Upload 10 files

.gitattributes

@@ -1,35 +1,9 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,105 @@
+---
+language: pt
+license: mit
+tags:
+  - bert
+  - pytorch
+datasets:
+  - brWaC
+---
+
+# BERTimbau Base (aka "bert-base-portuguese-cased")
+
+![Bert holding a berimbau](https://imgur.com/JZ7Hynh.jpg)
+
+## Introduction
+
+BERTimbau Base is a pretrained BERT model for Brazilian Portuguese that achieves state-of-the-art performances on three downstream NLP tasks: Named Entity Recognition, Sentence Textual Similarity and Recognizing Textual Entailment. It is available in two sizes: Base and Large.
+
+For further information or requests, please go to [BERTimbau repository](https://github.com/neuralmind-ai/portuguese-bert/).
+
+## Available models
+
+| Model                                    | Arch.      | #Layers | #Params |
+| ---------------------------------------- | ---------- | ------- | ------- |
+| `neuralmind/bert-base-portuguese-cased`  | BERT-Base  | 12      | 110M    |
+| `neuralmind/bert-large-portuguese-cased` | BERT-Large | 24      | 335M    |
+
+## Usage
+
+```python
+from transformers import AutoTokenizer  # Or BertTokenizer
+from transformers import AutoModelForPreTraining  # Or BertForPreTraining for loading pretraining heads
+from transformers import AutoModel  # or BertModel, for BERT without pretraining heads
+
+model = AutoModelForPreTraining.from_pretrained('neuralmind/bert-base-portuguese-cased')
+tokenizer = AutoTokenizer.from_pretrained('neuralmind/bert-base-portuguese-cased', do_lower_case=False)
+```
+
+### Masked language modeling prediction example
+
+```python
+from transformers import pipeline
+
+pipe = pipeline('fill-mask', model=model, tokenizer=tokenizer)
+
+pipe('Tinha uma [MASK] no meio do caminho.')
+# [{'score': 0.14287759363651276,
+#  'sequence': '[CLS] Tinha uma pedra no meio do caminho. [SEP]',
+#  'token': 5028,
+#  'token_str': 'pedra'},
+# {'score': 0.06213393807411194,
+#  'sequence': '[CLS] Tinha uma árvore no meio do caminho. [SEP]',
+#  'token': 7411,
+#  'token_str': 'árvore'},
+# {'score': 0.05515013635158539,
+#  'sequence': '[CLS] Tinha uma estrada no meio do caminho. [SEP]',
+#  'token': 5675,
+#  'token_str': 'estrada'},
+# {'score': 0.0299188531935215,
+#  'sequence': '[CLS] Tinha uma casa no meio do caminho. [SEP]',
+#  'token': 1105,
+#  'token_str': 'casa'},
+# {'score': 0.025660505518317223,
+#  'sequence': '[CLS] Tinha uma cruz no meio do caminho. [SEP]',
+#  'token': 3466,
+#  'token_str': 'cruz'}]
+
+```
+
+### For BERT embeddings
+
+```python
+import torch
+
+model = AutoModel.from_pretrained('neuralmind/bert-base-portuguese-cased')
+input_ids = tokenizer.encode('Tinha uma pedra no meio do caminho.', return_tensors='pt')
+
+with torch.no_grad():
+    outs = model(input_ids)
+    encoded = outs[0][0, 1:-1]  # Ignore [CLS] and [SEP] special tokens
+
+# encoded.shape: (8, 768)
+# tensor([[-0.0398, -0.3057,  0.2431,  ..., -0.5420,  0.1857, -0.5775],
+#         [-0.2926, -0.1957,  0.7020,  ..., -0.2843,  0.0530, -0.4304],
+#         [ 0.2463, -0.1467,  0.5496,  ...,  0.3781, -0.2325, -0.5469],
+#         ...,
+#         [ 0.0662,  0.7817,  0.3486,  ..., -0.4131, -0.2852, -0.2819],
+#         [ 0.0662,  0.2845,  0.1871,  ..., -0.2542, -0.2933, -0.0661],
+#         [ 0.2761, -0.1657,  0.3288,  ..., -0.2102,  0.0029, -0.2009]])
+```
+
+## Citation
+
+If you use our work, please cite:
+
+```bibtex
+@inproceedings{souza2020bertimbau,
+  author    = {F{\'a}bio Souza and
+               Rodrigo Nogueira and
+               Roberto Lotufo},
+  title     = {{BERT}imbau: pretrained {BERT} models for {B}razilian {P}ortuguese},
+  booktitle = {9th Brazilian Conference on Intelligent Systems, {BRACIS}, Rio Grande do Sul, Brazil, October 20-23 (to appear)},
+  year      = {2020}
+}
+```

added_tokens.json

@@ -0,0 +1 @@
+{}

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "type_vocab_size": 2,
+  "vocab_size": 29794
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96d2144445b6ba3530c27e38e7e27139fd0b0a5e36d9ca66f4155da7c5f199b0
+size 435825131

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb1693767adef60abf23d9fde3996f0c1e6310afad103a2db94ad44854568955
+size 438235074

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:934cefcc094555ce1d9493ccdc9bd052c9eb5e66a156fb0c630d0b653ce0185d
+size 529211872

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "init_inputs": []}