add roformer chinese small

README.md

@@ -0,0 +1,82 @@
+---
+language: zh
+tags:
+- roformer
+- pytorch
+- tf2.0
+inference: false
+---
+## 介绍
+### tf版本 
+https://github.com/ZhuiyiTechnology/roformer
+
+### pytorch版本+tf2.0版本
+https://github.com/JunnYu/RoFormer_pytorch
+
+## 安装
+```bash
+pip install roformer
+或
+pip install git+https://github.com/JunnYu/RoFormer_pytorch.git
+```
+
+## pytorch使用
+```python
+import torch
+from roformer import RoFormerForMaskedLM, RoFormerTokenizer
+
+text = "今天[MASK]很好，我[MASK]去公园玩。"
+tokenizer = RoFormerTokenizer.from_pretrained("junnyu/roformer_chinese_small")
+pt_model = RoFormerForMaskedLM.from_pretrained("junnyu/roformer_chinese_small")
+pt_inputs = tokenizer(text, return_tensors="pt")
+with torch.no_grad():
+    pt_outputs = pt_model(**pt_inputs).logits[0]
+pt_outputs_sentence = "pytorch: "
+for i, id in enumerate(tokenizer.encode(text)):
+    if id == tokenizer.mask_token_id:
+        tokens = tokenizer.convert_ids_to_tokens(pt_outputs[i].topk(k=5)[1])
+        pt_outputs_sentence += "[" + "||".join(tokens) + "]"
+    else:
+        pt_outputs_sentence += "".join(
+            tokenizer.convert_ids_to_tokens([id], skip_special_tokens=True))
+print(pt_outputs_sentence)
+# pytorch: 今天[天气||心情||感觉||环境||下午]很好，我[要||想||就||可以||去]去公园玩。
+```
+
+
+## tensorflow2.0使用
+```python
+import tensorflow as tf
+from roformer import RoFormerTokenizer, TFRoFormerForMaskedLM
+text = "今天[MASK]很好，我[MASK]去公园玩。"
+tokenizer = RoFormerTokenizer.from_pretrained("junnyu/roformer_chinese_small")
+tf_model = TFRoFormerForMaskedLM.from_pretrained("junnyu/roformer_chinese_small")
+tf_inputs = tokenizer(text, return_tensors="tf")
+tf_outputs = tf_model(**tf_inputs, training=False).logits[0]
+tf_outputs_sentence = "tf2.0: "
+for i, id in enumerate(tokenizer.encode(text)):
+    if id == tokenizer.mask_token_id:
+        tokens = tokenizer.convert_ids_to_tokens(
+            tf.math.top_k(tf_outputs[i], k=5)[1])
+        tf_outputs_sentence += "[" + "||".join(tokens) + "]"
+    else:
+        tf_outputs_sentence += "".join(
+            tokenizer.convert_ids_to_tokens([id], skip_special_tokens=True))
+print(tf_outputs_sentence)
+# tf2.0 今天[天气||心情||感觉||环境||下午]很好，我[要||想||就||可以||去]去公园玩。
+```
+
+## 引用
+
+Bibtex：
+
+```tex
+@misc{su2021roformer,
+      title={RoFormer: Enhanced Transformer with Rotary Position Embedding}, 
+      author={Jianlin Su and Yu Lu and Shengfeng Pan and Bo Wen and Yunfeng Liu},
+      year={2021},
+      eprint={2104.09864},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```

config.json

@@ -0,0 +1,18 @@
+{
+  "architectures": [
+    "RoFormerForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "model_type": "roformer",
+  "num_attention_heads": 6,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "type_vocab_size": 2,
+  "vocab_size": 50000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4a7c6cad49ff8e6a29dba326805f5c498150adcdbb8d10efe01b2feb5439126
+size 120808404

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:423272802837cb1803f2be1abb0830527ac175141b6691da7f7981bfc40f62f8
+size 197760800