From 73a15ad29ab604f3bdc31601849a9defe86d563f Mon Sep 17 00:00:00 2001 From: Xiao Date: Wed, 31 Jan 2024 01:59:23 +0000 Subject: [PATCH] Add model seq_len and dimensions to the README.md (#1) - Add model seq_len and dimensions to the README.md (038773d84178649586cfdf228df3e2a0838a5180) Co-authored-by: RAFAEL SANTOS SILVA --- README.md | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/README.md b/README.md index 1046434..be9e87c 100644 --- a/README.md +++ b/README.md @@ -25,6 +25,17 @@ This allows you to obtain token weights (similar to the BM25) without any additi 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. +## Model Specs + +| Model Name | Dimension | Sequence Length | +|:----:|:---:|:---:| +| [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) | 1024 | 8192 | +| [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) | 1024 | 512 | +| [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) | 768 | 512 | +| [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) | 384 | 512 | + + + ## FAQ **1. Introduction for different retrieval methods**