Hugging Face's logo

Metric-AI
/
ColQwenStella-2b-multilingual

Visual Document Retrieval
PEFT
Safetensors
vidore
multimodal_embedding
multilingual_embedding
Text-to-Visual Document (T→VD) retrieval
Model card Files Community
Markgazol commited on
Commit
b2538f6
·
verified ·
1 Parent(s): 6d84b59

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -27,7 +27,7 @@ pipeline_tag: visual-document-retrieval
27
  ---
28
  # ColQwenStella-2b-multilingual: Multilingual Visual Retriever based on the combination of Qwen2 Vision and stella_en_1.5B_v5 model.
29
 
30
- ## Ranked #1 among models <= 2B parameters and #7 overall on the Vidore benchmark (as of February 11, 2025). The reported scores on the [Vidore Leaderboard](https://huggingface.co/spaces/vidore/vidore-leaderboard) correspond to checkpoint-1800.
31
 
32
  ### This is the base version trained on 4xA100 80GB with per_device_batch_size=128 for 5 epoch.
33
 
 
27
  ---
28
  # ColQwenStella-2b-multilingual: Multilingual Visual Retriever based on the combination of Qwen2 Vision and stella_en_1.5B_v5 model.
29
 
30
+ ## Ranked #1 among models <= 2B parameters and #8 overall on the Vidore benchmark (as of February 11, 2025). The reported scores on the [Vidore Leaderboard](https://huggingface.co/spaces/vidore/vidore-leaderboard) correspond to checkpoint-1800.
31
 
32
  ### This is the base version trained on 4xA100 80GB with per_device_batch_size=128 for 5 epoch.
33