Update README.md
Browse files
README.md
CHANGED
@@ -13,24 +13,29 @@ license: mit
|
|
13 |
<a href=#usage>Usage</a> |
|
14 |
<a href="#evaluation">Evaluation</a> |
|
15 |
<a href="#train">Train</a> |
|
16 |
-
<a href="#contact">Contact</a> |
|
17 |
<a href="#citation">Citation</a> |
|
18 |
<a href="#license">License</a>
|
19 |
<p>
|
20 |
</h4>
|
21 |
|
22 |
-
More details please refer to our Github: [FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding)
|
23 |
|
24 |
|
25 |
[English](README.md) | [ä¸æ–‡](https://github.com/FlagOpen/FlagEmbedding/blob/master/README_zh.md)
|
26 |
|
27 |
-
FlagEmbedding
|
28 |
-
And it also can be used in vector databases for LLMs.
|
29 |
|
30 |
-
|
31 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
- 09/15/2023: The [technical report](https://arxiv.org/pdf/2309.07597.pdf) of BGE has been released
|
33 |
-
- 09/15/2023: The [
|
34 |
- 09/12/2023: New models:
|
35 |
- **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.
|
36 |
- **update embedding model**: release `bge-*-v1.5` embedding model to alleviate the issue of the similarity distribution, and enhance its retrieval ability without instruction.
|
@@ -384,10 +389,6 @@ The data format is the same as embedding model, so you can fine-tune it easily f
|
|
384 |
More details please refer to [./FlagEmbedding/reranker/README.md](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/reranker)
|
385 |
|
386 |
|
387 |
-
## Contact
|
388 |
-
If you have any question or suggestion related to this project, feel free to open an issue or pull request.
|
389 |
-
You also can email Shitao Xiao([email protected]) and Zheng Liu([email protected]).
|
390 |
-
|
391 |
|
392 |
## Citation
|
393 |
|
|
|
13 |
<a href=#usage>Usage</a> |
|
14 |
<a href="#evaluation">Evaluation</a> |
|
15 |
<a href="#train">Train</a> |
|
|
|
16 |
<a href="#citation">Citation</a> |
|
17 |
<a href="#license">License</a>
|
18 |
<p>
|
19 |
</h4>
|
20 |
|
21 |
+
**More details please refer to our Github: [FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding).**
|
22 |
|
23 |
|
24 |
[English](README.md) | [ä¸æ–‡](https://github.com/FlagOpen/FlagEmbedding/blob/master/README_zh.md)
|
25 |
|
26 |
+
FlagEmbedding focuses on retrieval-augmented LLMs, consisting of the following projects currently:
|
|
|
27 |
|
28 |
+
- **Fine-tuning of LM** : [LM-Cocktail](https://github.com/FlagOpen/FlagEmbedding/tree/master/LM_Cocktail)
|
29 |
+
- **Dense Retrieval**: [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), [C-MTEB](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB)
|
30 |
+
- **Reranker Model**: [BGE Reranker](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/reranker)
|
31 |
+
|
32 |
+
|
33 |
+
## News
|
34 |
+
|
35 |
+
- 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:
|
36 |
+
- 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)
|
37 |
- 09/15/2023: The [technical report](https://arxiv.org/pdf/2309.07597.pdf) of BGE has been released
|
38 |
+
- 09/15/2023: The [massive training data](https://data.baai.ac.cn/details/BAAI-MTP) of BGE has been released
|
39 |
- 09/12/2023: New models:
|
40 |
- **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.
|
41 |
- **update embedding model**: release `bge-*-v1.5` embedding model to alleviate the issue of the similarity distribution, and enhance its retrieval ability without instruction.
|
|
|
389 |
More details please refer to [./FlagEmbedding/reranker/README.md](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/reranker)
|
390 |
|
391 |
|
|
|
|
|
|
|
|
|
392 |
|
393 |
## Citation
|
394 |
|