Hugging Face's logo

ayousanz
/
any-ONNX-models

ONNX
Model card Files Community
ayousanz commited on
Commit
26ff328
•
1 Parent(s): e058778

Upload folder using huggingface_hub

Browse files
Files changed (21) hide show
  1. .gitattributes +7 -0
  2. rinna/japanese-gpt-neox-3.6b/Constant_251_attr__value +3 -0
  3. rinna/japanese-gpt-neox-3.6b/Constant_265_attr__value +3 -0
  4. rinna/japanese-gpt-neox-3.6b/_gpt_neox_layers.0_attention_rotary_emb_Constant_5_attr__value +3 -0
  5. rinna/japanese-gpt-neox-3.6b/_gpt_neox_layers.0_attention_rotary_emb_Constant_attr__value +3 -0
  6. rinna/japanese-gpt-neox-3.6b/config.json +28 -0
  7. rinna/japanese-gpt-neox-3.6b/generation_config.json +6 -0
  8. rinna/japanese-gpt-neox-3.6b/onnx/decoder_model.onnx +3 -0
  9. rinna/japanese-gpt-neox-3.6b/onnx/decoder_model.onnx_data +3 -0
  10. rinna/japanese-gpt-neox-3.6b/onnx/decoder_model_merged.onnx +3 -0
  11. rinna/japanese-gpt-neox-3.6b/onnx/decoder_model_merged.onnx_data +3 -0
  12. rinna/japanese-gpt-neox-3.6b/onnx/decoder_model_merged_quantized.onnx +3 -0
  13. rinna/japanese-gpt-neox-3.6b/onnx/decoder_model_quantized.onnx +3 -0
  14. rinna/japanese-gpt-neox-3.6b/onnx/decoder_with_past_model.onnx +3 -0
  15. rinna/japanese-gpt-neox-3.6b/onnx/decoder_with_past_model.onnx_data +3 -0
  16. rinna/japanese-gpt-neox-3.6b/onnx/decoder_with_past_model_quantized.onnx +3 -0
  17. rinna/japanese-gpt-neox-3.6b/quantize_config.json +103 -0
  18. rinna/japanese-gpt-neox-3.6b/special_tokens_map.json +9 -0
  19. rinna/japanese-gpt-neox-3.6b/spiece.model +3 -0
  20. rinna/japanese-gpt-neox-3.6b/tokenizer.json +0 -0
  21. rinna/japanese-gpt-neox-3.6b/tokenizer_config.json +17 -0
.gitattributes CHANGED
@@ -57,3 +57,10 @@ rinna/japanese-gpt-neox-3.6b-instruction-ppo/_gpt_neox_layers.0_attention_rotary
57
  rinna/japanese-gpt-neox-3.6b-instruction-ppo/onnx/decoder_model.onnx_data filter=lfs diff=lfs merge=lfs -text
58
  rinna/japanese-gpt-neox-3.6b-instruction-ppo/onnx/decoder_model_merged.onnx_data filter=lfs diff=lfs merge=lfs -text
59
  rinna/japanese-gpt-neox-3.6b-instruction-ppo/onnx/decoder_with_past_model.onnx_data filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
57
  rinna/japanese-gpt-neox-3.6b-instruction-ppo/onnx/decoder_model.onnx_data filter=lfs diff=lfs merge=lfs -text
58
  rinna/japanese-gpt-neox-3.6b-instruction-ppo/onnx/decoder_model_merged.onnx_data filter=lfs diff=lfs merge=lfs -text
59
  rinna/japanese-gpt-neox-3.6b-instruction-ppo/onnx/decoder_with_past_model.onnx_data filter=lfs diff=lfs merge=lfs -text
60
+ rinna/japanese-gpt-neox-3.6b/Constant_251_attr__value filter=lfs diff=lfs merge=lfs -text
61
+ rinna/japanese-gpt-neox-3.6b/Constant_265_attr__value filter=lfs diff=lfs merge=lfs -text
62
+ rinna/japanese-gpt-neox-3.6b/_gpt_neox_layers.0_attention_rotary_emb_Constant_5_attr__value filter=lfs diff=lfs merge=lfs -text
63
+ rinna/japanese-gpt-neox-3.6b/_gpt_neox_layers.0_attention_rotary_emb_Constant_attr__value filter=lfs diff=lfs merge=lfs -text
64
+ rinna/japanese-gpt-neox-3.6b/onnx/decoder_model.onnx_data filter=lfs diff=lfs merge=lfs -text
65
+ rinna/japanese-gpt-neox-3.6b/onnx/decoder_model_merged.onnx_data filter=lfs diff=lfs merge=lfs -text
66
+ rinna/japanese-gpt-neox-3.6b/onnx/decoder_with_past_model.onnx_data filter=lfs diff=lfs merge=lfs -text
rinna/japanese-gpt-neox-3.6b/Constant_251_attr__value ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83dd5f1a5a07912d2e7dbb73b75edeb2ce4c1f1d6ec48144a887bd4a4f72325b
3
+ size 4194304
rinna/japanese-gpt-neox-3.6b/Constant_265_attr__value ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83dd5f1a5a07912d2e7dbb73b75edeb2ce4c1f1d6ec48144a887bd4a4f72325b
3
+ size 4194304
rinna/japanese-gpt-neox-3.6b/_gpt_neox_layers.0_attention_rotary_emb_Constant_5_attr__value ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8b2c3afb641a83b5f366889f4cfd3d6fef51b67e5557d3d4805ae6723eaaad3
3
+ size 1048576
rinna/japanese-gpt-neox-3.6b/_gpt_neox_layers.0_attention_rotary_emb_Constant_attr__value ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6edec9e4b8ef2a104c6df52da29fdde53fdda740e89f909133154cbcbd5f7be3
3
+ size 1048576
rinna/japanese-gpt-neox-3.6b/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "rinna/japanese-gpt-neox-3.6b",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 2,
8
+ "classifier_dropout": 0.1,
9
+ "eos_token_id": 3,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout": 0.0,
12
+ "hidden_size": 2816,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 11264,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 2048,
17
+ "model_type": "gpt_neox",
18
+ "num_attention_heads": 22,
19
+ "num_hidden_layers": 36,
20
+ "rope_scaling": null,
21
+ "rotary_emb_base": 10000,
22
+ "rotary_pct": 1.0,
23
+ "tie_word_embeddings": false,
24
+ "transformers_version": "4.33.2",
25
+ "use_cache": true,
26
+ "use_parallel_residual": false,
27
+ "vocab_size": 32000
28
+ }
rinna/japanese-gpt-neox-3.6b/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 3,
5
+ "transformers_version": "4.33.2"
6
+ }
rinna/japanese-gpt-neox-3.6b/onnx/decoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c28a350f3205a7b6370777a9efe42b3fa01e40f28bdbfb0f8992321c728ca100
3
+ size 8567754
rinna/japanese-gpt-neox-3.6b/onnx/decoder_model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:414392848b0e7682c53a3f49c5d48cf8214e31233e67778de8d5e9cb1a1e2919
3
+ size 14428981248
rinna/japanese-gpt-neox-3.6b/onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48da761297c439271f3f76019a2d6c3a1c7cf45ffb8d48723000f568be922552
3
+ size 17150202
rinna/japanese-gpt-neox-3.6b/onnx/decoder_model_merged.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:414392848b0e7682c53a3f49c5d48cf8214e31233e67778de8d5e9cb1a1e2919
3
+ size 14428981248
rinna/japanese-gpt-neox-3.6b/onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33d0f469dbec5422fe9cda5a6dc41267c94a9788e0f4dd6da47e59c924636d75
3
+ size 3634824069
rinna/japanese-gpt-neox-3.6b/onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15906c7ae01fd3f6564467ae9992d557edb94f785f57757e965fc92e177708c7
3
+ size 3625355276
rinna/japanese-gpt-neox-3.6b/onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:098ef8799fe61cb4d2973c9457d06756045ac415bc8314e06ab8dc5b2b051184
3
+ size 8618967
rinna/japanese-gpt-neox-3.6b/onnx/decoder_with_past_model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:414392848b0e7682c53a3f49c5d48cf8214e31233e67778de8d5e9cb1a1e2919
3
+ size 14428981248
rinna/japanese-gpt-neox-3.6b/onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3da8efd4a49c24be8ad62078a679123261d408fe0e0b456e95deebf04e174656
3
+ size 3625414981
rinna/japanese-gpt-neox-3.6b/quantize_config.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": true,
3
+ "reduce_range": true,
4
+ "per_model_config": {
5
+ "decoder_model_merged": {
6
+ "op_types": [
7
+ "Erf",
8
+ "Unsqueeze",
9
+ "Sqrt",
10
+ "Softmax",
11
+ "Cast",
12
+ "Slice",
13
+ "Tile",
14
+ "ConstantOfShape",
15
+ "Mul",
16
+ "Gather",
17
+ "If",
18
+ "Shape",
19
+ "Neg",
20
+ "Expand",
21
+ "Transpose",
22
+ "Reshape",
23
+ "MatMul",
24
+ "GatherElements",
25
+ "Concat",
26
+ "Add",
27
+ "Sub",
28
+ "Squeeze",
29
+ "Where",
30
+ "Range",
31
+ "Constant",
32
+ "ReduceMean",
33
+ "Pow",
34
+ "Div"
35
+ ],
36
+ "weight_type": "QInt8"
37
+ },
38
+ "decoder_model": {
39
+ "op_types": [
40
+ "Erf",
41
+ "Unsqueeze",
42
+ "Sqrt",
43
+ "Softmax",
44
+ "Cast",
45
+ "Slice",
46
+ "Tile",
47
+ "ConstantOfShape",
48
+ "Mul",
49
+ "Gather",
50
+ "Shape",
51
+ "Neg",
52
+ "Expand",
53
+ "Transpose",
54
+ "Reshape",
55
+ "MatMul",
56
+ "GatherElements",
57
+ "Concat",
58
+ "Add",
59
+ "Sub",
60
+ "Squeeze",
61
+ "Where",
62
+ "Range",
63
+ "Constant",
64
+ "ReduceMean",
65
+ "Pow",
66
+ "Div"
67
+ ],
68
+ "weight_type": "QInt8"
69
+ },
70
+ "decoder_with_past_model": {
71
+ "op_types": [
72
+ "Erf",
73
+ "Unsqueeze",
74
+ "Sqrt",
75
+ "Softmax",
76
+ "Cast",
77
+ "Slice",
78
+ "Tile",
79
+ "ConstantOfShape",
80
+ "Mul",
81
+ "Gather",
82
+ "Shape",
83
+ "Neg",
84
+ "Expand",
85
+ "Transpose",
86
+ "Reshape",
87
+ "MatMul",
88
+ "GatherElements",
89
+ "Concat",
90
+ "Add",
91
+ "Squeeze",
92
+ "Sub",
93
+ "Where",
94
+ "Range",
95
+ "Constant",
96
+ "ReduceMean",
97
+ "Pow",
98
+ "Div"
99
+ ],
100
+ "weight_type": "QInt8"
101
+ }
102
+ }
103
+ }
rinna/japanese-gpt-neox-3.6b/special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "</s>",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "[UNK]"
9
+ }
rinna/japanese-gpt-neox-3.6b/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d78ab344146700112cd41628ac7ce54b79c0868fe0c7c201750d8237b54dbb4
3
+ size 786216
rinna/japanese-gpt-neox-3.6b/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
rinna/japanese-gpt-neox-3.6b/tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [],
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "[CLS]",
6
+ "do_lower_case": false,
7
+ "eos_token": "</s>",
8
+ "extra_ids": 0,
9
+ "legacy": true,
10
+ "mask_token": "[MASK]",
11
+ "model_max_length": 1000000000000000019884624838656,
12
+ "pad_token": "[PAD]",
13
+ "sep_token": "[SEP]",
14
+ "sp_model_kwargs": {},
15
+ "tokenizer_class": "T5Tokenizer",
16
+ "unk_token": "[UNK]"
17
+ }