ldwang commited on
Commit
6221169
1 Parent(s): d803ca7
1_Pooling/config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": true,
4
+ "pooling_mode_mean_tokens": false,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false
7
+ }
README.md CHANGED
@@ -1,3 +1,272 @@
1
  ---
 
 
 
 
 
 
2
  license: mit
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ pipeline_tag: sentence-similarity
3
+ tags:
4
+ - sentence-transformers
5
+ - feature-extraction
6
+ - sentence-similarity
7
+ - transformers
8
  license: mit
9
+ language:
10
+ - zh
11
  ---
12
+
13
+
14
+ <h1 align="center">FlagEmbedding</h1>
15
+
16
+
17
+ <h4 align="center">
18
+ <p>
19
+ <a href=#model-list>Model List</a> |
20
+ <a href=#usage>Usage</a> |
21
+ <a href="#evaluation">Evaluation</a> |
22
+ <a href="#train">Train</a> |
23
+ <a href="#contact">Contact</a> |
24
+ <a href="#license">License</a>
25
+ <p>
26
+ </h4>
27
+
28
+ More details please refer to our Github: [FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding).
29
+
30
+ [English](README.md) | [中文](https://github.com/FlagOpen/FlagEmbedding/blob/master/README_zh.md)
31
+
32
+ FlagEmbedding can map any text to a low-dimensional dense vector which can be used for tasks like retrieval, classification, clustering, or semantic search.
33
+ And it also can be used in vector database for LLMs.
34
+
35
+ ************* 🌟**Updates**🌟 *************
36
+ - 08/09/2023: BGE Models are integrated into **Langchain**, you can use it like [**this**](#using-langchain); C-MTEB **leaderboard** is [avaliable](https://huggingface.co/spaces/mteb/leaderboard).
37
+ - 08/05/2023: Release base-scale and small-scale models, **best performance among the models of the same size 🤗**
38
+ - 08/02/2023: Release `bge-large-*`(short for BAAI General Embedding) Models, **rank 1st on MTEB and C-MTEB benchmark!**
39
+ - 08/01/2023: We release the [Chinese Massive Text Embedding Benchmark](https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB) (**C-MTEB**), consisting of 31 test dataset.
40
+
41
+
42
+ ## Model List
43
+
44
+ `bge` is short for `BAAI general embedding`.
45
+
46
+ | Model | Language | Description | query instruction for retrieval\* |
47
+ |:-------------------------------|:--------:| :--------:| :--------:|
48
+ | [BAAI/bge-large-en](https://huggingface.co/BAAI/bge-large-en) | English | rank **1st** in [MTEB](https://huggingface.co/spaces/mteb/leaderboard) leaderboard | `Represent this sentence for searching relevant passages: ` |
49
+ | [BAAI/bge-base-en](https://huggingface.co/BAAI/bge-base-en) | English | rank **2nd** in [MTEB](https://huggingface.co/spaces/mteb/leaderboard) leaderboard | `Represent this sentence for searching relevant passages: ` |
50
+ | [BAAI/bge-small-en](https://huggingface.co/BAAI/bge-small-en) | English | a small-scale model but with competitive performance | `Represent this sentence for searching relevant passages: ` |
51
+ | [BAAI/bge-large-zh](https://huggingface.co/BAAI/bge-large-zh) | Chinese | rank **1st** in [C-MTEB](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB) benchmark | `为这个句子生成表示以用于检索相关文章:` |
52
+ | [BAAI/bge-large-zh-noinstruct](https://huggingface.co/BAAI/bge-large-zh-noinstruct) | Chinese | This model is trained without instruction, and rank **2nd** in [C-MTEB](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB) benchmark | |
53
+ | [BAAI/bge-base-zh](https://huggingface.co/BAAI/bge-base-zh) | Chinese | a base-scale model but has similar ability with `bge-large-zh` | `为这个句子生成表示以用于检索相关文章:` |
54
+ | [BAAI/bge-small-zh](https://huggingface.co/BAAI/bge-small-zh) | Chinese | a small-scale model but with competitive performance | `为这个句子生成表示以用于检索相关文章:` |
55
+
56
+ \*: If you need to search the **long** relevant passages to a **short** query (s2p retrieval task), you need to add the instruction to the query; in other cases, no instruction is needed, just use the original query directly. In all cases, **no instruction** need to be added to passages.
57
+
58
+ ## Usage
59
+
60
+ Here are some examples to use `bge` models with
61
+ [FlagEmbedding](#using-flagembedding), [Sentence-Transformers](#using-sentence-transformers), [Langchain](#using-langchain), or [Huggingface Transformers](#using-huggingface-transformers).
62
+
63
+ #### Using FlagEmbedding
64
+ ```
65
+ pip install -U FlagEmbedding
66
+ ```
67
+ If it doesn't work for you, you can see [FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding/blob/master/FlagEmbedding/baai_general_embedding/README.md) for more methods to install FlagEmbedding.
68
+
69
+ ```python
70
+ from FlagEmbedding import FlagModel
71
+ sentences = ["样例数据-1", "样例数据-2"]
72
+ model = FlagModel('BAAI/bge-large-zh', query_instruction_for_retrieval="为这个句子生成表示以用于检索相关文章:")
73
+ embeddings_1 = model.encode(sentences)
74
+ embeddings_2 = model.encode(sentences)
75
+ similarity = embeddings_1 @ embeddings_2.T
76
+ print(similarity)
77
+
78
+ # for s2p(short query to long passage) retrieval task, please use encode_queries() which will automatically add the instruction to each query
79
+ # corpus in retrieval task can still use encode() or encode_corpus(), since they don't need instruction
80
+ queries = ['query_1', 'query_2']
81
+ passages = ["样例文档-1", "样例文档-2"]
82
+ q_embeddings = model.encode_queries(queries)
83
+ p_embeddings = model.encode(passages)
84
+ scores = q_embeddings @ p_embeddings.T
85
+ ```
86
+ The value of argument `query_instruction_for_retrieval` see [Model List](https://github.com/FlagOpen/FlagEmbedding/tree/master#model-list).
87
+
88
+ FlagModel will use all available GPUs when encoding, please set `os.environ["CUDA_VISIBLE_DEVICES"]` to choose GPU.
89
+
90
+
91
+ #### Using Sentence-Transformers
92
+
93
+ Using this model also is easy when you have [sentence-transformers](https://www.SBERT.net) installed:
94
+
95
+ ```
96
+ pip install -U sentence-transformers
97
+ ```
98
+ ```python
99
+ from sentence_transformers import SentenceTransformer
100
+ sentences = ["样例数据-1", "样例数据-2"]
101
+ model = SentenceTransformer('BAAI/bge-large-zh')
102
+ embeddings_1 = model.encode(sentences, normalize_embeddings=True)
103
+ embeddings_2 = model.encode(sentences, normalize_embeddings=True)
104
+ similarity = embeddings_1 @ embeddings_2.T
105
+ print(similarity)
106
+ ```
107
+ For s2p(short query to long passage) retrieval task,
108
+ each short query should start with an instruction (instructions see [Model List](https://github.com/FlagOpen/FlagEmbedding/tree/master#model-list)).
109
+ But the instruction is not needed for passages.
110
+ ```python
111
+ from sentence_transformers import SentenceTransformer
112
+ queries = ['query_1', 'query_2']
113
+ passages = ["样例文档-1", "样例文档-2"]
114
+ instruction = "为这个句子生成表示以用于检索相关文章:"
115
+
116
+ model = SentenceTransformer('BAAI/bge-large-zh')
117
+ q_embeddings = model.encode([instruction+q for q in queries], normalize_embeddings=True)
118
+ p_embeddings = model.encode(passages, normalize_embeddings=True)
119
+ scores = q_embeddings @ p_embeddings.T
120
+ ```
121
+
122
+ #### Using Langchain
123
+
124
+ You can use `bge` in langchain like this:
125
+ ```python
126
+ from langchain.embeddings import HuggingFaceBgeEmbeddings
127
+ model_name = "BAAI/bge-small-en"
128
+ model_kwargs = {'device': 'cuda'}
129
+ encode_kwargs = {'normalize_embeddings': True} # set True to compute cosine similarity
130
+ model_norm = HuggingFaceBgeEmbeddings(
131
+ model_name=model_name,
132
+ model_kwargs=model_kwargs,
133
+ encode_kwargs=encode_kwargs
134
+ )
135
+ ```
136
+
137
+
138
+ #### Using HuggingFace Transformers
139
+
140
+ With transformers package, you can use the model like this: First, you pass your input through the transformer model, then you select the last hidden state of first token (i.e., [CLS]) as the sentence embedding.
141
+
142
+ ```python
143
+ from transformers import AutoTokenizer, AutoModel
144
+ import torch
145
+ # Sentences we want sentence embeddings for
146
+ sentences = ["样例数据-1", "样例数据-2"]
147
+
148
+ # Load model from HuggingFace Hub
149
+ tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-large-zh')
150
+ model = AutoModel.from_pretrained('BAAI/bge-large-zh')
151
+
152
+ # Tokenize sentences
153
+ encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
154
+ # for s2p(short query to long passage) retrieval task, add an instruction to query (not add instruction for passages)
155
+ # encoded_input = tokenizer([instruction + q for q in queries], padding=True, truncation=True, return_tensors='pt')
156
+
157
+ # Compute token embeddings
158
+ with torch.no_grad():
159
+ model_output = model(**encoded_input)
160
+ # Perform pooling. In this case, cls pooling.
161
+ sentence_embeddings = model_output[0][:, 0]
162
+ # normalize embeddings
163
+ sentence_embeddings = torch.nn.functional.normalize(sentence_embeddings, p=2, dim=1)
164
+ print("Sentence embeddings:", sentence_embeddings)
165
+ ```
166
+
167
+
168
+ ## Evaluation
169
+ `baai-general-embedding` models achieve **state-of-the-art performance on both MTEB and C-MTEB leaderboard!**
170
+ More details and evaluation tools see our [scripts](https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB/README.md).
171
+
172
+ - **MTEB**:
173
+
174
+ | Model Name | Dimension | Sequence Length | Average (56) | Retrieval (15) |Clustering (11) | Pair Classification (3) | Reranking (4) | STS (10) | Summarization (1) | Classification (12) |
175
+ |:----:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
176
+ | [**bge-large-en**](https://huggingface.co/BAAI/bge-large-en) | 1024 | 512 | **63.98** | **53.9** | **46.98** | 85.8 | **59.48** | 81.56 | 32.06 | **76.21** |
177
+ | [**bge-base-en**](https://huggingface.co/BAAI/bge-base-en) | 768 | 512 | 63.36 | 53.0 | 46.32 | 85.86 | 58.7 | 81.84 | 29.27 | 75.27 |
178
+ | [gte-large](https://huggingface.co/thenlper/gte-large) | 1024 | 512 | 63.13 | 52.22 | 46.84 | 85.00 | 59.13 | 83.35 | 31.66 | 73.33 |
179
+ | [gte-base](https://huggingface.co/thenlper/gte-base) | 768 | 512 | 62.39 | 51.14 | 46.2 | 84.57 | 58.61 | 82.3 | 31.17 | 73.01 |
180
+ | [e5-large-v2](https://huggingface.co/intfloat/e5-large-v2) | 1024| 512 | 62.25 | 50.56 | 44.49 | 86.03 | 56.61 | 82.05 | 30.19 | 75.24 |
181
+ | [**bge-small-en**](https://huggingface.co/BAAI/bge-small-en) | 384 | 512 | 62.11 | 51.82 | 44.31 | 83.78 | 57.97 | 80.72 | 30.53 | 74.37 |
182
+ | [instructor-xl](https://huggingface.co/hkunlp/instructor-xl) | 768 | 512 | 61.79 | 49.26 | 44.74 | 86.62 | 57.29 | 83.06 | 32.32 | 61.79 |
183
+ | [e5-base-v2](https://huggingface.co/intfloat/e5-base-v2) | 768 | 512 | 61.5 | 50.29 | 43.80 | 85.73 | 55.91 | 81.05 | 30.28 | 73.84 |
184
+ | [gte-small](https://huggingface.co/thenlper/gte-small) | 384 | 512 | 61.36 | 49.46 | 44.89 | 83.54 | 57.7 | 82.07 | 30.42 | 72.31 |
185
+ | [text-embedding-ada-002](https://platform.openai.com/docs/guides/embeddings) | 1536 | 8192 | 60.99 | 49.25 | 45.9 | 84.89 | 56.32 | 80.97 | 30.8 | 70.93 |
186
+ | [e5-small-v2](https://huggingface.co/intfloat/e5-base-v2) | 384 | 512 | 59.93 | 49.04 | 39.92 | 84.67 | 54.32 | 80.39 | 31.16 | 72.94 |
187
+ | [sentence-t5-xxl](https://huggingface.co/sentence-transformers/sentence-t5-xxl) | 768 | 512 | 59.51 | 42.24 | 43.72 | 85.06 | 56.42 | 82.63 | 30.08 | 73.42 |
188
+ | [all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) | 768 | 514 | 57.78 | 43.81 | 43.69 | 83.04 | 59.36 | 80.28 | 27.49 | 65.07 |
189
+ | [sgpt-bloom-7b1-msmarco](https://huggingface.co/bigscience/sgpt-bloom-7b1-msmarco) | 4096 | 2048 | 57.59 | 48.22 | 38.93 | 81.9 | 55.65 | 77.74 | 33.6 | 66.19 |
190
+ | [all-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2) | 384 | 512 | 56.53 | 42.69 | 41.81 | 82.41 | 58.44 | 79.8 | 27.9 | 63.21 |
191
+ | [all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) | 384 | 512 | 56.26 | 41.95 | 42.35 | 82.37 | 58.04 | 78.9 | 30.81 | 63.05 |
192
+ | [contriever-base-msmarco](https://huggingface.co/nthakur/contriever-base-msmarco) | 768 | 512 | 56.00 | 41.88 | 41.1 | 82.54 | 53.14 | 76.51 | 30.36 | 66.68 |
193
+ | [sentence-t5-base](https://huggingface.co/sentence-transformers/sentence-t5-base) | 768 | 512 | 55.27 | 33.63 | 40.21 | 85.18 | 53.09 | 81.14 | 31.39 | 69.81 |
194
+
195
+
196
+
197
+ - **C-MTEB**:
198
+ We create a benchmark C-MTEB for chinese text embedding which consists of 31 datasets from 6 tasks.
199
+ Please refer to [C_MTEB](https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB/README.md) for a detailed introduction.
200
+
201
+ | Model | Embedding dimension | Avg | Retrieval | STS | PairClassification | Classification | Reranking | Clustering |
202
+ |:-------------------------------|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|
203
+ | [**bge-large-zh**](https://huggingface.co/BAAI/bge-large-zh) | 1024 | **64.20** | **71.53** | **53.23** | **78.94** | 72.26 | **65.11** | 48.39 |
204
+ | [**bge-large-zh-noinstruct**](https://huggingface.co/BAAI/bge-large-zh-noinstruct) | 1024 | 63.53 | 70.55 | 50.98 | 76.77 | **72.49** | 64.91 | **50.01** |
205
+ | [**BAAI/bge-base-zh**](https://huggingface.co/BAAI/bge-base-zh) | 768 | 62.96 | 69.53 | 52.05 | 77.5 | 70.98 | 64.91 | 47.63 |
206
+ | [**BAAI/bge-small-zh**](https://huggingface.co/BAAI/bge-small-zh) | 512 | 58.27 | 63.07 | 46.87 | 70.35 | 67.78 | 61.48 | 45.09 |
207
+ | [m3e-base](https://huggingface.co/moka-ai/m3e-base) | 768 | 57.10 |56.91 | 48.15 | 63.99 | 70.28 | 59.34 | 47.68 |
208
+ | [m3e-large](https://huggingface.co/moka-ai/m3e-large) | 1024 | 57.05 |54.75 | 48.64 | 64.3 | 71.22 | 59.66 | 48.88 |
209
+ | [text-embedding-ada-002(OpenAI)](https://platform.openai.com/docs/guides/embeddings/what-are-embeddings) | 1536 | 53.02 | 52.0 | 40.61 | 69.56 | 67.38 | 54.28 | 45.68 |
210
+ | [luotuo](https://huggingface.co/silk-road/luotuo-bert-medium) | 1024 | 49.37 | 44.4 | 39.41 | 66.62 | 65.29 | 49.25 | 44.39 |
211
+ | [text2vec](https://huggingface.co/shibing624/text2vec-base-chinese) | 768 | 47.63 | 38.79 | 41.71 | 67.41 | 65.18 | 49.45 | 37.66 |
212
+ | [text2vec-large](https://huggingface.co/GanymedeNil/text2vec-large-chinese) | 1024 | 47.36 | 41.94 | 41.98 | 70.86 | 63.42 | 49.16 | 30.02 |
213
+
214
+
215
+
216
+ ## Train
217
+ This section will introduce the way we used to train the general embedding.
218
+ The training scripts are in [FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding/blob/master/FlagEmbedding/baai_general_embedding/README.md),
219
+ and we provide some examples to do [pre-train](https://github.com/FlagOpen/FlagEmbedding/blob/master/examples/pretrain/README.md) and [fine-tune](https://github.com/FlagOpen/FlagEmbedding/blob/master/examples/finetune/README.md).
220
+
221
+
222
+ **1. RetroMAE Pre-train**
223
+ We pre-train the model following the method [retromae](https://github.com/staoxiao/RetroMAE),
224
+ which shows promising improvement in retrieval task ([paper](https://aclanthology.org/2022.emnlp-main.35.pdf)).
225
+ The pre-training was conducted on 24 A100(40G) GPUs with a batch size of 720.
226
+ In retromae, the mask ratio of encoder and decoder are 0.3, 0.5 respectively.
227
+ We used the AdamW optimizer and the learning rate is 2e-5.
228
+
229
+ **Pre-training data**:
230
+ - English:
231
+ - [Pile](https://pile.eleuther.ai/)
232
+ - [wikipedia](https://huggingface.co/datasets/wikipedia)
233
+ - [msmarco](https://huggingface.co/datasets/Tevatron/msmarco-passage-corpus)
234
+ - Chinese:
235
+ - [wudao](https://github.com/BAAI-WuDao/Data)
236
+
237
+
238
+ **2. Finetune**
239
+ We fine-tune the model using a contrastive objective.
240
+ The format of input data is a triple`(query, positive, negative)`.
241
+ Besides the negative in the triple, we also adopt in-batch negatives strategy.
242
+ We employ the cross-device negatives sharing method to share negatives among different GPUs,
243
+ which can dramatically **increase the number of negatives**.
244
+
245
+ We trained our model on 48 A100(40G) GPUs with a large batch size of 32,768 (so there are **65,535** negatives for each query in a batch).
246
+ We used the AdamW optimizer and the learning rate is 1e-5.
247
+ The temperature for contrastive loss is 0.01.
248
+
249
+ Besides, we add instruction to the query for s2p(short query to long passage) retrieval task in the training (add nothing to passages).
250
+ For English, the instruction is `Represent this sentence for searching relevant passages: `;
251
+ For Chinese, the instruction is `为这个句子生成表示以用于检索相关文章:`.
252
+ In the evaluation, the instruction should be added for queries in retrieval task, not be added for other tasks.
253
+ Noted that the instruction is not needed for passages.
254
+
255
+ The finetune script is accessible in this repository: [FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding/blob/master/FlagEmbedding/baai_general_embedding/README.md).
256
+ You can easily finetune your model with it.
257
+
258
+ **Training data**:
259
+
260
+ - For English, we collect 230M text pairs from [wikipedia](https://huggingface.co/datasets/wikipedia), [cc-net](https://github.com/facebookresearch/cc_net), and so on.
261
+
262
+ - For chinese, we collect 120M text pairs from [wudao](https://github.com/BAAI-WuDao/Data), [simclue](https://github.com/CLUEbenchmark/SimCLUE) and so on.
263
+
264
+ **The data collection is to be released in the future.**
265
+
266
+ We will continually update the embedding models and training codes,
267
+ hoping to promote the development of the embedding model community.
268
+
269
+
270
+
271
+ ## License
272
+ FlagEmbedding is licensed under [MIT License](https://github.com/FlagOpen/FlagEmbedding/blob/master/LICENSE). The released models can be used for commercial purposes free of charge.
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/root/.cache/torch/sentence_transformers/BAAI_bge-base-zh/",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "directionality": "bidi",
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "LABEL_0"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "LABEL_0": 0
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "bert",
25
+ "num_attention_heads": 12,
26
+ "num_hidden_layers": 12,
27
+ "output_past": true,
28
+ "pad_token_id": 0,
29
+ "pooler_fc_size": 768,
30
+ "pooler_num_attention_heads": 12,
31
+ "pooler_num_fc_layers": 3,
32
+ "pooler_size_per_head": 128,
33
+ "pooler_type": "first_token_transform",
34
+ "position_embedding_type": "absolute",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.30.0",
37
+ "type_vocab_size": 2,
38
+ "use_cache": true,
39
+ "vocab_size": 21128
40
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.2.2",
4
+ "transformers": "4.28.1",
5
+ "pytorch": "1.13.0+cu117"
6
+ }
7
+ }
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ }
14
+ ]
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:731cf5d88ed555a21ff2f2d9fa4db43b10489173ddd9178db3eecfd7a2bae044
3
+ size 409138989
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": true
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": true,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 512,
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff