Visual Document Retrieval
PEFT
Safetensors
English
German
vidore
multimodal-embedding
pavolbauer commited on
Commit
d8a2b54
·
verified ·
1 Parent(s): 2d6e3d6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -32,7 +32,7 @@ Maximal resolution is set so that 768 image patches are created at most. Experim
32
 
33
  This version is trained with `colpali-engine==0.3.4`.
34
 
35
- Data is the same as the ColPali data described in the paper. Additionally the fine-tune has been carried out with the ShareGPT4V (https://sharegpt4v.github.io/) model.
36
 
37
 
38
  ## Model Training
 
32
 
33
  This version is trained with `colpali-engine==0.3.4`.
34
 
35
+ Data is the same as the ColPali data described in the paper. Additionally the fine-tune has been carried out with the ShareGPT4V (https://sharegpt4v.github.io/) dataset.
36
 
37
 
38
  ## Model Training