Hugging Face's logo

OpenNLPLab
/
TransNormerLLM2-1B-300B

Text Generation
Transformers
PyTorch
English
Chinese
TransNormerLLM
custom_code
Model card Files Community
2
SFconvertbot commited on
Commit
0eed957
·
verified ·
1 Parent(s): bf796dd

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.

Files changed (4) hide show
  1. model-00001-of-00003.safetensors +3 -0
  2. model-00002-of-00003.safetensors +3 -0
  3. model-00003-of-00003.safetensors +3 -0
  4. model.safetensors.index.json +90 -0
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22b80e33d7c4cc3924fb0d348ee31209a713ab25c0f58fa21a95c23b28ee7a20
3
+ size 994058288
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e359e05bef7febb83bbc69214ecc0ba9185e24c6c3b36c6909a41422b5eb8f2b
3
+ size 977278024
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22258c02668d97019e03082ac098ab9a679dd6a5bc7c526b3a2c548502754c59
3
+ size 69206392
model.safetensors.index.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 2040532992
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00001-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.channel_mixer.l1.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.channel_mixer.l2.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.channel_mixer.l3.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.token_mixer.lrpe.theta": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.token_mixer.out_proj.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.token_mixer.qkvu_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.1.channel_mixer.l1.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.1.channel_mixer.l2.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.1.channel_mixer.l3.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.token_mixer.out_proj.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.token_mixer.qkvu_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.10.channel_mixer.l1.weight": "model-00002-of-00003.safetensors",
20
+ "model.layers.10.channel_mixer.l2.weight": "model-00002-of-00003.safetensors",
21
+ "model.layers.10.channel_mixer.l3.weight": "model-00002-of-00003.safetensors",
22
+ "model.layers.10.token_mixer.out_proj.weight": "model-00002-of-00003.safetensors",
23
+ "model.layers.10.token_mixer.qkvu_proj.weight": "model-00002-of-00003.safetensors",
24
+ "model.layers.11.channel_mixer.l1.weight": "model-00002-of-00003.safetensors",
25
+ "model.layers.11.channel_mixer.l2.weight": "model-00002-of-00003.safetensors",
26
+ "model.layers.11.channel_mixer.l3.weight": "model-00002-of-00003.safetensors",
27
+ "model.layers.11.token_mixer.out_proj.weight": "model-00002-of-00003.safetensors",
28
+ "model.layers.11.token_mixer.qkvu_proj.weight": "model-00002-of-00003.safetensors",
29
+ "model.layers.12.channel_mixer.l1.weight": "model-00002-of-00003.safetensors",
30
+ "model.layers.12.channel_mixer.l2.weight": "model-00002-of-00003.safetensors",
31
+ "model.layers.12.channel_mixer.l3.weight": "model-00002-of-00003.safetensors",
32
+ "model.layers.12.token_mixer.out_proj.weight": "model-00002-of-00003.safetensors",
33
+ "model.layers.12.token_mixer.qkvu_proj.weight": "model-00002-of-00003.safetensors",
34
+ "model.layers.13.channel_mixer.l1.weight": "model-00002-of-00003.safetensors",
35
+ "model.layers.13.channel_mixer.l2.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.13.channel_mixer.l3.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.13.token_mixer.out_proj.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.13.token_mixer.qkvu_proj.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.14.channel_mixer.l1.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.14.channel_mixer.l2.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.14.channel_mixer.l3.weight": "model-00002-of-00003.safetensors",
42
+ "model.layers.14.token_mixer.out_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.14.token_mixer.qkvu_proj.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.15.channel_mixer.l1.weight": "model-00003-of-00003.safetensors",
45
+ "model.layers.15.channel_mixer.l2.weight": "model-00003-of-00003.safetensors",
46
+ "model.layers.15.channel_mixer.l3.weight": "model-00003-of-00003.safetensors",
47
+ "model.layers.15.token_mixer.out_proj.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.15.token_mixer.qkvu_proj.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.2.channel_mixer.l1.weight": "model-00001-of-00003.safetensors",
50
+ "model.layers.2.channel_mixer.l2.weight": "model-00001-of-00003.safetensors",
51
+ "model.layers.2.channel_mixer.l3.weight": "model-00001-of-00003.safetensors",
52
+ "model.layers.2.token_mixer.out_proj.weight": "model-00001-of-00003.safetensors",
53
+ "model.layers.2.token_mixer.qkvu_proj.weight": "model-00001-of-00003.safetensors",
54
+ "model.layers.3.channel_mixer.l1.weight": "model-00001-of-00003.safetensors",
55
+ "model.layers.3.channel_mixer.l2.weight": "model-00001-of-00003.safetensors",
56
+ "model.layers.3.channel_mixer.l3.weight": "model-00001-of-00003.safetensors",
57
+ "model.layers.3.token_mixer.out_proj.weight": "model-00001-of-00003.safetensors",
58
+ "model.layers.3.token_mixer.qkvu_proj.weight": "model-00001-of-00003.safetensors",
59
+ "model.layers.4.channel_mixer.l1.weight": "model-00001-of-00003.safetensors",
60
+ "model.layers.4.channel_mixer.l2.weight": "model-00001-of-00003.safetensors",
61
+ "model.layers.4.channel_mixer.l3.weight": "model-00001-of-00003.safetensors",
62
+ "model.layers.4.token_mixer.out_proj.weight": "model-00001-of-00003.safetensors",
63
+ "model.layers.4.token_mixer.qkvu_proj.weight": "model-00001-of-00003.safetensors",
64
+ "model.layers.5.channel_mixer.l1.weight": "model-00001-of-00003.safetensors",
65
+ "model.layers.5.channel_mixer.l2.weight": "model-00001-of-00003.safetensors",
66
+ "model.layers.5.channel_mixer.l3.weight": "model-00001-of-00003.safetensors",
67
+ "model.layers.5.token_mixer.out_proj.weight": "model-00001-of-00003.safetensors",
68
+ "model.layers.5.token_mixer.qkvu_proj.weight": "model-00001-of-00003.safetensors",
69
+ "model.layers.6.channel_mixer.l1.weight": "model-00001-of-00003.safetensors",
70
+ "model.layers.6.channel_mixer.l2.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.6.channel_mixer.l3.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.6.token_mixer.out_proj.weight": "model-00001-of-00003.safetensors",
73
+ "model.layers.6.token_mixer.qkvu_proj.weight": "model-00001-of-00003.safetensors",
74
+ "model.layers.7.channel_mixer.l1.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.7.channel_mixer.l2.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.7.channel_mixer.l3.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.7.token_mixer.out_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.7.token_mixer.qkvu_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.8.channel_mixer.l1.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.8.channel_mixer.l2.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.8.channel_mixer.l3.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.8.token_mixer.out_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.8.token_mixer.qkvu_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.9.channel_mixer.l1.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.9.channel_mixer.l2.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.9.channel_mixer.l3.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.9.token_mixer.out_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.9.token_mixer.qkvu_proj.weight": "model-00002-of-00003.safetensors"
89
+ }
90
+ }