first commit
Browse files- .gitattributes +1 -0
- config.json +62 -0
- model_optimized.onnx +3 -0
- ort_config.json +39 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +19 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "../output/xlm-minilmv2-multilingual/config.json",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 384,
|
13 |
+
"id2label": {
|
14 |
+
"0": "toxicity",
|
15 |
+
"1": "severe_toxicity",
|
16 |
+
"2": "obscene",
|
17 |
+
"3": "identity_attack",
|
18 |
+
"4": "insult",
|
19 |
+
"5": "threat",
|
20 |
+
"6": "sexual_explicit",
|
21 |
+
"7": "male",
|
22 |
+
"8": "female",
|
23 |
+
"9": "homosexual_gay_or_lesbian",
|
24 |
+
"10": "christian",
|
25 |
+
"11": "jewish",
|
26 |
+
"12": "muslim",
|
27 |
+
"13": "black",
|
28 |
+
"14": "white",
|
29 |
+
"15": "psychiatric_or_mental_illness"
|
30 |
+
},
|
31 |
+
"initializer_range": 0.02,
|
32 |
+
"intermediate_size": 1536,
|
33 |
+
"label2id": {
|
34 |
+
"black": 13,
|
35 |
+
"christian": 10,
|
36 |
+
"female": 8,
|
37 |
+
"homosexual_gay_or_lesbian": 9,
|
38 |
+
"identity_attack": 3,
|
39 |
+
"insult": 4,
|
40 |
+
"jewish": 11,
|
41 |
+
"male": 7,
|
42 |
+
"muslim": 12,
|
43 |
+
"obscene": 2,
|
44 |
+
"psychiatric_or_mental_illness": 15,
|
45 |
+
"severe_toxicity": 1,
|
46 |
+
"sexual_explicit": 6,
|
47 |
+
"threat": 5,
|
48 |
+
"toxicity": 0,
|
49 |
+
"white": 14
|
50 |
+
},
|
51 |
+
"layer_norm_eps": 1e-05,
|
52 |
+
"max_position_embeddings": 514,
|
53 |
+
"model_type": "xlm-roberta",
|
54 |
+
"num_attention_heads": 12,
|
55 |
+
"num_hidden_layers": 6,
|
56 |
+
"pad_token_id": 1,
|
57 |
+
"position_embedding_type": "absolute",
|
58 |
+
"transformers_version": "4.30.0",
|
59 |
+
"type_vocab_size": 1,
|
60 |
+
"use_cache": true,
|
61 |
+
"vocab_size": 250002
|
62 |
+
}
|
model_optimized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c719c36c2034885ebad89686ae13c1a583c9943e9d0bc79f665259a6be8a5aa1
|
3 |
+
size 428024965
|
ort_config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": false,
|
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": 1,
|
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": "1.14.1",
|
36 |
+
"quantization": {},
|
37 |
+
"transformers_version": "4.30.0",
|
38 |
+
"use_external_data_format": false
|
39 |
+
}
|
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 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
|
3 |
+
size 17082660
|
tokenizer_config.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"cls_token": "<s>",
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"mask_token": {
|
7 |
+
"__type": "AddedToken",
|
8 |
+
"content": "<mask>",
|
9 |
+
"lstrip": true,
|
10 |
+
"normalized": true,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"model_max_length": 512,
|
15 |
+
"pad_token": "<pad>",
|
16 |
+
"sep_token": "</s>",
|
17 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
18 |
+
"unk_token": "<unk>"
|
19 |
+
}
|