Upload folder using huggingface_hub
Browse files- Telling/config.json +62 -0
- Telling/label2id.json +19 -0
- Telling/model.safetensors +3 -0
- Telling/special_tokens_map.json +7 -0
- Telling/tokenizer.json +0 -0
- Telling/tokenizer_config.json +58 -0
- Telling/vocab.txt +0 -0
Telling/config.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForTokenClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "O",
|
| 13 |
+
"1": "Add3ressee",
|
| 14 |
+
"2": "Add5ressee",
|
| 15 |
+
"3": "Addressee",
|
| 16 |
+
"4": "Addrime",
|
| 17 |
+
"5": "Add\u0631\u062f\u0647",
|
| 18 |
+
"6": "Add\u0636\u0627Addressee",
|
| 19 |
+
"7": "Add\u0636\u0627ressee",
|
| 20 |
+
"8": "Add\u06f3ressee",
|
| 21 |
+
"9": "Atopic",
|
| 22 |
+
"10": "Means",
|
| 23 |
+
"11": "Medium",
|
| 24 |
+
"12": "Message",
|
| 25 |
+
"13": "Speaker",
|
| 26 |
+
"14": "Time",
|
| 27 |
+
"15": "Topic",
|
| 28 |
+
"16": "\u0645Means"
|
| 29 |
+
},
|
| 30 |
+
"initializer_range": 0.02,
|
| 31 |
+
"intermediate_size": 3072,
|
| 32 |
+
"label2id": {
|
| 33 |
+
"Add3ressee": 1,
|
| 34 |
+
"Add5ressee": 2,
|
| 35 |
+
"Addressee": 3,
|
| 36 |
+
"Addrime": 4,
|
| 37 |
+
"Add\u0631\u062f\u0647": 5,
|
| 38 |
+
"Add\u0636\u0627Addressee": 6,
|
| 39 |
+
"Add\u0636\u0627ressee": 7,
|
| 40 |
+
"Add\u06f3ressee": 8,
|
| 41 |
+
"Atopic": 9,
|
| 42 |
+
"Means": 10,
|
| 43 |
+
"Medium": 11,
|
| 44 |
+
"Message": 12,
|
| 45 |
+
"O": 0,
|
| 46 |
+
"Speaker": 13,
|
| 47 |
+
"Time": 14,
|
| 48 |
+
"Topic": 15,
|
| 49 |
+
"\u0645Means": 16
|
| 50 |
+
},
|
| 51 |
+
"layer_norm_eps": 1e-12,
|
| 52 |
+
"max_position_embeddings": 512,
|
| 53 |
+
"model_type": "bert",
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_hidden_layers": 12,
|
| 56 |
+
"pad_token_id": 0,
|
| 57 |
+
"position_embedding_type": "absolute",
|
| 58 |
+
"transformers_version": "4.57.3",
|
| 59 |
+
"type_vocab_size": 2,
|
| 60 |
+
"use_cache": true,
|
| 61 |
+
"vocab_size": 100000
|
| 62 |
+
}
|
Telling/label2id.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"O": 0,
|
| 3 |
+
"Add3ressee": 1,
|
| 4 |
+
"Add5ressee": 2,
|
| 5 |
+
"Addressee": 3,
|
| 6 |
+
"Addrime": 4,
|
| 7 |
+
"Addرده": 5,
|
| 8 |
+
"AddضاAddressee": 6,
|
| 9 |
+
"Addضاressee": 7,
|
| 10 |
+
"Add۳ressee": 8,
|
| 11 |
+
"Atopic": 9,
|
| 12 |
+
"Means": 10,
|
| 13 |
+
"Medium": 11,
|
| 14 |
+
"Message": 12,
|
| 15 |
+
"Speaker": 13,
|
| 16 |
+
"Time": 14,
|
| 17 |
+
"Topic": 15,
|
| 18 |
+
"مMeans": 16
|
| 19 |
+
}
|
Telling/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73386729b2947083c71d2e0e52e4c412f8c343ff1cba0a3e86e9d13e45c6a8cc
|
| 3 |
+
size 649078660
|
Telling/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 |
+
}
|
Telling/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Telling/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[MASK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[SEP]",
|
| 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_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
+
"never_split": null,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"strip_accents": null,
|
| 55 |
+
"tokenize_chinese_chars": true,
|
| 56 |
+
"tokenizer_class": "BertTokenizer",
|
| 57 |
+
"unk_token": "[UNK]"
|
| 58 |
+
}
|
Telling/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|