avacaondata
commited on
Commit
•
5dc7cc6
1
Parent(s):
0dd1bfd
model added
Browse files- config.json +29 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +17 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"language": "spanish",
|
15 |
+
"layer_norm_eps": 1e-12,
|
16 |
+
"max_position_embeddings": 512,
|
17 |
+
"model_type": "bert",
|
18 |
+
"name": "DPRContextEncoder",
|
19 |
+
"num_attention_heads": 12,
|
20 |
+
"num_hidden_layers": 12,
|
21 |
+
"output_past": true,
|
22 |
+
"pad_token_id": 1,
|
23 |
+
"position_embedding_type": "absolute",
|
24 |
+
"projection_dim": 0,
|
25 |
+
"transformers_version": "4.25.1",
|
26 |
+
"type_vocab_size": 2,
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 31002
|
29 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28d888c61724f6b2ffa3e49cac5af38955aaf3593f19656ace84b4a917bce760
|
3 |
+
size 439493047
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": true,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 512,
|
7 |
+
"name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"special_tokens_map_file": "/home/alejandro/.cache/huggingface/hub/models--dccuchile--bert-base-spanish-wwm-cased/snapshots/56a7647b957a4230fc3f80dafbe80f2ba9b0de73/special_tokens_map.json",
|
12 |
+
"strip_accents": false,
|
13 |
+
"tokenize_chinese_chars": true,
|
14 |
+
"tokenizer_class": "DPRContextEncoderTokenizer",
|
15 |
+
"unk_token": "[UNK]",
|
16 |
+
"use_fast": true
|
17 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|