PEFT
Safetensors
vidore-experimental
vidore
manu commited on
Commit
1cb649a
1 Parent(s): 9f79f9a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -8,7 +8,7 @@ tags:
8
 
9
  # ColSmolVLM-alpha: Visual Retriever based on SmolVLM-Instruct with ColBERT strategy
10
 
11
- ### This is the base version trained with batch_size 128 for 3 epochs
12
 
13
  ColSmolVLM is a model based on a novel model architecture and training strategy based on Vision Language Models (VLMs) to efficiently index documents from their visual features.
14
  It is a SmolVLM extension that generates [ColBERT](https://arxiv.org/abs/2004.12832)- style multi-vector representations of text and images.
 
8
 
9
  # ColSmolVLM-alpha: Visual Retriever based on SmolVLM-Instruct with ColBERT strategy
10
 
11
+ ### This is a version trained with batch_size 128 for 3 epochs
12
 
13
  ColSmolVLM is a model based on a novel model architecture and training strategy based on Vision Language Models (VLMs) to efficiently index documents from their visual features.
14
  It is a SmolVLM extension that generates [ColBERT](https://arxiv.org/abs/2004.12832)- style multi-vector representations of text and images.