LEIA
/

saroyehun commited on
Commit
5a5f0ba
1 Parent(s): be6253e

Upload with huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<mask>": 64000
3
+ }
bpe.codes ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "transformers/checkpoint/vent/linear_probe/vent_bertweet-tapt_lr5e-4_embdrop0.1_labelsmoothing0.1_42_temp/",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": 0.1,
9
+ "eos_token_id": 2,
10
+ "finetuning_task": "vent",
11
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "id2label": {
16
+ "0": "Sadness",
17
+ "1": "Affection",
18
+ "2": "Fear",
19
+ "3": "Happiness",
20
+ "4": "Anger"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "Affection": 1,
26
+ "Anger": 4,
27
+ "Fear": 2,
28
+ "Happiness": 3,
29
+ "Sadness": 0
30
+ },
31
+ "layer_norm_eps": 1e-05,
32
+ "max_position_embeddings": 130,
33
+ "model_type": "roberta",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "pad_token_id": 1,
37
+ "position_embedding_type": "absolute",
38
+ "problem_type": "single_label_classification",
39
+ "tokenizer_class": "BertweetTokenizer",
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.26.0.dev0",
42
+ "type_vocab_size": 1,
43
+ "use_cache": true,
44
+ "vocab_size": 64001
45
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aea2319ea55b46dbc4e3a3e1599ba2d8a51d98d5f1715983e3532516fbd6168
3
+ size 539680493
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "</s>",
8
+ "unk_token": "<unk>"
9
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "model_max_length": 128,
7
+ "name_or_path": "transformers/checkpoint/vent/linear_probe/vent_bertweet-tapt_lr5e-4_embdrop0.1_labelsmoothing0.1_42_temp/",
8
+ "normalization": true,
9
+ "normalzation": true,
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "special_tokens_map_file": null,
13
+ "tokenizer_class": "BertweetTokenizer",
14
+ "tokenizer_file": null,
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:f2fe9ad40e6e18a8ad3fd68bdc0122e139eae6cf49a0d07f7eae6282b7807bc7
3
+ size 3887
vocab.txt ADDED
The diff for this file is too large to render. See raw diff