Upload model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,271 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+license: mit
+---
+
+For more details please refer to our github repo: https://github.com/FlagOpen/FlagEmbedding
+
+# BGE-M3 ([paper](https://arxiv.org/pdf/2402.03216.pdf), [code](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/BGE_M3))
+
+In this project, we introduce BGE-M3, which is distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity. 
+- Multi-Functionality: It can simultaneously perform the three common retrieval functionalities of embedding model: dense retrieval, multi-vector retrieval, and sparse retrieval. 
+- Multi-Linguality: It can support more than 100 working languages. 
+- Multi-Granularity: It is able to process inputs of different granularities, spanning from short sentences to long documents of up to 8192 tokens. 
+
+**Some suggestions for retrieval pipeline in RAG:**
+We recommend to use following pipeline: hybrid retrieval + re-ranking. 
+- Hybrid retrieval leverages the strengths of various methods, offering higher accuracy and stronger generalization capabilities. 
+A classic example: using both embedding retrieval and the BM25 algorithm. 
+Now, you can try to use BGE-M3, which supports both embedding and sparse retrieval. 
+This allows you to obtain token weights (similar to the BM25) without any additional cost when generate dense embeddings.
+- As cross-encoder models, re-ranker demonstrates higher accuracy than bi-encoder embedding model. 
+Utilizing the re-ranking model (e.g., [bge-reranker](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/reranker), [cohere-reranker](https://txt.cohere.com/rerank/)) after retrieval can further filter the selected text.
+
+
+## News:
+- 2/6/2024: We release the [MLDR](https://huggingface.co/datasets/Shitao/MLDR) (a long document retrieval dataset covering 13 languages) and [evaluation pipeline](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB/MLDR). 
+- 2/1/2024: **Thanks for the excellent tool from Vespa.** You can easily use multiple modes of BGE-M3 following this [notebook](https://github.com/vespa-engine/pyvespa/blob/master/docs/sphinx/source/examples/mother-of-all-embedding-models-cloud.ipynb)
+
+
+## Specs
+
+- Model  
+
+| Model Name |  Dimension | Sequence Length | Introduction |
+|:----:|:---:|:---:|:---:|
+| [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) | 1024 | 8192 | multilingual; unified fine-tuning (dense, sparse, and colbert) from bge-m3-unsupervised|
+| [BAAI/bge-m3-unsupervised](https://huggingface.co/BAAI/bge-m3-unsupervised) | 1024 | 8192 | multilingual; contrastive learning from bge-m3-retromae |
+| [BAAI/bge-m3-retromae](https://huggingface.co/BAAI/bge-m3-retromae) | -- | 8192 | multilingual; extend the max_length of [xlm-roberta](https://huggingface.co/FacebookAI/xlm-roberta-large) to 8192 and further pretrained via [retromae](https://github.com/staoxiao/RetroMAE)| 
+| [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) | 1024 | 512 | English model | 
+| [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) |  768 | 512 | English model | 
+| [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) |  384 | 512 | English model | 
+
+- Data
+
+| Dataset |  Introduction |
+|:----:|:---:|
+| [MLDR](https://huggingface.co/datasets/Shitao/MLDR) | Docuemtn Retrieval Dataset, covering 13 languages|
+
+
+## FAQ
+
+**1. Introduction for different retrieval methods**
+
+- Dense retrieval: map the text into a single embedding, e.g., [DPR](https://arxiv.org/abs/2004.04906), [BGE-v1.5](https://github.com/FlagOpen/FlagEmbedding)
+- Sparse retrieval (lexical matching): a vector of size equal to the vocabulary, with the majority of positions set to zero, calculating a weight only for tokens present in the text. e.g., BM25, [unicoil](https://arxiv.org/pdf/2106.14807.pdf), and [splade](https://arxiv.org/abs/2107.05720)
+- Multi-vector retrieval: use multiple vectors to represent a text, e.g., [ColBERT](https://arxiv.org/abs/2004.12832).
+
+**2. Comparison with BGE-v1.5 and other monolingual models**
+
+BGE-M3 is a multilingual model, and its ability in monolingual embedding retrieval may not surpass models specifically designed for single languages. 
+However, we still recommend trying BGE-M3 because of its versatility (support for multiple languages and long texts). 
+Moreover, it can simultaneously generate multiple representations, and using them together can enhance accuracy and generalization, 
+unlike most existing models that can only perform dense retrieval. 
+
+In the open-source community, there are many excellent models (e.g., jina-embedding, colbert, e5, etc), 
+and users can choose a model that suits their specific needs based on practical considerations, 
+such as whether to require multilingual or cross-language support, and whether to process long texts.
+
+**3. How to use BGE-M3 in other projects?**
+
+For embedding retrieval, you can employ the BGE-M3 model using the same approach as BGE. 
+The only difference is that the BGE-M3 model no longer requires adding instructions to the queries. 
+For sparse retrieval methods, most open-source libraries currently do not support direct utilization of the BGE-M3 model. 
+Contributions from the community are welcome. 
+
+
+In our experiments, we use [Pyserini](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB/MLDR#hybrid-retrieval-dense--sparse) and Faiss to do hybrid retrieval.
+**Now you can ou can try the hybrid mode of BGE-M3 in [Vespa](https://github.com/vespa-engine/pyvespa/blob/master/docs/sphinx/source/examples/mother-of-all-embedding-models-cloud.ipynb
+). Thanks @jobergum.**
+
+
+**4. How to fine-tune bge-M3 model?**
+
+You can follow the common in this [example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) 
+to fine-tune the dense embedding.
+
+Our code and data for unified fine-tuning (dense, sparse, and multi-vectors) will be released.
+
+
+
+
+## Usage
+
+Install: 
+```
+git clone https://github.com/FlagOpen/FlagEmbedding.git
+cd FlagEmbedding
+pip install -e .
+```
+or: 
+```
+pip install -U FlagEmbedding
+```
+
+
+
+### Generate Embedding for text
+
+- Dense Embedding
+```python
+from FlagEmbedding import BGEM3FlagModel
+
+model = BGEM3FlagModel('BAAI/bge-m3',  
+                       use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
+
+sentences_1 = ["What is BGE M3?", "Defination of BM25"]
+sentences_2 = ["BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.", 
+               "BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document"]
+
+embeddings_1 = model.encode(sentences_1, 
+                            batch_size=12, 
+                            max_length=8192, # If you don't need such a long length, you can set a smaller value to speed up the encoding process.
+                            )['dense_vecs']
+embeddings_2 = model.encode(sentences_2)['dense_vecs']
+similarity = embeddings_1 @ embeddings_2.T
+print(similarity)
+# [[0.6265, 0.3477], [0.3499, 0.678 ]]
+```
+You also can use sentence-transformers and huggingface transformers to generate dense embeddings.
+Refer to [baai_general_embedding](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/baai_general_embedding#usage) for details.
+
+
+- Sparse Embedding (Lexical Weight)
+```python
+from FlagEmbedding import BGEM3FlagModel
+
+model = BGEM3FlagModel('BAAI/bge-m3',  use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
+
+sentences_1 = ["What is BGE M3?", "Defination of BM25"]
+sentences_2 = ["BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.", 
+               "BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document"]
+
+output_1 = model.encode(sentences_1, return_dense=True, return_sparse=True, return_colbert_vecs=False)
+output_2 = model.encode(sentences_2, return_dense=True, return_sparse=True, return_colbert_vecs=False)
+
+# you can see the weight for each token:
+print(model.convert_id_to_token(output_1['lexical_weights']))
+# [{'What': 0.08356, 'is': 0.0814, 'B': 0.1296, 'GE': 0.252, 'M': 0.1702, '3': 0.2695, '?': 0.04092}, 
+#  {'De': 0.05005, 'fin': 0.1368, 'ation': 0.04498, 'of': 0.0633, 'BM': 0.2515, '25': 0.3335}]
+
+
+# compute the scores via lexical mathcing
+lexical_scores = model.compute_lexical_matching_score(output_1['lexical_weights'][0], output_2['lexical_weights'][0])
+print(lexical_scores)
+# 0.19554901123046875
+
+print(model.compute_lexical_matching_score(output_1['lexical_weights'][0], output_1['lexical_weights'][1]))
+# 0.0
+```
+
+- Multi-Vector (ColBERT)
+```python
+from FlagEmbedding import BGEM3FlagModel
+
+model = BGEM3FlagModel('BAAI/bge-m3',  use_fp16=True) 
+
+sentences_1 = ["What is BGE M3?", "Defination of BM25"]
+sentences_2 = ["BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.", 
+               "BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document"]
+
+output_1 = model.encode(sentences_1, return_dense=True, return_sparse=True, return_colbert_vecs=True)
+output_2 = model.encode(sentences_2, return_dense=True, return_sparse=True, return_colbert_vecs=True)
+
+print(model.colbert_score(output_1['colbert_vecs'][0], output_2['colbert_vecs'][0]))
+print(model.colbert_score(output_1['colbert_vecs'][0], output_2['colbert_vecs'][1]))
+# 0.7797
+# 0.4620
+```
+
+
+### Compute score for text pairs
+Input a list of text pairs, you can get the scores computed by different methods.
+```python
+from FlagEmbedding import BGEM3FlagModel
+
+model = BGEM3FlagModel('BAAI/bge-m3',  use_fp16=True) 
+
+sentences_1 = ["What is BGE M3?", "Defination of BM25"]
+sentences_2 = ["BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.", 
+               "BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document"]
+
+sentence_pairs = [[i,j] for i in sentences_1 for j in sentences_2]
+
+print(model.compute_score(sentence_pairs, 
+                          max_passage_length=128, # a smaller max length leads to a lower latency
+                          weights_for_different_modes=[0.4, 0.2, 0.4])) # weights_for_different_modes(w) is used to do weighted sum: w[0]*dense_score + w[1]*sparse_score + w[2]*colbert_score
+
+# {
+#   'colbert': [0.7796499729156494, 0.4621465802192688, 0.4523794651031494, 0.7898575067520142], 
+#   'sparse': [0.195556640625, 0.00879669189453125, 0.0, 0.1802978515625], 
+#   'dense': [0.6259765625, 0.347412109375, 0.349853515625, 0.67822265625], 
+#   'sparse+dense': [0.482503205537796, 0.23454029858112335, 0.2332356721162796, 0.5122477412223816], 
+#   'colbert+sparse+dense': [0.6013619303703308, 0.3255828022956848, 0.32089319825172424, 0.6232916116714478]
+# }
+```
+
+
+
+
+## Evaluation  
+
+- Multilingual (Miracl dataset) 
+
+![avatar](./imgs/miracl.jpg)
+
+- Cross-lingual (MKQA dataset)
+
+![avatar](./imgs/mkqa.jpg)
+
+- Long Document Retrieval
+  - MLDR:   
+  ![avatar](./imgs/long.jpg)
+  Please note that [MLDR](https://huggingface.co/datasets/Shitao/MLDR) is a document retrieval dataset we constructed via LLM, 
+  covering 13 languages, including test set, validation set, and training set. 
+  We utilized the training set from MLDR to enhance the model's long document retrieval capabilities. 
+  Therefore, comparing baselines with `Dense w.o.long`(fine-tuning without long document dataset) is more equitable. 
+  Additionally, this long document retrieval dataset will be open-sourced to address the current lack of open-source multilingual long text retrieval datasets.
+  We believe that this data will be helpful for the open-source community in training document retrieval models.
+
+  - NarritiveQA:  
+  ![avatar](./imgs/nqa.jpg)
+
+
+## Training
+- Self-knowledge Distillation: combining multiple outputs from different 
+retrieval modes as reward signal to enhance the performance of single mode(especially for sparse retrieval and multi-vec(colbert) retrival)
+- Efficient Batching: Improve the efficiency when fine-tuning on long text. 
+The small-batch strategy is simple but effective, which also can used to fine-tune large embedding model.
+- MCLS: A simple method to improve the performance on long text without fine-tuning. 
+If you have no enough resource to fine-tuning model with long text, the method is useful.
+
+Refer to our [report](https://arxiv.org/pdf/2402.03216.pdf) for more details.
+
+**The fine-tuning codes and datasets will be open-sourced in the near future.**
+
+
+## Acknowledgement
+
+Thanks the authors of open-sourced datasets, including Miracl, MKQA, NarritiveQA, etc. 
+Thanks the open-sourced libraries like [Tevatron](https://github.com/texttron/tevatron), [pyserial](https://github.com/pyserial/pyserial).
+
+
+
+## Citation
+
+If you find this repository useful, please consider giving a star :star: and citation
+
+```
+@misc{bge-m3,
+      title={BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation}, 
+      author={Jianlv Chen and Shitao Xiao and Peitian Zhang and Kun Luo and Defu Lian and Zheng Liu},
+      year={2024},
+      eprint={2402.03216},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/home/jovyan/data-static-dgx05-pvc/jaehyeok/contrastive_pretraining/preliminary_checkpoints/random_infonce_cuda2_20250213_085935/checkpoints/checkpoint_epoch_1_step_120_loss_0.1573.pt",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "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-05,
+  "max_position_embeddings": 8194,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.48.3",
+    "pytorch": "2.2.0a0+81ea7a4"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41cb24ca745ef30ca273105565bcfbee23d5af1c104973e6a1f765cf0d4aaef7
+size 2271064456

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 1024,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e3b8957de04e3a4ed42b1a11381556f9adad8d0d502b9dd071c75f626b28f40
+size 17083053

tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 1024,
+  "model_max_length": 1024,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}