Fizzarolli commited on
Commit
f38f177
1 Parent(s): bdfc24c

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "kiddothe2b/longformer-mini-1024",
3
+ "architectures": ["LongformerForSequenceClassification"],
4
+ "attention_mode": "longformer",
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "attention_window": [128, 128, 128, 128, 128, 128],
7
+ "bos_token_id": null,
8
+ "classifier_dropout": null,
9
+ "cls_token_id": 101,
10
+ "eos_token_id": null,
11
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 256,
15
+ "ignore_attention_mask": false,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 1024,
18
+ "layer_norm_eps": 1e-5,
19
+ "max_position_embeddings": 1026,
20
+ "max_sentence_length": 128,
21
+ "max_sentence_size": 128,
22
+ "max_sentences": 8,
23
+ "model_max_length": 1024,
24
+ "model_type": "longformer",
25
+ "num_attention_heads": 4,
26
+ "num_hidden_layers": 6,
27
+ "pad_token_id": 0,
28
+ "position_embedding_type": "absolute",
29
+ "problem_type": "single_label_classification",
30
+ "sep_token_id": 102,
31
+ "seq_length": 1024,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.18.0",
34
+ "type_vocab_size": 2,
35
+ "use_cache": true,
36
+ "vocab_size": 30522
37
+ }
model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7667e61495668efb7935fe8c88fd1a3e00c515033036478c0791bd04514171a8
3
+ size 56315574
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5877e71b9587f7fc929cffbde06fd370fa831663d8f2ef3265870357b9e7f2e
3
+ size 56283016
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.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "data/PLMs/longformer", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}