mmaguero commited on
Commit
09c99bf
1 Parent(s): cf7b3f6

First model version

Browse files
README.md ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: gn
3
+ datasets:
4
+ - wikipedia
5
+ - wiktionary
6
+ widget:
7
+ - text: "Paraguay ha'e peteĩ táva oĩva [MASK] retãme "
8
+ ---
9
+
10
+ # BERT-i-small-cased (gnBERT-small-cased)
11
+
12
+ A pre-trained BERT model for **Guarani** (6 layers, cased). Trained on Wikipedia + Wiktionary (~800K tokens).
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": null,
7
+ "do_sample": false,
8
+ "eos_token_ids": null,
9
+ "finetuning_task": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "is_decoder": false,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "length_penalty": 1.0,
26
+ "max_length": 20,
27
+ "max_position_embeddings": 512,
28
+ "model_type": "bert",
29
+ "num_attention_heads": 12,
30
+ "num_beams": 1,
31
+ "num_hidden_layers": 6,
32
+ "num_labels": 2,
33
+ "num_return_sequences": 1,
34
+ "output_attentions": false,
35
+ "output_hidden_states": false,
36
+ "output_past": true,
37
+ "pad_token_id": null,
38
+ "pruned_heads": {},
39
+ "repetition_penalty": 1.0,
40
+ "temperature": 1.0,
41
+ "top_k": 50,
42
+ "top_p": 1.0,
43
+ "torchscript": false,
44
+ "type_vocab_size": 2,
45
+ "use_bfloat16": false,
46
+ "vocab_size": 30000
47
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7546ae4e78818751c983ba36bbeb24ba6e203619b5bb884113f20304b84daa03
3
+ size 268749430
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": false, "tokenize_chinese_chars": false}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bfdb909831f16761af7abaf30b3fcafb610b064fcc4fdbc98744558113457e3
3
+ size 1711
vocab.txt ADDED
The diff for this file is too large to render. See raw diff