Upload ./ with huggingface_hub
Browse files- config.json +44 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "stage_f/pretrain_mlm_convbert-base-turkish-mc4-cased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ConvBertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"conv_kernel_size": 9,
|
| 10 |
+
"embedding_size": 768,
|
| 11 |
+
"eos_token_id": 2,
|
| 12 |
+
"head_ratio": 2,
|
| 13 |
+
"hidden_act": "gelu",
|
| 14 |
+
"hidden_dropout_prob": 0.1,
|
| 15 |
+
"hidden_size": 768,
|
| 16 |
+
"id2label": {
|
| 17 |
+
"0": "INSULT",
|
| 18 |
+
"1": "OTHER",
|
| 19 |
+
"2": "PROFANITY",
|
| 20 |
+
"3": "RACIST",
|
| 21 |
+
"4": "SEXIST"
|
| 22 |
+
},
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 3072,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"INSULT": 0,
|
| 27 |
+
"OTHER": 1,
|
| 28 |
+
"PROFANITY": 2,
|
| 29 |
+
"RACIST": 3,
|
| 30 |
+
"SEXIST": 4
|
| 31 |
+
},
|
| 32 |
+
"layer_norm_eps": 1e-12,
|
| 33 |
+
"max_position_embeddings": 512,
|
| 34 |
+
"model_type": "convbert",
|
| 35 |
+
"num_attention_heads": 12,
|
| 36 |
+
"num_groups": 1,
|
| 37 |
+
"num_hidden_layers": 12,
|
| 38 |
+
"pad_token_id": 0,
|
| 39 |
+
"problem_type": "single_label_classification",
|
| 40 |
+
"torch_dtype": "float32",
|
| 41 |
+
"transformers_version": "4.24.0",
|
| 42 |
+
"type_vocab_size": 2,
|
| 43 |
+
"vocab_size": 32000
|
| 44 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b579d137e5e9c68328e3324022c22f26062293efee478346ee9a1a30ddd08cd2
|
| 3 |
+
size 429744261
|
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 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"do_basic_tokenize": true,
|
| 4 |
+
"do_lower_case": false,
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"max_len": 512,
|
| 7 |
+
"name_or_path": "stage_f/pretrain_mlm_convbert-base-turkish-mc4-cased",
|
| 8 |
+
"never_split": null,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"special_tokens_map_file": null,
|
| 12 |
+
"strip_accents": false,
|
| 13 |
+
"tokenize_chinese_chars": true,
|
| 14 |
+
"tokenizer_class": "ConvBertTokenizer",
|
| 15 |
+
"unk_token": "[UNK]"
|
| 16 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:644b008111996ed49314c86415dcd843b0e68bd06aa5e0304e4a48617aecac63
|
| 3 |
+
size 3451
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|