Visual Document Retrieval
PEFT
Safetensors
English
vidore
multimodal-embedding
yydxlv commited on
Commit
9dc398d
·
verified ·
1 Parent(s): fd3358e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -18,7 +18,7 @@ ColQwen is a model based on a novel model architecture and training strategy bas
18
  It is a Qwen2-VL-7B extension that generates ColBERT- style multi-vector representations of text and images.
19
  It was introduced in the paper ColPali: Efficient Document Retrieval with Vision Language Models and first released in this repository.
20
 
21
- This version is trained with batch_size 32*8 for 3 epochs.
22
 
23
 
24
 
 
18
  It is a Qwen2-VL-7B extension that generates ColBERT- style multi-vector representations of text and images.
19
  It was introduced in the paper ColPali: Efficient Document Retrieval with Vision Language Models and first released in this repository.
20
 
21
+ This version is trained on 8*A800 with batch_size 32*8 for 3 epochs.
22
 
23
 
24