First model version

README.md

@@ -0,0 +1,12 @@
+---
+language: gn
+datasets:
+- wikipedia
+- wiktionary
+widget:
+- text: "Paraguay ha'e peteĩ táva oĩva [MASK] retãme  "
+---
+
+# BERT-i-large-cased (gnBERT-large-cased)
+
+A pre-trained BERT model for **Guarani** (24 layers, cased). Trained on Wikipedia + Wiktionary (~800K tokens).

config.json

@@ -0,0 +1,47 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "do_sample": false,
+  "eos_token_ids": null,
+  "finetuning_task": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "is_decoder": false,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "length_penalty": 1.0,
+  "max_length": 20,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_beams": 1,
+  "num_hidden_layers": 24,
+  "num_labels": 2,
+  "num_return_sequences": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "output_past": true,
+  "pad_token_id": null,
+  "pruned_heads": {},
+  "repetition_penalty": 1.0,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "torchscript": false,
+  "type_vocab_size": 2,
+  "use_bfloat16": false,
+  "vocab_size": 30000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c15879ed887abad5bb4576328670acf841ce9f595f9cb363aeb036068042a83
+size 1342851931

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "tokenize_chinese_chars": false}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad17416fc5dd7c3c75feda6f859538139bb9f06508154f5859a47db104339384
+size 1433