Hugging Face's logo

tarekziade
/
wikipedia-summaries-t5-small

Text2Text Generation
Transformers
ONNX
Safetensors
t5
text-generation-inference
Inference Endpoints
Model card Files Community
tarekziade commited on
Commit
1883ef9
•
1 Parent(s): 65a8d05

Upload 13 files

Browse files
Files changed (12) hide show
  1. config.json +1 -2
  2. onnx/decoder_model.onnx +3 -0
  3. onnx/decoder_model_merged.onnx +3 -0
  4. onnx/decoder_model_merged_quantized.onnx +3 -0
  5. onnx/decoder_model_quantized.onnx +3 -0
  6. onnx/decoder_with_past_model.onnx +3 -0
  7. onnx/decoder_with_past_model_quantized.onnx +3 -0
  8. onnx/encoder_model.onnx +3 -0
  9. onnx/encoder_model_quantized.onnx +3 -0
  10. quantize_config.json +139 -0
  11. tokenizer.json +0 -0
  12. tokenizer_config.json +111 -0
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "t5-small",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
@@ -54,7 +54,6 @@
54
  "prefix": "translate English to Romanian: "
55
  }
56
  },
57
- "torch_dtype": "float32",
58
  "transformers_version": "4.36.2",
59
  "use_cache": true,
60
  "vocab_size": 32128
 
1
  {
2
+ "_name_or_path": "tarekziade/wikipedia-summaries-t5-small",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
 
54
  "prefix": "translate English to Romanian: "
55
  }
56
  },
 
57
  "transformers_version": "4.36.2",
58
  "use_cache": true,
59
  "vocab_size": 32128
onnx/decoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3112e6c948585a688ba943a635a218b54d6b6b3898ef9d4a837a4df96f176850
3
+ size 166670420
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ef13ddc3f1b45c37e32bd0b13f2adc6d37df2999316fd3041a7afe3e95c2ba7
3
+ size 166832597
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e666a977332337d0acb86b168036089106dd274d12d4bc6d44d0197dc1429613
3
+ size 42431545
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0f1aca08cc0de7009371cb1d504b49103856c3a326112bcdc932ba1679022b1
3
+ size 42154656
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38ca14fa9ea6514f54f2ee38548db6254a55df658408fcb9d57140284e206f36
3
+ size 154076560
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:807da02e9d56c3606ae01541a05d806fb63f6fd1ef01082761ca2705e1bfce9c
3
+ size 38952261
onnx/encoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89f98a598b3c083feb35314a806d299971d5d345bd6d3b9419fcad12fe66487d
3
+ size 141404303
onnx/encoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:223835e19bb595b8cb3faa405036a0dc0b6196564df8b726b40ae652ac6d8d2d
3
+ size 35640020
quantize_config.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": true,
3
+ "reduce_range": true,
4
+ "per_model_config": {
5
+ "decoder_with_past_model": {
6
+ "op_types": [
7
+ "Pow",
8
+ "Div",
9
+ "Shape",
10
+ "Expand",
11
+ "Softmax",
12
+ "Log",
13
+ "ConstantOfShape",
14
+ "Concat",
15
+ "Neg",
16
+ "LessOrEqual",
17
+ "Constant",
18
+ "Range",
19
+ "Where",
20
+ "Tile",
21
+ "Slice",
22
+ "Reshape",
23
+ "ReduceMean",
24
+ "Gather",
25
+ "MatMul",
26
+ "Cast",
27
+ "Min",
28
+ "Transpose",
29
+ "Less",
30
+ "Sqrt",
31
+ "Add",
32
+ "Mul",
33
+ "Unsqueeze",
34
+ "Relu",
35
+ "Sub"
36
+ ],
37
+ "weight_type": "QInt8"
38
+ },
39
+ "decoder_model": {
40
+ "op_types": [
41
+ "Pow",
42
+ "Div",
43
+ "Shape",
44
+ "Expand",
45
+ "Softmax",
46
+ "Log",
47
+ "ConstantOfShape",
48
+ "Concat",
49
+ "Neg",
50
+ "LessOrEqual",
51
+ "Constant",
52
+ "Range",
53
+ "Where",
54
+ "Tile",
55
+ "Reshape",
56
+ "ReduceMean",
57
+ "Gather",
58
+ "MatMul",
59
+ "Cast",
60
+ "Min",
61
+ "Transpose",
62
+ "Less",
63
+ "Sqrt",
64
+ "Add",
65
+ "Mul",
66
+ "Unsqueeze",
67
+ "Relu",
68
+ "Sub"
69
+ ],
70
+ "weight_type": "QInt8"
71
+ },
72
+ "encoder_model": {
73
+ "op_types": [
74
+ "Pow",
75
+ "Abs",
76
+ "Div",
77
+ "Shape",
78
+ "Softmax",
79
+ "Log",
80
+ "ConstantOfShape",
81
+ "Concat",
82
+ "Greater",
83
+ "Constant",
84
+ "Range",
85
+ "Where",
86
+ "Reshape",
87
+ "ReduceMean",
88
+ "Gather",
89
+ "MatMul",
90
+ "Cast",
91
+ "Min",
92
+ "Transpose",
93
+ "Less",
94
+ "Sqrt",
95
+ "Add",
96
+ "Mul",
97
+ "Unsqueeze",
98
+ "Relu",
99
+ "Sub"
100
+ ],
101
+ "weight_type": "QInt8"
102
+ },
103
+ "decoder_model_merged": {
104
+ "op_types": [
105
+ "Pow",
106
+ "Div",
107
+ "Shape",
108
+ "Expand",
109
+ "Softmax",
110
+ "Log",
111
+ "ConstantOfShape",
112
+ "Concat",
113
+ "Neg",
114
+ "If",
115
+ "LessOrEqual",
116
+ "Constant",
117
+ "Range",
118
+ "Where",
119
+ "Tile",
120
+ "Slice",
121
+ "Reshape",
122
+ "ReduceMean",
123
+ "Gather",
124
+ "MatMul",
125
+ "Cast",
126
+ "Min",
127
+ "Transpose",
128
+ "Less",
129
+ "Sqrt",
130
+ "Add",
131
+ "Mul",
132
+ "Unsqueeze",
133
+ "Relu",
134
+ "Sub"
135
+ ],
136
+ "weight_type": "QInt8"
137
+ }
138
+ }
139
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "clean_up_tokenization_spaces": true,
105
+ "eos_token": "</s>",
106
+ "extra_ids": 100,
107
+ "model_max_length": 512,
108
+ "pad_token": "<pad>",
109
+ "tokenizer_class": "T5Tokenizer",
110
+ "unk_token": "<unk>"
111
+ }