initial release

README.md

@@ -0,0 +1,26 @@
+---
+language:
+- "lzh"
+tags:
+- "classical chinese"
+- "literary chinese"
+- "ancient chinese"
+license: "apache-2.0"
+pipeline_tag: "fill-mask"
+widget:
+- text: "孟子[MASK]梁惠王"
+---
+
+# roberta-classical-chinese-large-char
+
+## Model Description
+
+This is a RoBERTa model pre-trained on Classical Chinese texts, derived from [GuwenBERT-large](https://huggingface.co/ethanyt/guwenbert-large). Character-embeddings are enhanced into traditional/simplified characters. You can fine-tune `roberta-classical-chinese-large-char` for downstream tasks, such as sentencization, POS-tagging, dependency-parsing, and so on.
+
+## How to Use
+
+```py
+from transformers import AutoTokenizer,AutoModel
+tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/roberta-classical-chinese-large-char")
+model=AutoModel.from_pretrained("KoichiYasuoka/roberta-classical-chinese-large-char")
+```

config.json

@@ -0,0 +1,23 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "tokenizer_class": "BertTokenizer",
+  "type_vocab_size": 1,
+  "vocab_size": 26318
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b86e31db88d1346640833ddddb45da032d98bc62d005abbb980046a57361d1ad
+size 1323629438

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": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "ethanyt/guwenbert-large", "do_basic_tokenize": true, "never_split": null}