Tevatron
/

OmniEmbed-v0.1

Visual Document Retrieval

Model card Files Files and versions

MrLight commited on Apr 18

Commit

01bab30

·

verified ·

1 Parent(s): e85e31b

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -12,12 +12,12 @@ base_model:
 - Tevatron/Qwen2.5-Omni-7B-Thinker
 pipeline_tag: visual-document-retrieval
 ---
-# Tevatron/OmniEmbed-v0
 **OmniEmbed** is a powerful multi-modal embedding model built on [Qwen2.5-Omni-7B](https://huggingface.co/Qwen/Qwen2.5-Omni-7B) using our [Tevatron](https://github.com/texttron/tevatron/) toolkit—a unified toolkit across scale, language, and modality for document retrieval.
 OmniEmbed generates unified embeddings across multilingual text, images, audio, and video, enabling effective cross-modal retrieval for diverse applications.
-✅ Text ✅ Image ✅ Audio ✅ Video ✅ Multilingual
 ## Evaluation Results:

 - Tevatron/Qwen2.5-Omni-7B-Thinker
 pipeline_tag: visual-document-retrieval
 ---
+# Tevatron/OmniEmbed-v0.1
 **OmniEmbed** is a powerful multi-modal embedding model built on [Qwen2.5-Omni-7B](https://huggingface.co/Qwen/Qwen2.5-Omni-7B) using our [Tevatron](https://github.com/texttron/tevatron/) toolkit—a unified toolkit across scale, language, and modality for document retrieval.
 OmniEmbed generates unified embeddings across multilingual text, images, audio, and video, enabling effective cross-modal retrieval for diverse applications.
+📝 Text   🖼️ Image   🎧 Audio   🎥 Video   🌐 Multilingual
 ## Evaluation Results: