Upload 4 files
Browse filesUpload BERTimbau-base model fine-tuned with legal vocabulary.
- config.json +61 -0
- finetuned_BERT_1e4_10k_32_tf_ckpt.ckpt.index +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_num_labels": 2,
|
3 |
+
"architectures": [
|
4 |
+
"BertForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bad_words_ids": null,
|
8 |
+
"bos_token_id": null,
|
9 |
+
"decoder_start_token_id": null,
|
10 |
+
"directionality": "bidi",
|
11 |
+
"do_sample": false,
|
12 |
+
"early_stopping": false,
|
13 |
+
"eos_token_id": null,
|
14 |
+
"finetuning_task": null,
|
15 |
+
"hidden_act": "gelu",
|
16 |
+
"hidden_dropout_prob": 0.1,
|
17 |
+
"hidden_size": 768,
|
18 |
+
"id2label": {
|
19 |
+
"0": "LABEL_0",
|
20 |
+
"1": "LABEL_1"
|
21 |
+
},
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"intermediate_size": 3072,
|
24 |
+
"is_decoder": false,
|
25 |
+
"is_encoder_decoder": false,
|
26 |
+
"label2id": {
|
27 |
+
"LABEL_0": 0,
|
28 |
+
"LABEL_1": 1
|
29 |
+
},
|
30 |
+
"layer_norm_eps": 1e-12,
|
31 |
+
"length_penalty": 1.0,
|
32 |
+
"max_length": 20,
|
33 |
+
"max_position_embeddings": 512,
|
34 |
+
"min_length": 0,
|
35 |
+
"model_type": "bert",
|
36 |
+
"no_repeat_ngram_size": 0,
|
37 |
+
"num_attention_heads": 12,
|
38 |
+
"num_beams": 1,
|
39 |
+
"num_hidden_layers": 12,
|
40 |
+
"num_return_sequences": 1,
|
41 |
+
"output_attentions": false,
|
42 |
+
"output_hidden_states": false,
|
43 |
+
"output_past": true,
|
44 |
+
"pad_token_id": 0,
|
45 |
+
"pooler_fc_size": 768,
|
46 |
+
"pooler_num_attention_heads": 12,
|
47 |
+
"pooler_num_fc_layers": 3,
|
48 |
+
"pooler_size_per_head": 128,
|
49 |
+
"pooler_type": "first_token_transform",
|
50 |
+
"prefix": null,
|
51 |
+
"pruned_heads": {},
|
52 |
+
"repetition_penalty": 1.0,
|
53 |
+
"task_specific_params": null,
|
54 |
+
"temperature": 1.0,
|
55 |
+
"top_k": 50,
|
56 |
+
"top_p": 1.0,
|
57 |
+
"torchscript": false,
|
58 |
+
"type_vocab_size": 2,
|
59 |
+
"use_bfloat16": false,
|
60 |
+
"vocab_size": 29794
|
61 |
+
}
|
finetuned_BERT_1e4_10k_32_tf_ckpt.ckpt.index
ADDED
Binary file (8.23 kB). View file
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ecd98d822c51fb3b6da9f5b9d51f9ba921ed27d7ec3a97b840e5a4838220cdde
|
3 |
+
size 1309
|