israelcamp commited on
Commit
4bc3ae1
1 Parent(s): 7a78a8f

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/content/albertinha-ptbr-xsmall",
3
+ "architectures": [
4
+ "DebertaV2Model"
5
+ ],
6
+ "attention_head_size": 64,
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 384,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 1536,
13
+ "layer_norm_eps": 1e-07,
14
+ "max_position_embeddings": 512,
15
+ "max_relative_positions": -1,
16
+ "model_type": "deberta-v2",
17
+ "norm_rel_ebd": "layer_norm",
18
+ "num_attention_heads": 6,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 0,
21
+ "pooler_dropout": 0,
22
+ "pooler_hidden_act": "gelu",
23
+ "pooler_hidden_size": 384,
24
+ "pos_att_type": [
25
+ "p2c",
26
+ "c2p"
27
+ ],
28
+ "position_biased_input": false,
29
+ "position_buckets": 256,
30
+ "relative_attention": true,
31
+ "share_att_key": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.33.2",
34
+ "type_vocab_size": 0,
35
+ "vocab_size": 50270
36
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54c06d2c54027969e2562d530edbc3a2b7beaae7f60c4e207c850cd2a5a38b89
3
+ size 163245605
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "[UNK]"
9
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "do_lower_case": false,
6
+ "eos_token": "[SEP]",
7
+ "mask_token": "[MASK]",
8
+ "max_length": 10,
9
+ "model_max_length": 512,
10
+ "pad_to_multiple_of": null,
11
+ "pad_token": "[PAD]",
12
+ "pad_token_type_id": 0,
13
+ "padding_side": "right",
14
+ "sep_token": "[SEP]",
15
+ "sp_model_kwargs": {},
16
+ "split_by_punct": false,
17
+ "tokenizer_class": "DebertaV2Tokenizer",
18
+ "unk_token": "[UNK]"
19
+ }