Safetensors
razzant commited on
Commit
daa6833
·
1 Parent(s): 0700252

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -25,7 +25,7 @@ To further enhance the model's multimodal capabilities, we employ trainable spec
25
  2. Once the adapter has learned to map ViT's visual embeddings to the language model's textual space, we proceed to unfreeze Mistral for improved understanding of dialog formats and complex queries.
26
 
27
  <p align="left">
28
- <img src="https://raw.githubusercontent.com/AIRI-Institute/OmniFusion/main/content/datasets.png" width="80%">
29
  </p>
30
 
31
  ### Results
@@ -45,7 +45,7 @@ Model Performance on Visual Dialog Benchmark
45
  ### Examples
46
 
47
  <p align="left">
48
- <img src="https://raw.githubusercontent.com/AIRI-Institute/OmniFusion/main/content/examples.png" width="100%">
49
  </p>
50
 
51
  ### Future Plans
 
25
  2. Once the adapter has learned to map ViT's visual embeddings to the language model's textual space, we proceed to unfreeze Mistral for improved understanding of dialog formats and complex queries.
26
 
27
  <p align="left">
28
+ <img src="https://raw.githubusercontent.com/AIRI-Institute/OmniFusion/main/content/datasets.png" width="50%">
29
  </p>
30
 
31
  ### Results
 
45
  ### Examples
46
 
47
  <p align="left">
48
+ <img src="https://raw.githubusercontent.com/AIRI-Institute/OmniFusion/main/content/examples.png" width="70%">
49
  </p>
50
 
51
  ### Future Plans