Upload tiny models for RoCBertForPreTraining

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "RoCBertForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "concat_input": true,
+  "enable_cls": true,
+  "enable_pronunciation": true,
+  "enable_shape": true,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 37,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "roc_bert",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 5,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "pronunciation_embed_dim": 32,
+  "pronunciation_vocab_size": 99,
+  "shape_embed_dim": 32,
+  "shape_vocab_size": 99,
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.0.dev0",
+  "type_vocab_size": 16,
+  "use_cache": true,
+  "vocab_size": 21128
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aef23c0d3e806153a53400c3dfbcd07f173f2d5bef8fbd2c688ad570bcae36f
+size 3074516

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "weiweishi/roc-bert-base-zh",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "RoCBertTokenizer",
+  "unk_token": "[UNK]"
+}