ziyjiang commited on
Commit
795dcd0
·
verified ·
1 Parent(s): 3e21148

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -17,7 +17,6 @@ tags:
17
 
18
  This repo contains the model checkpoint for [VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks](https://arxiv.org/abs/2410.05160). In this paper, we aimed at building a unified multimodal embedding model for any tasks. Our model is based on converting an existing well-trained VLM (Phi-3.5-V) into an embedding model. The basic idea is to add an [EOS] token in the end of the sequence, which will be used as the representation of the multimodal inputs.
19
 
20
- <img width="1432" alt="abs" src="https://raw.githubusercontent.com/TIGER-AI-Lab/VLM2Vec/refs/heads/main/figures//train_vlm.png">
21
 
22
  ## Release
23
  Our model is being trained on MMEB-train and evaluated on MMEB-eval with contrastive learning. We only use in-batch negatives for training. Our best results were based on Lora training with batch size of 1024. We also have checkpoint with full training with batch size of 2048. Our results on 36 evaluation datasets are:
@@ -34,7 +33,7 @@ Our model is being trained on MMEB-train and evaluated on MMEB-eval with contras
34
 
35
  ### Experimental Results
36
  Our model can outperform the existing baselines by a huge margin.
37
- <img width="900" alt="abs" src="https://raw.githubusercontent.com/TIGER-AI-Lab/VLM2Vec/refs/heads/main/figures//vlm2vec_results.png">
38
 
39
  ## How to use VLM2Vec
40
 
 
17
 
18
  This repo contains the model checkpoint for [VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks](https://arxiv.org/abs/2410.05160). In this paper, we aimed at building a unified multimodal embedding model for any tasks. Our model is based on converting an existing well-trained VLM (Phi-3.5-V) into an embedding model. The basic idea is to add an [EOS] token in the end of the sequence, which will be used as the representation of the multimodal inputs.
19
 
 
20
 
21
  ## Release
22
  Our model is being trained on MMEB-train and evaluated on MMEB-eval with contrastive learning. We only use in-batch negatives for training. Our best results were based on Lora training with batch size of 1024. We also have checkpoint with full training with batch size of 2048. Our results on 36 evaluation datasets are:
 
33
 
34
  ### Experimental Results
35
  Our model can outperform the existing baselines by a huge margin.
36
+ <img width="900" alt="abs" src="vlm2vec_v1_result.png">
37
 
38
  ## How to use VLM2Vec
39