soosoo/bge-m3
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Xiao 2024-03-02 12:28:04 +00:00 committed by system
parent 3ab7155aa9
commit 3641912a2b
No known key found for this signature in database
GPG Key ID: 6A528E38E0733467
1 changed files with 10 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
README.md
View File

@ -27,8 +27,9 @@ Utilizing the re-ranking model (e.g., [bge-reranker](https://github.com/FlagOpen
## News: ## 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). - 2024/3/2: Release unified fine-tuning [example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/unified_finetune) and [data](https://huggingface.co/datasets/Shitao/bge-m3-data)
- 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) - 2024/2/6: 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).
- 2024/2/1: **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 ## Specs
@ -47,8 +48,10 @@ Utilizing the re-ranking model (e.g., [bge-reranker](https://github.com/FlagOpen
- Data - Data
| Dataset | Introduction | | Dataset | Introduction |
|:----:|:---:| |:----------------------------------------------------------:|:-------------------------------------------------:|
| [MLDR](https://huggingface.co/datasets/Shitao/MLDR) | Docuemtn Retrieval Dataset, covering 13 languages | | [MLDR](https://huggingface.co/datasets/Shitao/MLDR) | Docuemtn Retrieval Dataset, covering 13 languages |
| [bge-m3-data](https://huggingface.co/datasets/Shitao/bge-m3-data) | Fine-tuning data used by bge-m3 |
## FAQ ## FAQ
@ -88,7 +91,8 @@ In our experiments, we use [Pyserini](https://github.com/FlagOpen/FlagEmbedding/
You can follow the common in this [example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) You can follow the common in this [example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune)
to fine-tune the dense embedding. to fine-tune the dense embedding.
Our code and data for unified fine-tuning (dense, sparse, and multi-vectors) will be released. If you want to fine-tune all embedding function of m3, you can refer to the [unified_fine-tuning example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/unified_finetune)
@ -258,7 +262,6 @@ If you have no enough resource to fine-tuning model with long text, the method i
Refer to our [report](https://arxiv.org/pdf/2402.03216.pdf) for more details. 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 ## Acknowledgement