Add the encoder's tokenizer and config (byte-identical to ScienceSoft/scnsoft-pii-encoder at b1a36210) so the directory loads in the engine
Browse files- .gitattributes +1 -0
- MANIFEST.sha256 +4 -0
- config.json +53 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +55 -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
|
MANIFEST.sha256
CHANGED
|
@@ -2,3 +2,7 @@
|
|
| 2 |
7bf1257edaa508b110646407f151352c117e935001da42bd4f96810c53fb75e0 THIRD_PARTY_NOTICES.md
|
| 3 |
ddaff31d9e705ed3eb610467b3b783acd4116892887641c25db538a7215687f1 doc_labels.json
|
| 4 |
0c9c1780673d719310afd1bce2538d8e078ea2adf0bc3a6e397c564ac6486b6e onnx/model_quantized.onnx
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
7bf1257edaa508b110646407f151352c117e935001da42bd4f96810c53fb75e0 THIRD_PARTY_NOTICES.md
|
| 3 |
ddaff31d9e705ed3eb610467b3b783acd4116892887641c25db538a7215687f1 doc_labels.json
|
| 4 |
0c9c1780673d719310afd1bce2538d8e078ea2adf0bc3a6e397c564ac6486b6e onnx/model_quantized.onnx
|
| 5 |
+
a514807cffabd8abaf028cfaffe7ff0c4f60b97ea2db80c41f14172ae6b018ca tokenizer.json
|
| 6 |
+
1e840bedc5fac622c796f19c2021c4040641326fcacb9d18ab87c5d2e050e0db config.json
|
| 7 |
+
ccf223ba3d5b3cc7fa6c3bf451f3bb40557a5c92b0aa33f63d17802ff1a96fd9 tokenizer_config.json
|
| 8 |
+
06e405a36dfe4b9604f484f6a1e619af1a7f7d09e34a8555eb0b77b66318067f special_tokens_map.json
|
config.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"XLMRobertaForTokenClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "O",
|
| 15 |
+
"1": "B-PERSON",
|
| 16 |
+
"2": "I-PERSON",
|
| 17 |
+
"3": "B-ORGANIZATION",
|
| 18 |
+
"4": "I-ORGANIZATION",
|
| 19 |
+
"5": "B-LOCATION",
|
| 20 |
+
"6": "I-LOCATION",
|
| 21 |
+
"7": "B-ADDRESS",
|
| 22 |
+
"8": "I-ADDRESS",
|
| 23 |
+
"9": "B-DATE_TIME",
|
| 24 |
+
"10": "I-DATE_TIME"
|
| 25 |
+
},
|
| 26 |
+
"initializer_range": 0.02,
|
| 27 |
+
"intermediate_size": 3072,
|
| 28 |
+
"label2id": {
|
| 29 |
+
"B-ADDRESS": 7,
|
| 30 |
+
"B-DATE_TIME": 9,
|
| 31 |
+
"B-LOCATION": 5,
|
| 32 |
+
"B-ORGANIZATION": 3,
|
| 33 |
+
"B-PERSON": 1,
|
| 34 |
+
"I-ADDRESS": 8,
|
| 35 |
+
"I-DATE_TIME": 10,
|
| 36 |
+
"I-LOCATION": 6,
|
| 37 |
+
"I-ORGANIZATION": 4,
|
| 38 |
+
"I-PERSON": 2,
|
| 39 |
+
"O": 0
|
| 40 |
+
},
|
| 41 |
+
"layer_norm_eps": 1e-05,
|
| 42 |
+
"max_position_embeddings": 514,
|
| 43 |
+
"model_type": "xlm-roberta",
|
| 44 |
+
"num_attention_heads": 12,
|
| 45 |
+
"num_hidden_layers": 12,
|
| 46 |
+
"output_past": true,
|
| 47 |
+
"pad_token_id": 1,
|
| 48 |
+
"position_embedding_type": "absolute",
|
| 49 |
+
"transformers_version": "4.57.1",
|
| 50 |
+
"type_vocab_size": 1,
|
| 51 |
+
"use_cache": true,
|
| 52 |
+
"vocab_size": 250002
|
| 53 |
+
}
|
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:a514807cffabd8abaf028cfaffe7ff0c4f60b97ea2db80c41f14172ae6b018ca
|
| 3 |
+
size 17082987
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 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": "</s>",
|
| 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": true,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "<mask>",
|
| 50 |
+
"model_max_length": 512,
|
| 51 |
+
"pad_token": "<pad>",
|
| 52 |
+
"sep_token": "</s>",
|
| 53 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 54 |
+
"unk_token": "<unk>"
|
| 55 |
+
}
|