Hugging Face's logo

racineai
/
QwenAmann-4B-dse

Visual Document Retrieval
Safetensors
qwen3_vl
dse
retrieval
vision-language
multimodal
document-embedding
multilingual
RAG
Model card Files
xet
Community
TW3Partners commited on
Commit
3c4c7bf
·
verified ·
1 Parent(s): 56dab4a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -31,6 +31,8 @@ A multimodal vision-language model specialized for multilingual technical docume
31
 
32
  QwenAmann-4B-dse is a 4B parameter vision-language model designed for efficient retrieval of technical documentation. It directly encodes document screenshots into embeddings, preserving all information including text, images, and layout without requiring separate content extraction.
33
 
 
 
34
  ## Performance
35
 
36
  ### ENERGY Benchmark (racineai/Open-VLM-Retrieval-Leaderboard)
 
31
 
32
  QwenAmann-4B-dse is a 4B parameter vision-language model designed for efficient retrieval of technical documentation. It directly encodes document screenshots into embeddings, preserving all information including text, images, and layout without requiring separate content extraction.
33
 
34
+ ![Racine QwenAmann](https://cdn-uploads.huggingface.co/production/uploads/659826211ec4d9b9a1f2ef3a/bJnqVmcEuprC9-gxNw579.png)
35
+
36
  ## Performance
37
 
38
  ### ENERGY Benchmark (racineai/Open-VLM-Retrieval-Leaderboard)