Xenova HF staff commited on
Commit
019333b
1 Parent(s): c06f3b7

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "hf-tiny-model-private/tiny-random-ErnieMForQuestionAnswering",
3
+ "act_dropout": 0.0,
4
+ "architectures": [
5
+ "ErnieMForQuestionAnswering"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 32,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 37,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "ernie_m",
17
+ "num_attention_heads": 4,
18
+ "num_hidden_layers": 5,
19
+ "pad_token_id": 1,
20
+ "transformers_version": "4.38.2",
21
+ "type_vocab_size": 16,
22
+ "vocab_size": 250002
23
+ }
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5aca2c640804908ba4a3898194da6334adff3b813d1326864a30d0924fe0660
3
+ size 32312890
onnx/model_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80eb60e2c64f35849bdae6c55c54ebc8238a0ab5583a48ec79c87a2510b9014d
3
+ size 32206226
onnx/model_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f58f1fa34e3af888208bdbbb9fa978033def055fb7c1fbf4509ff33776d8f85f
3
+ size 16256417
onnx/model_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5558d3ad6163e048262adaf8bf4beb5e85aef24448ad22b2a901f103428fc1e9
3
+ size 8252511
onnx/model_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f08040faadf3fcb7b8a7ee88c452f77575e93d06c4b3733146f54c52aa747d9
3
+ size 32210743
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5558d3ad6163e048262adaf8bf4beb5e85aef24448ad22b2a901f103428fc1e9
3
+ size 8252511
onnx/model_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7648aae7274144208651ecae66f8f9720c594d4aed9075ad390199ff41a75a2f
3
+ size 8252510
quantize_config.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "fp16": {},
3
+ "q8": {
4
+ "per_model_config": {
5
+ "model": {
6
+ "op_types": [
7
+ "Add",
8
+ "Cast",
9
+ "Concat",
10
+ "Constant",
11
+ "ConstantOfShape",
12
+ "CumSum",
13
+ "Div",
14
+ "Erf",
15
+ "Gather",
16
+ "Identity",
17
+ "MatMul",
18
+ "Mul",
19
+ "Pow",
20
+ "ReduceMean",
21
+ "Reshape",
22
+ "Shape",
23
+ "Softmax",
24
+ "Split",
25
+ "Sqrt",
26
+ "Squeeze",
27
+ "Sub",
28
+ "Transpose",
29
+ "Unsqueeze"
30
+ ],
31
+ "weight_type": "QInt8"
32
+ }
33
+ },
34
+ "per_channel": true,
35
+ "reduce_range": true
36
+ },
37
+ "int8": {
38
+ "per_model_config": {
39
+ "model": {
40
+ "op_types": [
41
+ "Add",
42
+ "Cast",
43
+ "Concat",
44
+ "Constant",
45
+ "ConstantOfShape",
46
+ "CumSum",
47
+ "Div",
48
+ "Erf",
49
+ "Gather",
50
+ "Identity",
51
+ "MatMul",
52
+ "Mul",
53
+ "Pow",
54
+ "ReduceMean",
55
+ "Reshape",
56
+ "Shape",
57
+ "Softmax",
58
+ "Split",
59
+ "Sqrt",
60
+ "Squeeze",
61
+ "Sub",
62
+ "Transpose",
63
+ "Unsqueeze"
64
+ ],
65
+ "weight_type": "QInt8"
66
+ }
67
+ },
68
+ "per_channel": true,
69
+ "reduce_range": true
70
+ },
71
+ "uint8": {
72
+ "per_model_config": {
73
+ "model": {
74
+ "op_types": [
75
+ "Add",
76
+ "Cast",
77
+ "Concat",
78
+ "Constant",
79
+ "ConstantOfShape",
80
+ "CumSum",
81
+ "Div",
82
+ "Erf",
83
+ "Gather",
84
+ "Identity",
85
+ "MatMul",
86
+ "Mul",
87
+ "Pow",
88
+ "ReduceMean",
89
+ "Reshape",
90
+ "Shape",
91
+ "Softmax",
92
+ "Split",
93
+ "Sqrt",
94
+ "Squeeze",
95
+ "Sub",
96
+ "Transpose",
97
+ "Unsqueeze"
98
+ ],
99
+ "weight_type": "QUInt8"
100
+ }
101
+ },
102
+ "per_channel": true,
103
+ "reduce_range": true
104
+ },
105
+ "q4": {
106
+ "block_size": 32,
107
+ "is_symmetric": true,
108
+ "accuracy_level": null
109
+ },
110
+ "bnb4": {
111
+ "block_size": 64,
112
+ "quant_type": 1
113
+ }
114
+ }
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[CLS]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[PAD]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "encoding": "utf8",
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "sp_model_kwargs": {},
53
+ "tokenizer_class": "ErnieMTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff