Fine-tuned DistilBERT sarcasm detector v1
Browse files- config.json +28 -0
- label_map.json +1 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "gelu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DistilBertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.1,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"dtype": "float32",
|
| 11 |
+
"eos_token_id": null,
|
| 12 |
+
"hidden_dim": 3072,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "distilbert",
|
| 16 |
+
"n_heads": 12,
|
| 17 |
+
"n_layers": 6,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"problem_type": "single_label_classification",
|
| 20 |
+
"qa_dropout": 0.1,
|
| 21 |
+
"seq_classif_dropout": 0.2,
|
| 22 |
+
"sinusoidal_pos_embds": false,
|
| 23 |
+
"tie_weights_": true,
|
| 24 |
+
"tie_word_embeddings": true,
|
| 25 |
+
"transformers_version": "5.0.0",
|
| 26 |
+
"use_cache": false,
|
| 27 |
+
"vocab_size": 30522
|
| 28 |
+
}
|
label_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"LABEL_0": "Not Sarcastic", "LABEL_1": "Sarcastic"}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66156545f31b8a99eae41bfd9acaa0d3427e40d1e0338381f9899452f8fc58de
|
| 3 |
+
size 267832560
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"is_local": false,
|
| 6 |
+
"mask_token": "[MASK]",
|
| 7 |
+
"model_max_length": 512,
|
| 8 |
+
"pad_token": "[PAD]",
|
| 9 |
+
"sep_token": "[SEP]",
|
| 10 |
+
"strip_accents": null,
|
| 11 |
+
"tokenize_chinese_chars": true,
|
| 12 |
+
"tokenizer_class": "BertTokenizer",
|
| 13 |
+
"unk_token": "[UNK]"
|
| 14 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6699a6b74b54c50b701813dd5748753993e60d67c11fceacb66180de06fe014f
|
| 3 |
+
size 5201
|