Upload 4 files

config.json

@@ -1,10 +1,13 @@
 {
+  "_name_or_path": "roberta-tagalog-base",
   "architectures": [
-    "XLMRobertaForMaskedLM"
+    "RobertaForMaskedLM"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
+  "classifier_dropout": null,
   "eos_token_id": 2,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -12,14 +15,14 @@
   "intermediate_size": 3072,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
+  "model_type": "roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "output_past": true,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.17.0.dev0",
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.3",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 30000
 }

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "special_tokens_map_file": null, "name_or_path": "lm-pretraining/configs/base/", "tokenizer_class": "RobertaTokenizer"}