Add 140k Model

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "./KcRoBERTa",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.26.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 30000
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61434a46d79b54a790bb3c123650a8091080c7ac091180bebecb987e355e7b0d
+size 436461843

special_tokens_map.json

@@ -0,0 +1,14 @@
+{
+  "additional_special_tokens": [
+    "[UNK]",
+    "[CLS]",
+    "[SEP]",
+    "[PAD]",
+    "[MASK]"
+  ],
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,6 @@
+{
+  "model_max_length": 512,
+  "name_or_path": "./KcRoBERTa",
+  "special_tokens_map_file": "./KcRoBERTa/special_tokens_map.json",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}