00002-of-00033.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00033.safetensors",
22
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00002-of-00033.safetensors",
23
+ "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00033.safetensors",
24
+ "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00033.safetensors",
25
+ "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00033.safetensors",
26
+ "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00033.safetensors",
27
+ "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00033.safetensors",
28
+ "model.layers.2.mlp.down_proj.weight": "model-00003-of-00033.safetensors",
29
+ "model.layers.2.mlp.up_proj.weight": "model-00003-of-00033.safetensors",
30
+ "model.layers.2.input_layernorm.weight": "model-00003-of-00033.safetensors",
31
+ "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00033.safetensors",
32
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00003-of-00033.safetensors",
33
+ "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00033.safetensors",
34
+ "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00033.safetensors",
35
+ "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00033.safetensors",
36
+ "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00033.safetensors",
37
+ "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00033.safetensors",
38
+ "model.layers.3.mlp.down_proj.weight": "model-00004-of-00033.safetensors",
39
+ "model.layers.3.mlp.up_proj.weight": "model-00004-of-00033.safetensors",
40
+ "model.layers.3.input_layernorm.weight": "model-00004-of-00033.safetensors",
41
+ "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00033.safetensors",
42
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00004-of-00033.safetensors",
43
+ "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00033.safetensors",
44
+ "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00033.safetensors",
45
+ "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00033.safetensors",
46
+ "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00033.safetensors",
47
+ "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00033.safetensors",
48
+ "model.layers.4.mlp.down_proj.weight": "model-00005-of-00033.safetensors",
49
+ "model.layers.4.mlp.up_proj.weight": "model-00005-of-00033.safetensors",
50
+ "model.layers.4.input_layernorm.weight": "model-00005-of-00033.safetensors",
51
+ "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00033.safetensors",
52
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00005-of-00033.safetensors",
53
+ "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00033.safetensors",
54
+ "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00033.safetensors",
55
+ "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00033.safetensors",
56
+ "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00033.safetensors",
57
+ "model.layers.5.mlp.gate_proj.weight": "model-00006-of-00033.safetensors",
58
+ "model.layers.5.mlp.down_proj.weight": "model-00006-of-00033.safetensors",
59
+ "model.layers.5.mlp.up_proj.weight": "model-00006-of-00033.safetensors",
60
+ "model.layers.5.input_layernorm.weight": "model-00006-of-00033.safetensors",
61
+ "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00033.safetensors",
62
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00006-of-00033.safetensors",
63
+ "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00033.safetensors",
64
+ "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00033.safetensors",
65
+ "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00033.safetensors",
66
+ "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00033.safetensors",
67
+ "model.layers.6.mlp.gate_proj.weight": "model-00007-of-00033.safetensors",
68
+ "model.layers.6.mlp.down_proj.weight": "model-00007-of-00033.safetensors",
69
+ "model.layers.6.mlp.up_proj.weight": "model-00007-of-00033.safetensors",
70
+ "model.layers.6.input_layernorm.weight": "model-00007-of-00033.safetensors",
71
+ "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00033.safetensors",
72
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00007-of-00033.safetensors",
73
+ "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00033.safetensors",
74
+ "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00033.safetensors",
75
+ "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00033.safetensors",
76
+ "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00033.safetensors",
77
+ "model.layers.7.mlp.gate_proj.weight": "model-00008-of-00033.safetensors",
78
+ "model.layers.7.mlp.down_proj.weight": "model-00008-of-00033.safetensors",
79
+ "model.layers.7.mlp.up_proj.weight": "model-00008-of-00033.safetensors",
80
+ "model.layers.7.input_layernorm.weight": "model-00008-of-00033.safetensors",
81
+ "model.layers.7.post_attention_layernorm.weight": "model-00008-of-00033.safetensors",
82
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00008-of-00033.safetensors",
83
+ "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00033.safetensors",
84
+ "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00033.safetensors",
85
+ "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00033.safetensors",
86
+ "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00033.safetensors",
87
+ "model.layers.8.mlp.gate_proj.weight": "model-00009-of-00033.safetensors",
88
+ "model.layers.8.mlp.down_proj.weight": "model-00009-of-00033.safetensors",
89
+ "model.layers.8.mlp.up_proj.weight": "model-00009-of-00033.safetensors",
90
+ "model.layers.8.input_layernorm.weight": "model-00009-of-00033.safetensors",
91
+ "model.layers.8.post_attention_layernorm.weight": "model-00009-of-00033.safetensors",
92
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00009-of-00033.safetensors",
93
+ "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00033.safetensors",
94
+ "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00033.safetensors",
95
+ "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00033.safetensors",
96
+ "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00033.safetensors",
97
+ "model.layers.9.mlp.gate_proj.weight": "model-00010-of-00033.safetensors",
98
+ "model.layers.9.mlp.down_proj.weight": "model-00010-of-00033.safetensors",
99
+ "model.layers.9.mlp.up_proj.weight": "model-00010-of-00033.safetensors",
100
+ "model.layers.9.input_layernorm.weight": "model-00010-of-00033.safetensors",
101
+ "model.layers.9.post_attention_layernorm.weight": "model-00010-of-00033.safetensors",
102
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00010-of-00033.safetensors",
103
+ "model.layers.10.self_attn.q_proj.weight": "model-00011-of-00033.safetensors",
104
+ "model.layers.10.self_attn.k_proj.weight": "model-00011-of-00033.safetensors",
105
+ "model.layers.10.self_attn.v_proj.weight": "model-00011-of-00033.safetensors",
106
+ "model.layers.10.self_attn.o_proj.weight": "model-00011-of-00033.safetensors",
107
+ "model.layers.10.mlp.gate_proj.weight": "model-00011-of-00033.safetensors",
108
+ "model.layers.10.mlp.down_proj.weight": "model-00011-of-00033.safetensors",
109
+ "model.layers.10.mlp.up_proj.weight": "model-00011-of-00033.safetensors",
110
+ "model.layers.10.input_layernorm.weight": "model-00011-of-00033.safetensors",
111
+ "model.layers.10.post_attention_layernorm.weight": "model-00011-of-00033.safetensors",
112
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00011-of-00033.safetensors",
113
+ "model.layers.11.self_attn.q_proj.weight": "model-00012-of-00033.safetensors",
114
+ "model.layers.11.self_attn.k_proj.weight": "model-00012-of-00033.safetensors",
115
+ "model.layers.11.self_attn.v_proj.weight": "model-00012-of-00033.safetensors",
116
+ "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00033.safetensors",
117
+ "model.layers.11.mlp.gate_proj.weight": "model-00012-of-00033.safetensors",
118
+ "model.layers.11.mlp.down_proj.weight": "model-00012-of-00033.safetensors",
119
+ "model.layers.11.mlp.up_proj.weight": "model-00012-of-00033.safetensors",
120
+ "model.layers.11.input_layernorm.weight": "model-00012-of-00033.safetensors",
121
+ "model.layers.11.post_attention_layernorm.weight": "model-00012-of-00033.safetensors",
122
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00012-of-00033.safetensors",
123
+ "model.layers.12.self_attn.q_proj.weight": "model-00013-of-00033.safetensors",
124
+ "model.layers.12.self_attn.k_proj.weight": "model-00013-of-00033.safetensors",
125
+ "model.layers.12.self_attn.v_proj.weight": "model-00013-of-00033.safetensors",
126
+ "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00033.safetensors",
127
+ "model.layers.12.mlp.gate_proj.weight": "model-00013-of-00033.safetensors",
128
+ "model.layers.12.mlp.down_proj.weight": "model-00013-of-00033.safetensors",
129
+ "model.layers.12.mlp.up_proj.weight": "model-00013-of-00033.safetensors",
130
+ "model.layers.12.input_layernorm.weight": "model-00013-of-00033.safetensors",
131
+ "model.layers.12.post_attention_layernorm.weight": "model-00013-of-00033.safetensors",
132
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00013-of-00033.safetensors",
133
+ "model.layers.13.self_attn.q_proj.weight": "model-00014-of-00033.safetensors",
134
+ "model.layers.13.self_attn.k_proj.weight": "model-00014-of-00033.safetensors",
135
+ "model.layers.13.self_attn.v_proj.weight": "model-00014-of-00033.safetensors",
136
+ "model.layers.13.self_attn.o_proj.weight": "model-00014-of-00033.safetensors",
137
+ "model.layers.13.mlp.gate_proj.weight": "model-00014-of-00033.safetensors",
138
+ "model.layers.13.mlp.down_proj.weight": "model-00014-of-00033.safetensors",
139
+ "model.layers.13.mlp.up_proj.weight": "model-00014-of-00033.safetensors",
140
+ "model.layers.13.input_layernorm.weight": "model-00014-of-00033.safetensors",
141
+ "model.layers.13.post_attention_layernorm.weight": "model-00014-of-00033.safetensors",
142
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00014-of-00033.safetensors",
143
+ "model.layers.14.self_attn.q_proj.weight": "model-00015-of-00033.safetensors",
144
+ "model.layers.14.self_attn.k_proj.weight": "model-00015-of-00033.safetensors",
145
+ "model.layers.14.self_attn.v_proj.weight": "model-00015-of-00033.safetensors",
146
+ "model.layers.14.self_attn.o_proj.weight": "model-00015-of-00033.safetensors",
147
+ "model.layers.14.mlp.gate_proj.weight": "model-00015-of-00033.safetensors",
148
+ "model.layers.14.mlp.down_proj.weight": "model-00015-of-00033.safetensors",
149
+ "model.layers.14.mlp.up_proj.weight": "model-00015-of-00033.safetensors",
150
+ "model.layers.14.input_layernorm.weight": "model-00015-of-00033.safetensors",
151
+ "model.layers.14.post_attention_layernorm.weight": "model-00015-of-00033.safetensors",
152
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00015-of-00033.safetensors",
153
+ "model.layers.15.self_attn.q_proj.weight": "model-00016-of-00033.safetensors",
154
+ "model.layers.15.self_attn.k_proj.weight": "model-00016-of-00033.safetensors",
155
+ "model.layers.15.self_attn.v_proj.weight": "model-00016-of-00033.safetensors",
156
+ "model.layers.15.self_attn.o_proj.weight": "model-00016-of-00033.safetensors",
157
+ "model.layers.15.mlp.gate_proj.weight": "model-00016-of-00033.safetensors",
158
+ "model.layers.15.mlp.down_proj.weight": "model-00016-of-00033.safetensors",
159
+ "model.layers.15.mlp.up_proj.weight": "model-00016-of-00033.safetensors",
160
+ "model.layers.15.input_layernorm.weight": "model-00016-of-00033.safetensors",
161
+ "model.layers.15.post_attention_layernorm.weight": "model-00016-of-00033.safetensors",
162
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00016-of-00033.safetensors",
163
+ "model.layers.16.self_attn.q_proj.weight": "model-00017-of-00033.safetensors",
164
+ "model.layers.16.self_attn.k_proj.weight": "model-00017-of-00033.safetensors",
165
+ "model.layers.16.self_attn.v_proj.weight": "model-00017-of-00033.safetensors",
166
+ "model.layers.16.self_attn.o_proj.weight": "model-00017-of-00033.safetensors",
167
+ "model.layers.16.mlp.gate_proj.weight": "model-00017-of-00033.safetensors",
168
+ "model.layers.16.mlp.down_proj.weight": "model-00017-of-00033.safetensors",
169
+ "model.layers.16.mlp.up_proj.weight": "model-00017-of-00033.safetensors",
170
+ "model.layers.16.input_layernorm.weight": "model-00017-of-00033.safetensors",
171
+ "model.layers.16.post_attention_layernorm.weight": "model-00017-of-00033.safetensors",
172
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00017-of-00033.safetensors",
173
+ "model.layers.17.self_attn.q_proj.weight": "model-00018-of-00033.safetensors",
174
+ "model.layers.17.self_attn.k_proj.weight": "model-00018-of-00033.safetensors",
175
+ "model.layers.17.self_attn.v_proj.weight": "model-00018-of-00033.safetensors",
176
+ "model.layers.17.self_attn.o_proj.weight": "model-00018-of-00033.safetensors",
177
+ "model.layers.17.mlp.gate_proj.weight": "model-00018-of-00033.safetensors",
178
+ "model.layers.17.mlp.down_proj.weight": "model-00018-of-00033.safetensors",
179
+ "model.layers.17.mlp.up_proj.weight": "model-00018-of-00033.safetensors",
180
+ "model.layers.17.input_layernorm.weight": "model-00018-of-00033.safetensors",
181
+ "model.layers.17.post_attention_layernorm.weight": "model-00018-of-00033.safetensors",
182
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00018-of-00033.safetensors",
183
+ "model.layers.18.self_attn.q_proj.weight": "model-00019-of-00033.safetensors",
184
+ "model.layers.18.self_attn.k_proj.weight": "model-00019-of-00033.safetensors",
185
+ "model.layers.18.self_attn.v_proj.weight": "model-00019-of-00033.safetensors",
186
+ "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00033.safetensors",
187
+ "model.layers.18.mlp.gate_proj.weight": "model-00019-of-00033.safetensors",
188
+ "model.layers.18.mlp.down_proj.weight": "model-00019-of-00033.safetensors",
189
+ "model.layers.18.mlp.up_proj.weight": "model-00019-of-00033.safetensors",
190
+ "model.layers.18.input_layernorm.weight": "model-00019-of-00033.safetensors",
191
+ "model.layers.18.post_attention_layernorm.weight": "model-00019-of-00033.safetensors",
192
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00019-of-00033.safetensors",
193
+ "model.layers.19.self_attn.q_proj.weight": "model-00020-of-00033.safetensors",
194
+ "model.layers.19.self_attn.k_proj.weight": "model-00020-of-00033.safetensors",
195
+ "model.layers.19.self_attn.v_proj.weight": "model-00020-of-00033.safetensors",
196
+ "model.layers.19.self_attn.o_proj.weight": "model-00020-of-00033.safetensors",
197
+ "model.layers.19.mlp.gate_proj.weight": "model-00020-of-00033.safetensors",
198
+ "model.layers.19.mlp.down_proj.weight": "model-00020-of-00033.safetensors",
199
+ "model.layers.19.mlp.up_proj.weight": "model-00020-of-00033.safetensors",
200
+ "model.layers.19.input_layernorm.weight": "model-00020-of-00033.safetensors",
201
+ "model.layers.19.post_attention_layernorm.weight": "model-00020-of-00033.safetensors",
202
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00020-of-00033.safetensors",
203
+ "model.layers.20.self_attn.q_proj.weight": "model-00021-of-00033.safetensors",
204
+ "model.layers.20.self_attn.k_proj.weight": "model-00021-of-00033.safetensors",
205
+ "model.layers.20.self_attn.v_proj.weight": "model-00021-of-00033.safetensors",
206
+ "model.layers.20.self_attn.o_proj.weight": "model-00021-of-00033.safetensors",
207
+ "model.layers.20.mlp.gate_proj.weight": "model-00021-of-00033.safetensors",
208
+ "model.layers.20.mlp.down_proj.weight": "model-00021-of-00033.safetensors",
209
+ "model.layers.20.mlp.up_proj.weight": "model-00021-of-00033.safetensors",
210
+ "model.layers.20.input_layernorm.weight": "model-00021-of-00033.safetensors",
211
+ "model.layers.20.post_attention_layernorm.weight": "model-00021-of-00033.safetensors",
212
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00021-of-00033.safetensors",
213
+ "model.layers.21.self_attn.q_proj.weight": "model-00022-of-00033.safetensors",
214
+ "model.layers.21.self_attn.k_proj.weight": "model-00022-of-00033.safetensors",
215
+ "model.layers.21.self_attn.v_proj.weight": "model-00022-of-00033.safetensors",
216
+ "model.layers.21.self_attn.o_proj.weight": "model-00022-of-00033.safetensors",
217
+ "model.layers.21.mlp.gate_proj.weight": "model-00022-of-00033.safetensors",
218
+ "model.layers.21.mlp.down_proj.weight": "model-00022-of-00033.safetensors",
219
+ "model.layers.21.mlp.up_proj.weight": "model-00022-of-00033.safetensors",
220
+ "model.layers.21.input_layernorm.weight": "model-00022-of-00033.safetensors",
221
+ "model.layers.21.post_attention_layernorm.weight": "model-00022-of-00033.safetensors",
222
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00022-of-00033.safetensors",
223
+ "model.layers.22.self_attn.q_proj.weight": "model-00023-of-00033.safetensors",
224
+ "model.layers.22.self_attn.k_proj.weight": "model-00023-of-00033.safetensors",
225
+ "model.layers.22.self_attn.v_proj.weight": "model-00023-of-00033.safetensors",
226
+ "model.layers.22.self_attn.o_proj.weight": "model-00023-of-00033.safetensors",
227
+ "model.layers.22.mlp.gate_proj.weight": "model-00023-of-00033.safetensors",
228
+ "model.layers.22.mlp.down_proj.weight": "model-00023-of-00033.safetensors",
229
+ "model.layers.22.mlp.up_proj.weight": "model-00023-of-00033.safetensors",
230
+ "model.layers.22.input_layernorm.weight": "model-00023-of-00033.safetensors",
231
+ "model.layers.22.post_attention_layernorm.weight": "model-00023-of-00033.safetensors",
232
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00023-of-00033.safetensors",
233
+ "model.layers.23.self_attn.q_proj.weight": "model-00024-of-00033.safetensors",
234
+ "model.layers.23.self_attn.k_proj.weight": "model-00024-of-00033.safetensors",
235
+ "model.layers.23.self_attn.v_proj.weight": "model-00024-of-00033.safetensors",
236
+ "model.layers.23.self_attn.o_proj.weight": "model-00024-of-00033.safetensors",
237
+ "model.layers.23.mlp.gate_proj.weight": "model-00024-of-00033.safetensors",
238
+ "model.layers.23.mlp.down_proj.weight": "model-00024-of-00033.safetensors",
239
+ "model.layers.23.mlp.up_proj.weight": "model-00024-of-00033.safetensors",
240
+ "model.layers.23.input_layernorm.weight": "model-00024-of-00033.safetensors",
241
+ "model.layers.23.post_attention_layernorm.weight": "model-00024-of-00033.safetensors",
242
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00024-of-00033.safetensors",
243
+ "model.layers.24.self_attn.q_proj.weight": "model-00025-of-00033.safetensors",
244
+ "model.layers.24.self_attn.k_proj.weight": "model-00025-of-00033.safetensors",
245
+ "model.layers.24.self_attn.v_proj.weight": "model-00025-of-00033.safetensors",
246
+ "model.layers.24.self_attn.o_proj.weight": "model-00025-of-00033.safetensors",
247
+ "model.layers.24.mlp.gate_proj.weight": "model-00025-of-00033.safetensors",
248
+ "model.layers.24.mlp.down_proj.weight": "model-00025-of-00033.safetensors",
249
+ "model.layers.24.mlp.up_proj.weight": "model-00025-of-00033.safetensors",
250
+ "model.layers.24.input_layernorm.weight": "model-00025-of-00033.safetensors",
251
+ "model.layers.24.post_attention_layernorm.weight": "model-00025-of-00033.safetensors",
252
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00025-of-00033.safetensors",
253
+ "model.layers.25.self_attn.q_proj.weight": "model-00026-of-00033.safetensors",
254
+ "model.layers.25.self_attn.k_proj.weight": "model-00026-of-00033.safetensors",
255
+ "model.layers.25.self_attn.v_proj.weight": "model-00026-of-00033.safetensors",
256
+ "model.layers.25.self_attn.o_proj.weight": "model-00026-of-00033.safetensors",
257
+ "model.layers.25.mlp.gate_proj.weight": "model-00026-of-00033.safetensors",
258
+ "model.layers.25.mlp.down_proj.weight": "model-00026-of-00033.safetensors",
259
+ "model.layers.25.mlp.up_proj.weight": "model-00026-of-00033.safetensors",
260
+ "model.layers.25.input_layernorm.weight": "model-00026-of-00033.safetensors",
261
+ "model.layers.25.post_attention_layernorm.weight": "model-00026-of-00033.safetensors",
262
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00026-of-00033.safetensors",
263
+ "model.layers.26.self_attn.q_proj.weight": "model-00027-of-00033.safetensors",
264
+ "model.layers.26.self_attn.k_proj.weight": "model-00027-of-00033.safetensors",
265
+ "model.layers.26.self_attn.v_proj.weight": "model-00027-of-00033.safetensors",
266
+ "model.layers.26.self_attn.o_proj.weight": "model-00027-of-00033.safetensors",
267
+ "model.layers.26.mlp.gate_proj.weight": "model-00027-of-00033.safetensors",
268
+ "model.layers.26.mlp.down_proj.weight": "model-00027-of-00033.safetensors",
269
+ "model.layers.26.mlp.up_proj.weight": "model-00027-of-00033.safetensors",
270
+ "model.layers.26.input_layernorm.weight": "model-00027-of-00033.safetensors",
271
+ "model.layers.26.post_attention_layernorm.weight": "model-00027-of-00033.safetensors",
272
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "model-00027-of-00033.safetensors",
273
+ "model.layers.27.self_attn.q_proj.weight": "model-00028-of-00033.safetensors",
274
+ "model.layers.27.self_attn.k_proj.weight": "model-00028-of-00033.safetensors",
275
+ "model.layers.27.self_attn.v_proj.weight": "model-00028-of-00033.safetensors",
276
+ "model.layers.27.self_attn.o_proj.weight": "model-00028-of-00033.safetensors",
277
+ "model.layers.27.mlp.gate_proj.weight": "model-00028-of-00033.safetensors",
278
+ "model.layers.27.mlp.down_proj.weight": "model-00028-of-00033.safetensors",
279
+ "model.layers.27.mlp.up_proj.weight": "model-00028-of-00033.safetensors",
280
+ "model.layers.27.input_layernorm.weight": "model-00028-of-00033.safetensors",
281
+ "model.layers.27.post_attention_layernorm.weight": "model-00028-of-00033.safetensors",
282
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "model-00028-of-00033.safetensors",
283
+ "model.layers.28.self_attn.q_proj.weight": "model-00029-of-00033.safetensors",
284
+ "model.layers.28.self_attn.k_proj.weight": "model-00029-of-00033.safetensors",
285
+ "model.layers.28.self_attn.v_proj.weight": "model-00029-of-00033.safetensors",
286
+ "model.layers.28.self_attn.o_proj.weight": "model-00029-of-00033.safetensors",
287
+ "model.layers.28.mlp.gate_proj.weight": "model-00029-of-00033.safetensors",
288
+ "model.layers.28.mlp.down_proj.weight": "model-00029-of-00033.safetensors",
289
+ "model.layers.28.mlp.up_proj.weight": "model-00029-of-00033.safetensors",
290
+ "model.layers.28.input_layernorm.weight": "model-00029-of-00033.safetensors",
291
+ "model.layers.28.post_attention_layernorm.weight": "model-00029-of-00033.safetensors",
292
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "model-00029-of-00033.safetensors",
293
+ "model.layers.29.self_attn.q_proj.weight": "model-00030-of-00033.safetensors",
294
+ "model.layers.29.self_attn.k_proj.weight": "model-00030-of-00033.safetensors",
295
+ "model.layers.29.self_attn.v_proj.weight": "model-00030-of-00033.safetensors",
296
+ "model.layers.29.self_attn.o_proj.weight": "model-00030-of-00033.safetensors",
297
+ "model.layers.29.mlp.gate_proj.weight": "model-00030-of-00033.safetensors",
298
+ "model.layers.29.mlp.down_proj.weight": "model-00030-of-00033.safetensors",
299
+ "model.layers.29.mlp.up_proj.weight": "model-00030-of-00033.safetensors",
300
+ "model.layers.29.input_layernorm.weight": "model-00030-of-00033.safetensors",
301
+ "model.layers.29.post_attention_layernorm.weight": "model-00030-of-00033.safetensors",
302
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "model-00030-of-00033.safetensors",
303
+ "model.layers.30.self_attn.q_proj.weight": "model-00031-of-00033.safetensors",
304
+ "model.layers.30.self_attn.k_proj.weight": "model-00031-of-00033.safetensors",
305
+ "model.layers.30.self_attn.v_proj.weight": "model-00031-of-00033.safetensors",
306
+ "model.layers.30.self_attn.o_proj.weight": "model-00031-of-00033.safetensors",
307
+ "model.layers.30.mlp.gate_proj.weight": "model-00031-of-00033.safetensors",
308
+ "model.layers.30.mlp.down_proj.weight": "model-00031-of-00033.safetensors",
309
+ "model.layers.30.mlp.up_proj.weight": "model-00031-of-00033.safetensors",
310
+ "model.layers.30.input_layernorm.weight": "model-00031-of-00033.safetensors",
311
+ "model.layers.30.post_attention_layernorm.weight": "model-00031-of-00033.safetensors",
312
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "model-00031-of-00033.safetensors",
313
+ "model.layers.31.self_attn.q_proj.weight": "model-00032-of-00033.safetensors",
314
+ "model.layers.31.self_attn.k_proj.weight": "model-00032-of-00033.safetensors",
315
+ "model.layers.31.self_attn.v_proj.weight": "model-00032-of-00033.safetensors",
316
+ "model.layers.31.self_attn.o_proj.weight": "model-00032-of-00033.safetensors",
317
+ "model.layers.31.mlp.gate_proj.weight": "model-00032-of-00033.safetensors",
318
+ "model.layers.31.mlp.down_proj.weight": "model-00032-of-00033.safetensors",
319
+ "model.layers.31.mlp.up_proj.weight": "model-00032-of-00033.safetensors",
320
+ "model.layers.31.input_layernorm.weight": "model-00032-of-00033.safetensors",
321
+ "model.layers.31.post_attention_layernorm.weight": "model-00032-of-00033.safetensors",
322
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "model-00032-of-00033.safetensors",
323
+ "model.embed_tokens.weight": "model-00033-of-00033.safetensors",
324
+ "model.norm.weight": "model-00033-of-00033.safetensors",
325
+ "lm_head.weight": "model-00033-of-00033.safetensors"
326
+ },
327
+ "metadata": {
328
+ "total_size": 13476835328
329
+ }
330
+ }