Initial Commit
Browse files- README.md +7 -3
- config.json +20 -0
- flax_model.msgpack +3 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
README.md
CHANGED
@@ -1,3 +1,7 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
1 |
+
# Parrot
|
2 |
+
|
3 |
+
THIS IS AN ANCILLARY MODEL FOR PARROT PARAPHRASER
|
4 |
+
|
5 |
+
## 1. What is Parrot?
|
6 |
+
Parrot is a paraphrase based utterance augmentation framework purpose built to accelerate training NLU models. A paraphrase framework is more than just a paraphrasing model. Please refer to the [github page](https://github.com/PrithivirajDamodaran/Parrot) or The model card prithivida/parrot_paraphraser_on_T5
|
7 |
+
|
config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"BertForSequenceClassification"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"finetuning_task": "cola",
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 768,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 3072,
|
12 |
+
"layer_norm_eps": 1e-12,
|
13 |
+
"max_position_embeddings": 512,
|
14 |
+
"model_type": "bert",
|
15 |
+
"num_attention_heads": 12,
|
16 |
+
"num_hidden_layers": 12,
|
17 |
+
"pad_token_id": 0,
|
18 |
+
"type_vocab_size": 2,
|
19 |
+
"vocab_size": 30522
|
20 |
+
}
|
flax_model.msgpack
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d864a49900962d8f95ce6df87e68fd35dd72f31d92f54ce823d06e1ebd24bfd
|
3 |
+
size 437942328
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:daf55ee85f1607a78c851d0e7ff6fc444b421b436cface3bf521478c22d0beb8
|
3 |
+
size 437985387
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "model_max_length": 512}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|