Upload folder using huggingface_hub
Browse files- config.json +70 -0
- model.pt +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_name": "uitnlp/visobert",
|
| 3 |
+
"task_config": {
|
| 4 |
+
"sentiment": {
|
| 5 |
+
"dataset": "hung20gg/NEU-ESC",
|
| 6 |
+
"num_labels": 4,
|
| 7 |
+
"type": "single_label",
|
| 8 |
+
"text_col": "Text",
|
| 9 |
+
"label_col": "Sentiment"
|
| 10 |
+
},
|
| 11 |
+
"topic": {
|
| 12 |
+
"dataset": "hung20gg/NEU-ESC",
|
| 13 |
+
"num_labels": 10,
|
| 14 |
+
"type": "single_label",
|
| 15 |
+
"text_col": "Text",
|
| 16 |
+
"label_col": "Classification"
|
| 17 |
+
},
|
| 18 |
+
"hate_speech": {
|
| 19 |
+
"dataset": "sonlam1102/vithsd",
|
| 20 |
+
"num_labels": 5,
|
| 21 |
+
"type": "multi_label",
|
| 22 |
+
"text_col": "content",
|
| 23 |
+
"label_col": "labels",
|
| 24 |
+
"label_list": [
|
| 25 |
+
"individual",
|
| 26 |
+
"groups",
|
| 27 |
+
"religion/creed",
|
| 28 |
+
"race/ethnicity",
|
| 29 |
+
"politics"
|
| 30 |
+
]
|
| 31 |
+
},
|
| 32 |
+
"clickbait": {
|
| 33 |
+
"dataset": "blanatole/ViClickbait-2025",
|
| 34 |
+
"num_labels": 2,
|
| 35 |
+
"type": "single_label",
|
| 36 |
+
"text_col": "text",
|
| 37 |
+
"label_col": "label",
|
| 38 |
+
"dual_input": true
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"max_seq_length": 128,
|
| 42 |
+
"hidden_dropout": 0.2,
|
| 43 |
+
"training_config": {
|
| 44 |
+
"num_epochs": 10,
|
| 45 |
+
"batch_size": 32,
|
| 46 |
+
"learning_rate": 2e-05,
|
| 47 |
+
"loss_weighting": "uncertainty",
|
| 48 |
+
"task_sampling": "proportional"
|
| 49 |
+
},
|
| 50 |
+
"final_results": {
|
| 51 |
+
"hate_speech_f1": 1.0,
|
| 52 |
+
"hate_speech_acc": 1.0,
|
| 53 |
+
"hate_speech_loss": 8.714258829154326e-09,
|
| 54 |
+
"clickbait_f1": 0.7949312440038375,
|
| 55 |
+
"clickbait_acc": 0.8245614035087719,
|
| 56 |
+
"clickbait_loss": 0.43148229067975824,
|
| 57 |
+
"sentiment_f1": 1.0,
|
| 58 |
+
"sentiment_acc": 1.0,
|
| 59 |
+
"sentiment_loss": 0.0,
|
| 60 |
+
"topic_f1": 1.0,
|
| 61 |
+
"topic_acc": 1.0,
|
| 62 |
+
"topic_loss": 5.103137090982615e-11
|
| 63 |
+
},
|
| 64 |
+
"best_scores": {
|
| 65 |
+
"hate_speech": 1.0,
|
| 66 |
+
"clickbait": 0.8027838536488368,
|
| 67 |
+
"sentiment": 1.0,
|
| 68 |
+
"topic": 1.0
|
| 69 |
+
}
|
| 70 |
+
}
|
model.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e1c9ac8d8ee901dc50470eb75188612818e3f5907fb64cda290f13877a80426
|
| 3 |
+
size 395096839
|
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02aaf05cda4db99e86b7c76eba6258867ce4d043da0fed19c87a7d46c8b53a65
|
| 3 |
+
size 470732
|
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
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"15001": {
|
| 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": 1000000000000000019884624838656,
|
| 51 |
+
"pad_token": "<pad>",
|
| 52 |
+
"sep_token": "</s>",
|
| 53 |
+
"sp_model_kwargs": {},
|
| 54 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 55 |
+
"unk_token": "<unk>"
|
| 56 |
+
}
|