Hugging Face's logo

google
/
embeddinggemma-2

Feature Extraction
Transformers
Safetensors
sentence-transformers
multilingual
embedding_gemma2
embedding
multimodal-embedding
multimodal
vision
audio
video
image-feature-extraction
audio-feature-extraction
video-feature-extraction
sentence-similarity
Model card Files
xet
 Community
20

Update README.md

#21
by hschechter - opened
base: refs/heads/main
←
from: refs/pr/21
Discussion Files changed
+7
-7
Files changed (1) hide show
  1. README.md +7 -7
README.md CHANGED
@@ -16,7 +16,7 @@ tags:
16
  - sentence-similarity
17
  language:
18
  - multilingual
19
- library_name: transformers
20
  ---
21
 
22
  <div align="center">
@@ -79,12 +79,12 @@ EmbeddingGemma 2 was evaluated across text, code, vision, visual document, video
79
  | :---- | :---- | :---- | :---- | :---- |
80
  | *Text* | Massive Text Embedding Benchmark (MTEB, multilingual, v2) | Mean(Task), Multiple | 61.36 | 61.15 |
81
  | | Massive Text Embedding Benchmark (MTEB, code, v1) | Mean(Task), NDCG@10 | 78.68 | 68.76 |
82
- | *Image* | Massive Image Embedding Benchmark (MIEB, lite) | Mean(TaskType), Multiple | 64.64 | \- |
83
  | | Massive Multimodal Embedding Benchmark (MMEB v2 \- Image) | Mean(Task), Hit@1 | 57.28 | \- |
84
  | | Massive Multimodal Embedding Benchmark (MMEB v2 \- VisDoc) | Mean(Task), NDCG@5 | 67.84 | \- |
85
  | *Video* | Massive Multimodal Embedding Benchmark (MMEB v2 \- Video) | Mean(Task), Hit@1 | 50.67 | \- |
86
  | *Audio* | Massive Sound Embedding Benchmark (MSEB, Retrieval) | Mean(Task), MRR@10 | 69.54 | \- |
87
- | | Massive Audio Embedding Benchmark (MAEB) *Hugging Face*&nbsp; | Mean(Task), Multiple | 49.39 | \- |
88
 
89
  ### Evaluation Results with Vector Truncation
90
 
@@ -93,10 +93,10 @@ With this, model users can reduce storage requirements, with minimal quality imp
93
 
94
  | Output Dimension | Compression Ratio | MTEB *(multilingual, v2) Mean(Task)* | MTEB *(eng, v2) Mean(Task)* | MTEB *(code, v1) Mean(Task)* | MIEB *(lite) Mean(TaskType)* | MMEB (v2) *Overall* | MSEB *(Retrieval) Mean(Task)* | MAEB *Mean(Task)* |
95
  | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
96
- | 768d (Full) | 1:1 | 61.36 | 68.46 | 78.68 | 64.64 | 59.01 | 69.54 | 49.39 |
97
- | 512d | 1:1.5 | 61.17 | 68.41 | 77.24 | 64.32 | 58.38 | 69.18 | 49.21 |
98
- | 256d | 1:3 | 60.41 | 67.78 | 76.18 | 63.13 | 56.24 | 66.76 | 48.91 |
99
- | 128d | 1:6 | 57.89 | 65.68 | 71.41 | 59.06 | 45.65 | 56.71 | 46.92 |
100
 
101
  ## **Quick Start**
102
 
 
16
  - sentence-similarity
17
  language:
18
  - multilingual
19
+ library_name: sentence-transformers
20
  ---
21
 
22
  <div align="center">
 
79
  | :---- | :---- | :---- | :---- | :---- |
80
  | *Text* | Massive Text Embedding Benchmark (MTEB, multilingual, v2) | Mean(Task), Multiple | 61.36 | 61.15 |
81
  | | Massive Text Embedding Benchmark (MTEB, code, v1) | Mean(Task), NDCG@10 | 78.68 | 68.76 |
82
+ | *Image* | Massive Image Embedding Benchmark (MIEB, lite) | Mean(TaskType), Multiple | 65.67 | \- |
83
  | | Massive Multimodal Embedding Benchmark (MMEB v2 \- Image) | Mean(Task), Hit@1 | 57.28 | \- |
84
  | | Massive Multimodal Embedding Benchmark (MMEB v2 \- VisDoc) | Mean(Task), NDCG@5 | 67.84 | \- |
85
  | *Video* | Massive Multimodal Embedding Benchmark (MMEB v2 \- Video) | Mean(Task), Hit@1 | 50.67 | \- |
86
  | *Audio* | Massive Sound Embedding Benchmark (MSEB, Retrieval) | Mean(Task), MRR@10 | 69.54 | \- |
87
+ | | Massive Audio Embedding Benchmark (MAEB) *Hugging Face*&nbsp; | Mean(Task), Multiple | 49.87 | \- |
88
 
89
  ### Evaluation Results with Vector Truncation
90
 
 
93
 
94
  | Output Dimension | Compression Ratio | MTEB *(multilingual, v2) Mean(Task)* | MTEB *(eng, v2) Mean(Task)* | MTEB *(code, v1) Mean(Task)* | MIEB *(lite) Mean(TaskType)* | MMEB (v2) *Overall* | MSEB *(Retrieval) Mean(Task)* | MAEB *Mean(Task)* |
95
  | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
96
+ | 768d (Full) | 1:1 | 61.36 | 68.46 | 78.68 | 65.67 | 59.01 | 69.54 | 49.87 |
97
+ | 512d | 1:1.5 | 61.17 | 68.41 | 77.24 | 65.34 | 58.38 | 69.18 | 49.76 |
98
+ | 256d | 1:3 | 60.41 | 67.78 | 76.18 | 64.16 | 56.24 | 66.76 | 49.13 |
99
+ | 128d | 1:6 | 57.89 | 65.68 | 71.41 | 59.97 | 45.65 | 56.71 | 47.28 |
100
 
101
  ## **Quick Start**
102