Shitao commited on
Commit
7774ef4
1 Parent(s): d4532f2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -9
README.md CHANGED
@@ -2622,18 +2622,30 @@ language:
2622
  <p>
2623
  </h4>
2624
 
2625
- More details please refer to our Github: [FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding).
2626
 
 
2627
 
2628
- [English](README.md) | [中文](https://github.com/FlagOpen/FlagEmbedding/blob/master/README_zh.md)
2629
 
2630
- FlagEmbedding can map any text to a low-dimensional dense vector which can be used for tasks like retrieval, classification, clustering, or semantic search.
2631
- And it also can be used in vector databases for LLMs.
2632
 
2633
- ************* 🌟**Updates**🌟 *************
2634
- - 10/12/2023: Release [LLM-Embedder](./FlagEmbedding/llm_embedder/README.md), a unified embedding model to support diverse retrieval augmentation needs for LLMs. [Paper](https://arxiv.org/pdf/2310.07554.pdf) :fire:
2635
- - 09/15/2023: The [technical report](https://arxiv.org/pdf/2309.07597.pdf) of BGE has been released
2636
- - 09/15/2023: The [masive training data](https://data.baai.ac.cn/details/BAAI-MTP) of BGE has been released
 
 
 
 
 
 
 
 
 
 
 
 
 
2637
  - 09/12/2023: New models:
2638
  - **New reranker model**: release cross-encoder models `BAAI/bge-reranker-base` and `BAAI/bge-reranker-large`, which are more powerful than embedding model. We recommend to use/fine-tune them to re-rank top-k documents returned by embedding models.
2639
  - **update embedding model**: release `bge-*-v1.5` embedding model to alleviate the issue of the similarity distribution, and enhance its retrieval ability without instruction.
@@ -2658,6 +2670,7 @@ And it also can be used in vector databases for LLMs.
2658
 
2659
  | Model | Language | | Description | query instruction for retrieval [1] |
2660
  |:-------------------------------|:--------:| :--------:| :--------:|:--------:|
 
2661
  | [BAAI/llm-embedder](https://huggingface.co/BAAI/llm-embedder) | English | [Inference](./FlagEmbedding/llm_embedder/README.md) [Fine-tune](./FlagEmbedding/llm_embedder/README.md) | a unified embedding model to support diverse retrieval augmentation needs for LLMs | See [README](./FlagEmbedding/llm_embedder/README.md) |
2662
  | [BAAI/bge-reranker-large](https://huggingface.co/BAAI/bge-reranker-large) | Chinese and English | [Inference](#usage-for-reranker) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker) | a cross-encoder model which is more accurate but less efficient [2] | |
2663
  | [BAAI/bge-reranker-base](https://huggingface.co/BAAI/bge-reranker-base) | Chinese and English | [Inference](#usage-for-reranker) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker) | a cross-encoder model which is more accurate but less efficient [2] | |
@@ -2674,7 +2687,6 @@ And it also can be used in vector databases for LLMs.
2674
  | [BAAI/bge-base-zh](https://huggingface.co/BAAI/bge-base-zh) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | a base-scale model but with similar ability to `bge-large-zh` | `为这个句子生成表示以用于检索相关文章:` |
2675
  | [BAAI/bge-small-zh](https://huggingface.co/BAAI/bge-small-zh) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | 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:` |
2676
 
2677
-
2678
  [1\]: If you need to search the relevant passages to a query, we suggest 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** needs to be added to passages.
2679
 
2680
  [2\]: Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding. To balance the accuracy and time cost, cross-encoder is widely used to re-rank top-k documents retrieved by other simple models.
 
2622
  <p>
2623
  </h4>
2624
 
2625
+ For more details please refer to our Github: [FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding).
2626
 
2627
+ If you are looking for a model that supports more languages, longer texts, and other retrieval methods, you can try using [bge-m3](https://huggingface.co/BAAI/bge-m3).
2628
 
 
2629
 
2630
+ [English](README.md) | [中文](https://github.com/FlagOpen/FlagEmbedding/blob/master/README_zh.md)
 
2631
 
2632
+ FlagEmbedding focuses on retrieval-augmented LLMs, consisting of the following projects currently:
2633
+
2634
+ - **Long-Context LLM**: [Activation Beacon](https://github.com/FlagOpen/FlagEmbedding/tree/master/Long_LLM/activation_beacon)
2635
+ - **Fine-tuning of LM** : [LM-Cocktail](https://github.com/FlagOpen/FlagEmbedding/tree/master/LM_Cocktail)
2636
+ - **Dense Retrieval**: [BGE-M3](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/BGE_M3), [LLM Embedder](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_embedder), [BGE Embedding](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/baai_general_embedding)
2637
+ - **Reranker Model**: [BGE Reranker](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/reranker)
2638
+ - **Benchmark**: [C-MTEB](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB)
2639
+
2640
+ ## News
2641
+ - 1/30/2024: Release **BGE-M3**, a new member to BGE model series! M3 stands for **M**ulti-linguality (100+ languages), **M**ulti-granularities (input length up to 8192), **M**ulti-Functionality (unification of dense, lexical, multi-vec/colbert retrieval).
2642
+ It is the first embedding model that supports all three retrieval methods, achieving new SOTA on multi-lingual (MIRACL) and cross-lingual (MKQA) benchmarks.
2643
+ [Technical Report](https://github.com/FlagOpen/FlagEmbedding/blob/master/FlagEmbedding/BGE_M3/BGE_M3.pdf) and [Code](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/BGE_M3). :fire:
2644
+ - 1/9/2024: Release [Activation-Beacon](https://github.com/FlagOpen/FlagEmbedding/tree/master/Long_LLM/activation_beacon), an effective, efficient, compatible, and low-cost (training) method to extend the context length of LLM. [Technical Report](https://arxiv.org/abs/2401.03462) :fire:
2645
+ - 12/24/2023: Release **LLaRA**, a LLaMA-7B based dense retriever, leading to state-of-the-art performances on MS MARCO and BEIR. Model and code will be open-sourced. Please stay tuned. [Technical Report](https://arxiv.org/abs/2312.15503) :fire:
2646
+ - 11/23/2023: Release [LM-Cocktail](https://github.com/FlagOpen/FlagEmbedding/tree/master/LM_Cocktail), a method to maintain general capabilities during fine-tuning by merging multiple language models. [Technical Report](https://arxiv.org/abs/2311.13534) :fire:
2647
+ - 10/12/2023: Release [LLM-Embedder](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_embedder), a unified embedding model to support diverse retrieval augmentation needs for LLMs. [Technical Report](https://arxiv.org/pdf/2310.07554.pdf)
2648
+ - 09/15/2023: The [technical report](https://arxiv.org/pdf/2309.07597.pdf) and [massive training data](https://data.baai.ac.cn/details/BAAI-MTP) of BGE has been released
2649
  - 09/12/2023: New models:
2650
  - **New reranker model**: release cross-encoder models `BAAI/bge-reranker-base` and `BAAI/bge-reranker-large`, which are more powerful than embedding model. We recommend to use/fine-tune them to re-rank top-k documents returned by embedding models.
2651
  - **update embedding model**: release `bge-*-v1.5` embedding model to alleviate the issue of the similarity distribution, and enhance its retrieval ability without instruction.
 
2670
 
2671
  | Model | Language | | Description | query instruction for retrieval [1] |
2672
  |:-------------------------------|:--------:| :--------:| :--------:|:--------:|
2673
+ | [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) | Multilingual | [Inference](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/BGE_M3#usage) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/BGE_M3) | Multi-Functionality(dense retrieval, sparse retrieval, multi-vector(colbert)), Multi-Linguality, and Multi-Granularity(8192 tokens) | |
2674
  | [BAAI/llm-embedder](https://huggingface.co/BAAI/llm-embedder) | English | [Inference](./FlagEmbedding/llm_embedder/README.md) [Fine-tune](./FlagEmbedding/llm_embedder/README.md) | a unified embedding model to support diverse retrieval augmentation needs for LLMs | See [README](./FlagEmbedding/llm_embedder/README.md) |
2675
  | [BAAI/bge-reranker-large](https://huggingface.co/BAAI/bge-reranker-large) | Chinese and English | [Inference](#usage-for-reranker) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker) | a cross-encoder model which is more accurate but less efficient [2] | |
2676
  | [BAAI/bge-reranker-base](https://huggingface.co/BAAI/bge-reranker-base) | Chinese and English | [Inference](#usage-for-reranker) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker) | a cross-encoder model which is more accurate but less efficient [2] | |
 
2687
  | [BAAI/bge-base-zh](https://huggingface.co/BAAI/bge-base-zh) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | a base-scale model but with similar ability to `bge-large-zh` | `为这个句子生成表示以用于检索相关文章:` |
2688
  | [BAAI/bge-small-zh](https://huggingface.co/BAAI/bge-small-zh) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | 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:` |
2689
 
 
2690
  [1\]: If you need to search the relevant passages to a query, we suggest 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** needs to be added to passages.
2691
 
2692
  [2\]: Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding. To balance the accuracy and time cost, cross-encoder is widely used to re-rank top-k documents retrieved by other simple models.