cardiffnlp
commited on
Commit
•
3613b66
1
Parent(s):
bdffab9
Adding bertweet classifier
Browse files- README.md +0 -0
- added_tokens.json +1 -0
- bpe.codes +0 -0
- config.json +24 -0
- pytorch_model.bin +3 -0
- tf_model.h5 +3 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
README.md
ADDED
File without changes
|
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<mask>": 64000}
|
bpe.codes
ADDED
The diff for this file is too large to render.
See raw diff
|
|
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/jupyter/misc/tweeteval/TweetEval_models_bertweet/original/bertweet-base-hate/",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 130,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"tokenizer_class": "BertweetTokenizer",
|
22 |
+
"type_vocab_size": 1,
|
23 |
+
"vocab_size": 64001
|
24 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce7a1e129ff8796ebd2d895352688ab245ea09393875a0cfcb354efa2f60229d
|
3 |
+
size 539690697
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b79903d0546fa5090ed413f1801a72983ed6bfa1baaee444017feb90ef4fe64e
|
3 |
+
size 542244576
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"normalization": false, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "do_lower_case": false, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/home/jupyter/TMP_finetune_tweeteval/model/"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|