anpigon commited on
Commit
a75d92c
1 Parent(s): cc5cb21

Add model_quantized.onnx and remove config files

Browse files
onnx/config.json DELETED
@@ -1,30 +0,0 @@
1
- {
2
- "_name_or_path": "roberta_base_qa_onnx",
3
- "architectures": [
4
- "RobertaModel"
5
- ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "bos_token_id": 0,
8
- "classifier_dropout": null,
9
- "eos_token_id": 2,
10
- "export_model_type": "transformer",
11
- "gradient_checkpointing": false,
12
- "hidden_act": "gelu",
13
- "hidden_dropout_prob": 0.1,
14
- "hidden_size": 768,
15
- "initializer_range": 0.02,
16
- "intermediate_size": 3072,
17
- "layer_norm_eps": 1e-05,
18
- "max_position_embeddings": 514,
19
- "model_type": "roberta",
20
- "num_attention_heads": 12,
21
- "num_hidden_layers": 12,
22
- "pad_token_id": 1,
23
- "position_embedding_type": "absolute",
24
- "tokenizer_class": "BertTokenizer",
25
- "torch_dtype": "float32",
26
- "transformers_version": "4.37.2",
27
- "type_vocab_size": 1,
28
- "use_cache": true,
29
- "vocab_size": 32000
30
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
onnx/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47d2e905b4713257ffc0c605f37befc2f3c2ea46793b01346609b50f7f1647b3
3
+ size 110517465
onnx/ort_config.json DELETED
@@ -1,39 +0,0 @@
1
- {
2
- "one_external_file": true,
3
- "opset": null,
4
- "optimization": {
5
- "disable_attention": null,
6
- "disable_attention_fusion": false,
7
- "disable_bias_gelu": null,
8
- "disable_bias_gelu_fusion": false,
9
- "disable_bias_skip_layer_norm": null,
10
- "disable_bias_skip_layer_norm_fusion": false,
11
- "disable_embed_layer_norm": true,
12
- "disable_embed_layer_norm_fusion": true,
13
- "disable_gelu": null,
14
- "disable_gelu_fusion": false,
15
- "disable_group_norm_fusion": true,
16
- "disable_layer_norm": null,
17
- "disable_layer_norm_fusion": false,
18
- "disable_packed_kv": true,
19
- "disable_rotary_embeddings": false,
20
- "disable_shape_inference": true,
21
- "disable_skip_layer_norm": null,
22
- "disable_skip_layer_norm_fusion": false,
23
- "enable_gelu_approximation": false,
24
- "enable_gemm_fast_gelu_fusion": false,
25
- "enable_transformers_specific_optimizations": true,
26
- "fp16": false,
27
- "no_attention_mask": false,
28
- "optimization_level": 2,
29
- "optimize_for_gpu": false,
30
- "optimize_with_onnxruntime_only": null,
31
- "use_mask_index": false,
32
- "use_multi_head_attention": false,
33
- "use_raw_attention_mask": false
34
- },
35
- "optimum_version": "1.18.0.dev0",
36
- "quantization": {},
37
- "transformers_version": "4.37.2",
38
- "use_external_data_format": false
39
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
onnx/special_tokens_map.json DELETED
@@ -1,51 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "[CLS]",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "cls_token": {
10
- "content": "[CLS]",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "eos_token": {
17
- "content": "[SEP]",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "mask_token": {
24
- "content": "[MASK]",
25
- "lstrip": false,
26
- "normalized": false,
27
- "rstrip": false,
28
- "single_word": false
29
- },
30
- "pad_token": {
31
- "content": "[PAD]",
32
- "lstrip": false,
33
- "normalized": false,
34
- "rstrip": false,
35
- "single_word": false
36
- },
37
- "sep_token": {
38
- "content": "[SEP]",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false
43
- },
44
- "unk_token": {
45
- "content": "[UNK]",
46
- "lstrip": false,
47
- "normalized": false,
48
- "rstrip": false,
49
- "single_word": false
50
- }
51
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
onnx/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
onnx/tokenizer_config.json DELETED
@@ -1,66 +0,0 @@
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
- "4": {
36
- "content": "[MASK]",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- }
43
- },
44
- "bos_token": "[CLS]",
45
- "clean_up_tokenization_spaces": true,
46
- "cls_token": "[CLS]",
47
- "do_basic_tokenize": true,
48
- "do_lower_case": false,
49
- "eos_token": "[SEP]",
50
- "mask_token": "[MASK]",
51
- "max_length": 128,
52
- "model_max_length": 512,
53
- "never_split": null,
54
- "pad_to_multiple_of": null,
55
- "pad_token": "[PAD]",
56
- "pad_token_type_id": 0,
57
- "padding_side": "right",
58
- "sep_token": "[SEP]",
59
- "stride": 0,
60
- "strip_accents": null,
61
- "tokenize_chinese_chars": true,
62
- "tokenizer_class": "BertTokenizer",
63
- "truncation_side": "right",
64
- "truncation_strategy": "longest_first",
65
- "unk_token": "[UNK]"
66
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
onnx/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
onnx/vocab.txt DELETED
The diff for this file is too large to render. See raw diff