create

README.md

@@ -0,0 +1,25 @@
+---
+language: zh
+---
+
+## roberta-chinese-homie-large
+
+This is a Chinese pre-training model RoBERTa, pre-trained on a large-scale corpus. It is suitable for fine-tuning on specific downstream tasks, or as a parameter initialization for pre-training, which can improve performance. Due to excessive alchemy, it is not suitable for Fill Mask directly, unless you have performed a small amount of pre-training.
+
+I don't know what homie means, but someone calls me that. I believe this is an interesting natural language processing. I don't know what homie means, but I've been called that and I can feel the meaning. 
+
+## Bibtex entry and citation info
+Please cite if you find it helpful.
+```
+@article{zhu2023metaaid,
+  title={MetaAID 2.0: An Extensible Framework for Developing Metaverse Applications via Human-controllable Pre-trained Models},
+  author={Zhu, Hongyin},
+  journal={arXiv preprint arXiv:2302.13173},
+  year={2023}
+}
+
+```
+
+---
+license: other
+---

added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "[/heading]": 21131,
+  "[/triple]": 21130,
+  "[heading]": 21129,
+  "[t1]": 21133,
+  "[t2]": 21134,
+  "[t3]": 21135,
+  "[t4]": 21136,
+  "[t5]": 21137,
+  "[t6]": 21138,
+  "[t]": 21132,
+  "[triple]": 21128
+}

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "hfl/chinese-roberta-wwm-ext-large",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21139
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.27.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19e9013ceb964b149d4c2f715f9a547a450364953b91b097c9ec4233aed168c2
+size 1302364075

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 +1,13 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--hfl--chinese-roberta-wwm-ext-large/snapshots/a25cc9e05974bd9687e528edd516f2cfdb3f5db9/special_tokens_map.json",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12f9d1ffc9458f0aa5eae6026c8e03a5a13929481d0780342fd266988b9a5dba
+size 1007