DominicTWHV commited on
Commit ·
9dedc10
1
Parent(s): 254ce26
New model upload
Browse files- config.json +56 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +23 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaV2ForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "scam",
|
| 14 |
+
"1": "violence",
|
| 15 |
+
"2": "harassment",
|
| 16 |
+
"3": "hate_speech",
|
| 17 |
+
"4": "toxicity",
|
| 18 |
+
"5": "obscenity"
|
| 19 |
+
},
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 3072,
|
| 22 |
+
"label2id": {
|
| 23 |
+
"harassment": 2,
|
| 24 |
+
"hate_speech": 3,
|
| 25 |
+
"obscenity": 5,
|
| 26 |
+
"scam": 0,
|
| 27 |
+
"toxicity": 4,
|
| 28 |
+
"violence": 1
|
| 29 |
+
},
|
| 30 |
+
"layer_norm_eps": 1e-07,
|
| 31 |
+
"legacy": true,
|
| 32 |
+
"max_position_embeddings": 512,
|
| 33 |
+
"max_relative_positions": -1,
|
| 34 |
+
"model_type": "deberta-v2",
|
| 35 |
+
"norm_rel_ebd": "layer_norm",
|
| 36 |
+
"num_attention_heads": 12,
|
| 37 |
+
"num_hidden_layers": 12,
|
| 38 |
+
"pad_token_id": 0,
|
| 39 |
+
"pooler_dropout": 0,
|
| 40 |
+
"pooler_hidden_act": "gelu",
|
| 41 |
+
"pooler_hidden_size": 768,
|
| 42 |
+
"pos_att_type": [
|
| 43 |
+
"p2c",
|
| 44 |
+
"c2p"
|
| 45 |
+
],
|
| 46 |
+
"position_biased_input": false,
|
| 47 |
+
"position_buckets": 256,
|
| 48 |
+
"problem_type": "multi_label_classification",
|
| 49 |
+
"relative_attention": true,
|
| 50 |
+
"share_att_key": true,
|
| 51 |
+
"tie_word_embeddings": true,
|
| 52 |
+
"transformers_version": "5.1.0",
|
| 53 |
+
"type_vocab_size": 0,
|
| 54 |
+
"use_cache": false,
|
| 55 |
+
"vocab_size": 128100
|
| 56 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8aaceebc639ca66d11bcf469d0c0ca96b4e0ea879fb43941c6534d7520904c00
|
| 3 |
+
size 737731560
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "[CLS]",
|
| 5 |
+
"cls_token": "[CLS]",
|
| 6 |
+
"do_lower_case": false,
|
| 7 |
+
"eos_token": "[SEP]",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"[PAD]",
|
| 10 |
+
"[CLS]",
|
| 11 |
+
"[SEP]"
|
| 12 |
+
],
|
| 13 |
+
"is_local": false,
|
| 14 |
+
"mask_token": "[MASK]",
|
| 15 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 16 |
+
"pad_token": "[PAD]",
|
| 17 |
+
"sep_token": "[SEP]",
|
| 18 |
+
"split_by_punct": false,
|
| 19 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 20 |
+
"unk_id": 3,
|
| 21 |
+
"unk_token": "[UNK]",
|
| 22 |
+
"vocab_type": "spm"
|
| 23 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7769d4c338d2ebd179d31ff380b5f07198db5794b19e1ff307e9b86488d80a50
|
| 3 |
+
size 5265
|