Skip to content

Commit 7ba1d71

Browse files
bene2k1nerda-codes
andauthored
Apply suggestions from code review
Co-authored-by: nerda-codes <[email protected]>
1 parent c6751aa commit 7ba1d71

File tree

1 file changed

+4
-1
lines changed

1 file changed

+4
-1
lines changed

ai-data/managed-inference/reference-content/bge-multilingual-gemma2.mdx

Lines changed: 4 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -7,6 +7,9 @@ content:
77
paragraph: This page provides information on the BGE-Multilingual-Gemma2 embedding model
88
tags: embedding
99
categories:
10+
dates:
11+
validation: 2024-10-30
12+
posted: 2024-10-30
1013
- ai-data
1114
---
1215

@@ -37,7 +40,7 @@ As such, it is distributed under the [Gemma terms of use](https://ai.google.dev/
3740

3841
## Why is it useful?
3942

40-
- BGE-Multilingual-Gemma2 tops the [MTEB leaderboard](https://huggingface.co/spaces/mteb/leaderboard) scoring #1 in french, #1 in polish, #7 in english, as of writing (Q4 2024).
43+
- BGE-Multilingual-Gemma2 tops the [MTEB leaderboard](https://huggingface.co/spaces/mteb/leaderboard) scoring the number one spot in French and Polish, and number seven in English, at the time of writing this page (Q4 2024).
4144
- As its name suggests, the model's training data spans a broad range of languages, including English, Chinese, Polish, French, and more!
4245
- It encodes text into 3584-dimensional vectors, providing a very detailed representation of sentence semantics.
4346
- BGE-Multilingual-Gemma2 in its L4/FP32 configuration boats a high context length of 4096 tokens, particularly useful for ingesting data and building RAG applications.

0 commit comments

Comments
 (0)