Add model seq_len and dimensions to the README.md
#1
by xfalcox - opened
README.md
CHANGED
|
@@ -25,6 +25,17 @@ This allows you to obtain token weights (similar to the BM25) without any additi
|
|
| 25 |
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.
|
| 26 |
|
| 27 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
## FAQ
|
| 29 |
|
| 30 |
**1. Introduction for different retrieval methods**
|
|
|
|
| 25 |
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.
|
| 26 |
|
| 27 |
|
| 28 |
+
## Model Specs
|
| 29 |
+
|
| 30 |
+
| Model Name | Dimension | Sequence Length |
|
| 31 |
+
|:----:|:---:|:---:|
|
| 32 |
+
| [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) | 1024 | 8192 |
|
| 33 |
+
| [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) | 1024 | 512 |
|
| 34 |
+
| [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) | 768 | 512 |
|
| 35 |
+
| [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) | 384 | 512 |
|
| 36 |
+
|
| 37 |
+
|
| 38 |
+
|
| 39 |
## FAQ
|
| 40 |
|
| 41 |
**1. Introduction for different retrieval methods**
|