Update README.md

README.md

@@ -1,6 +1,8 @@
 ---
 tags:
 - mteb
+- sentence-transfomres
+- transformers
 model-index:
 - name: bge-large-en
   results:
@@ -1195,7 +1197,7 @@ model-index:
     - type: map_at_5
       value: 17.516000000000002
     - type: mrr_at_1
-      value: 71.0
+      value: 71
     - type: mrr_at_10
       value: 78.724
     - type: mrr_at_100
@@ -1219,7 +1221,7 @@ model-index:
     - type: ndcg_at_5
       value: 45.961
     - type: precision_at_1
-      value: 71.0
+      value: 71
     - type: precision_at_10
       value: 34.575
     - type: precision_at_100
@@ -1884,7 +1886,7 @@ model-index:
     - type: map_at_5
       value: 11.672
     - type: mrr_at_1
-      value: 26.0
+      value: 26
     - type: mrr_at_10
       value: 37.335
     - type: mrr_at_100
@@ -1896,7 +1898,7 @@ model-index:
     - type: mrr_at_5
       value: 36.028
     - type: ndcg_at_1
-      value: 26.0
+      value: 26
     - type: ndcg_at_10
       value: 22.215
     - type: ndcg_at_100
@@ -1908,7 +1910,7 @@ model-index:
     - type: ndcg_at_5
       value: 18.759999999999998
     - type: precision_at_1
-      value: 26.0
+      value: 26
     - type: precision_at_10
       value: 11.43
     - type: precision_at_100
@@ -2155,7 +2157,7 @@ model-index:
     - type: map_at_5
       value: 66.281
     - type: mrr_at_1
-      value: 61.0
+      value: 61
     - type: mrr_at_10
       value: 68.953
     - type: mrr_at_100
@@ -2167,7 +2169,7 @@ model-index:
     - type: mrr_at_5
       value: 68.05
     - type: ndcg_at_1
-      value: 61.0
+      value: 61
     - type: ndcg_at_10
       value: 72.369
     - type: ndcg_at_100
@@ -2179,7 +2181,7 @@ model-index:
     - type: ndcg_at_5
       value: 69.72500000000001
     - type: precision_at_1
-      value: 61.0
+      value: 61
     - type: precision_at_10
       value: 9.733
     - type: precision_at_100
@@ -2331,7 +2333,7 @@ model-index:
     - type: map_at_5
       value: 1.069
     - type: mrr_at_1
-      value: 88.0
+      value: 88
     - type: mrr_at_10
       value: 93.4
     - type: mrr_at_100
@@ -2339,11 +2341,11 @@ model-index:
     - type: mrr_at_1000
       value: 93.4
     - type: mrr_at_3
-      value: 93.0
+      value: 93
     - type: mrr_at_5
       value: 93.4
     - type: ndcg_at_1
-      value: 86.0
+      value: 86
     - type: ndcg_at_10
       value: 75.375
     - type: ndcg_at_100
@@ -2355,9 +2357,9 @@ model-index:
     - type: ndcg_at_5
       value: 80.175
     - type: precision_at_1
-      value: 88.0
+      value: 88
     - type: precision_at_10
-      value: 79.0
+      value: 79
     - type: precision_at_100
       value: 53.16
     - type: precision_at_1000
@@ -2365,7 +2367,7 @@ model-index:
     - type: precision_at_3
       value: 85.333
     - type: precision_at_5
-      value: 84.0
+      value: 84
     - type: recall_at_1
       value: 0.231
     - type: recall_at_10
@@ -2596,4 +2598,243 @@ model-index:
       value: 83.56538942001427
     - type: max_f1
       value: 75.73635656329888
----
+license: mit
+language:
+- en
+pipeline_tag: sentence-similarity
+---
+
+
+<h1 align="center">FlagEmbedding</h1>
+
+
+<h4 align="center">
+    <p>
+        <a href=#model-list>Model List</a> | 
+        <a href=#usage>Usage</a>  |
+        <a href="#evaluation">Evaluation</a> |
+        <a href="#train">Train</a> |
+        <a href="#contact">Contact</a> |
+        <a href="#license">License</a> 
+    <p>
+</h4>
+
+More details please refer to our github: [FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding).
+
+[English](README.md) | [中文](README_zh.md)
+
+FlagEmbedding can map any text to a low-dimensional dense vector which can be used for tasks like retrieval, classification,  clustering, or semantic search.
+And it also can be used in vector database for LLMs.
+
+************* 🌟**Updates**🌟 *************
+- 08/05/2023: Release base-scale and small-scale models, **best performance among the models of the same size 🤗**
+- 08/02/2023: Release `bge-large-*`(short for BAAI General Embedding) Models, **rank 1st on MTEB and C-MTEB benchmark!**  
+- 08/01/2023: We release the Chinese Massive Text Embedding Benchmark (**C-MTEB**), consisting of 31 test dataset.   
+
+
+## Model List
+
+`bge` is short for `BAAI general embedding`.
+
+|              Model              | Language | Description | query instruction for retrieval |
+|:-------------------------------|:--------:| :--------:| :--------:|
+|  [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: `  |
+|  [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: `  |
+|  [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: `  |
+|  [BAAI/bge-large-zh](https://huggingface.co/BAAI/bge-large-zh) |   Chinese | **rank 1st** in [C-MTEB](https://github.com/FlagOpen/FlagEmbedding/tree/master/benchmark) benchmark | `为这个句子生成表示以用于检索相关文章：`  |
+|  [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/benchmark) benchmark |   |
+|  [BAAI/bge-base-zh](https://huggingface.co/BAAI/bge-base-zh) |   Chinese |  a base-scale model but with competitive performance | `为这个句子生成表示以用于检索相关文章：`  |
+|  [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：`  |
+
+
+
+## Usage 
+
+* **Using FlagEmbedding**
+```
+pip install flag_embedding
+```
+```python
+from flag_embedding import FlagModel
+sentences = ["样例数据-1", "样例数据-2"]
+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：")
+embeddings = model.encode(sentences)
+print(embeddings)
+
+# for retrieval task, please use encode_queries() which will automatically add the instruction to each query
+# corpus in retrieval task can still use encode() or encode_corpus()
+queries = ['query_1', 'query_2']
+passages = ["样例段落-1", "样例段落-2"]
+q_embeddings = model.encode_queries(queries)
+p_embeddings = model.encode(passages)
+scores = q_embeddings @ p_embeddings.T
+```
+The value of argument `query_instruction_for_retrieval` see [Model List](https://github.com/FlagOpen/FlagEmbedding/tree/master#model-list). 
+
+FlagModel will use all available GPUs when encoding, please set `os.environ["CUDA_VISIBLE_DEVICES"]` to choose GPU.
+
+
+* **Using Sentence-Transformers**
+
+Using this model also is easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+
+```
+pip install -U sentence-transformers
+```
+```python
+from sentence_transformers import SentenceTransformer
+sentences = ["样例数据-1", "样例数据-2"]
+model = SentenceTransformer('BAAI/bge-large-zh')
+embeddings = model.encode(sentences, normalize_embeddings=True)
+print(embeddings)
+```
+For retrieval task, 
+each query should start with a instruction (instructions see [Model List](https://github.com/FlagOpen/FlagEmbedding/tree/master#model-list)). 
+```python
+from sentence_transformers import SentenceTransformer
+queries = ["手机开不了机怎么办？"]
+passages = ["样例段落-1", "样例段落-2"]
+instruction = "为这个句子生成表示以用于检索相关文章："
+
+model = SentenceTransformer('BAAI/bge-large-zh')
+q_embeddings = model.encode([instruction+q for q in queries], normalize_embeddings=True)
+p_embeddings = model.encode(passages, normalize_embeddings=True)
+scores = q_embeddings @ p_embeddings.T
+```
+
+* **Using HuggingFace Transformers**
+
+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.
+
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+# Sentences we want sentence embeddings for
+sentences = ["样例数据-1", "样例数据-2"]
+
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-large-zh')
+model = AutoModel.from_pretrained('BAAI/bge-large-zh')
+
+# Tokenize sentences
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+# for retrieval task, add a instruction to query
+# encoded_input = tokenizer([instruction + q for q in queries], padding=True, truncation=True, return_tensors='pt')
+
+# Compute token embeddings
+with torch.no_grad():
+    model_output = model(**encoded_input)
+    # Perform pooling. In this case, cls pooling.
+    sentence_embeddings = model_output[0][:, 0]
+# normalize embeddings
+sentence_embeddings = torch.nn.functional.normalize(sentence_embeddings, p=2, dim=1)
+print("Sentence embeddings:", sentence_embeddings)
+```
+
+
+## Evaluation  
+`baai-general-embedding` models achieve **state-of-the-art performance on both MTEB and C-MTEB leaderboard!**
+More details and evaluation scripts see [benchemark](benchmark/README.md). 
+
+- **MTEB**:   
+
+| Model Name |  Dimension | Sequence Length | Average (56) | Retrieval (15) |Clustering (11) | Pair Classification (3) | Reranking (4) |  STS (10) | Summarization (1) | Classification (12) |
+|:----:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
+| [**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** | 
+| [**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 | 
+| [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 |
+| [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 |
+| [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 |
+| [**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 |  
+| [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 |
+| [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 |
+| [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 |
+| [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 |
+| [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 |
+| [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 |
+| [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 |
+| [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 |
+| [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 |
+| [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 |
+| [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 |
+| [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 |
+
+
+
+- **C-MTEB**:  
+We create a benchmark C-MTEB for Chinese text embedding which consists of  31 datasets from 6 tasks. 
+Please refer to [benchemark](benchmark/README.md) for a detailed introduction.
+ 
+| Model | Embedding dimension | Avg | Retrieval | STS | PairClassification | Classification | Reranking | Clustering |
+|:-------------------------------|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|
+| [**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 |  
+| [**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** |   
+| [**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 |  
+| [**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 |  
+| [m3e-base](https://huggingface.co/moka-ai/m3e-base) | 768 | 57.10 |56.91 | 48.15 | 63.99 | 70.28 | 59.34 | 47.68 |  
+| [m3e-large](https://huggingface.co/moka-ai/m3e-large) | 1024 |  57.05 |54.75 | 48.64 | 64.3 | 71.22 | 59.66 | 48.88 |  
+| [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 |  
+| [luotuo](https://huggingface.co/silk-road/luotuo-bert-medium) | 1024 | 49.37 |  44.4 | 39.41 | 66.62 | 65.29 | 49.25 | 44.39 | 
+| [text2vec](https://huggingface.co/shibing624/text2vec-base-chinese) | 768 |  47.63 | 38.79 | 41.71 | 67.41 | 65.18 | 49.45 | 37.66 |  
+| [text2vec-large](https://huggingface.co/GanymedeNil/text2vec-large-chinese) | 1024 | 47.36 | 41.94 | 41.98 | 70.86 | 63.42 | 49.16 | 30.02 |  
+
+
+
+
+## Train
+This section will introduce the way we used to train the general embedding. 
+The training scripts are in [flag_embedding](https://github.com/FlagOpen/FlagEmbedding/tree/master/flag_embedding/baai_general_embedding/), 
+and we provide some examples to do [pre-train](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/pretrain/) and [fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune).
+
+
+**1. RetroMAE Pre-train**  
+We pre-train the model following the method [retromae](https://github.com/staoxiao/RetroMAE), 
+which shows promising improvement in retrieval task ([paper](https://aclanthology.org/2022.emnlp-main.35.pdf)). 
+The pre-training was conducted on 24 A100(40G) GPUs with a batch size of 720. 
+In retromae, the mask ratio of the encoder and decoder are 0.3, and 0.5 respectively.
+We used the AdamW optimizer and the learning rate is 2e-5.
+
+**Pre-training data**:
+- English: 
+    - [Pile](https://pile.eleuther.ai/)
+    - [wikipedia](https://huggingface.co/datasets/wikipedia)
+    - [msmarco](https://huggingface.co/datasets/Tevatron/msmarco-passage-corpus)
+- Chinese: 
+    - Subset of [wudao](https://github.com/BAAI-WuDao/Data)
+    - [baidu-baike](https://baike.baidu.com/)
+
+
+**2. Finetune**  
+We fine-tune the model using a contrastive objective. 
+The format of input data is a triple`(query, positive, negative)`. 
+Besides the negative in the triple, we also adopt in-batch negatives strategy. 
+We employ the cross-device negatives sharing method to share negatives among different GPUs, 
+which can dramatically **increase the number of negatives**.
+
+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). 
+We used the AdamW optimizer and the learning rate is 1e-5.
+The temperature for contrastive loss is 0.01.
+
+For the version with `*-instrcution`, we add instruction to the query for the retrieval task in the training. 
+For English, the instruction is `Represent this sentence for searching relevant passages: `;
+For Chinese, the instruction is `为这个句子生成表示以用于检索相关文章：`.
+In the evaluation, the instruction should be added for sentence to passages retrieval task, not be added for other tasks.
+
+
+The finetune script is accessible in this repository: [flag_embedding](https://github.com/FlagOpen/FlagEmbedding/tree/master/flag_embedding/baai_general_embedding/README.md). 
+You can easily finetune your model with it.
+
+**Training data**:
+
+- 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.
+
+- For Chinese, we collect 120M text pairs from [wudao](https://github.com/BAAI-WuDao/Data), [simclue](https://github.com/CLUEbenchmark/SimCLUE) and so on.
+
+**The data collection is to be released in the future.**
+
+We will continually update the embedding models and training codes, 
+hoping to promote the development of the embedding model community.
+
+
+## License
+FlagEmbedding is licensed under [MIT License](). The released models can be used for commercial purposes free of charge.