update

README.md

@@ -0,0 +1,32 @@
+This model has been trained on massive Chinese plain-text open-domain dialogues following the approach described in [Re$^3$Dial: Retrieve, Reorganize and Rescale Conversations for Long-Turn Open-Domain Dialogue Pre-training](https://arxiv.org/abs/2305.02606). The associated Github repository is available here https://github.com/thu-coai/Re3Dial.
+
+### Usage
+
+```python
+from transformers import BertTokenizer, BertModel
+import torch
+
+
+def get_embedding(encoder, inputs):
+    outputs = encoder(**inputs)
+    pooled_output = outputs[0][:, 0, :]
+    return pooled_output
+
+tokenizer = BertTokenizer.from_pretrained('xwwwww/bert-chinese-dialogue-retriever-query')
+tokenizer.add_tokens(['<uttsep>'])
+query_encoder = BertModel.from_pretrained('xwwwww/bert-chinese-dialogue-retriever-query')
+context_encoder = BertModel.from_pretrained('xwwwww/bert-chinese-dialogue-retriever-context')
+
+query = '你好<uttsep>好久不见，最近在干嘛'
+context = '正在准备考试<uttsep>是什么考试呀，很辛苦吧'
+
+query_inputs = tokenizer([query], return_tensors='pt')
+context_inputs = tokenizer([context], return_tensors='pt')
+
+query_embedding = get_embedding(query_encoder, query_inputs)
+context_embedding = get_embedding(context_encoder, context_inputs)
+
+score = torch.cosine_similarity(query_embedding, context_embedding, dim=1)
+
+print('similarity score = ', score)
+```

added_tokens.json

@@ -0,0 +1 @@
+{}

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "directionality": "bidi",
+  "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-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "type_vocab_size": 2,
+  "vocab_size": 21129
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f29bd3a31022813466042d30c9391714dcb57a72d362855e21bccf7682f8dec
+size 409141297

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 @@
+{"init_inputs": []}