Hugging Face's logo

kpyu
/
eilev-blip2-opt-2.7b

Image-to-Text
Transformers
Safetensors
English
blip-2
text2text-generation
video-to-text
video-captioning
image-captioning
visual-question-answering
Inference Endpoints
Model card Files Community
kpyu commited on
Commit
908a96b
•
1 Parent(s): f1eb471

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -14,6 +14,8 @@ tags:
14
  ---
15
  # Model Card for EILEV BLIP-2-OPT-2.7B
16
 
 
 
17
  [Salesforce/blip2-opt-2.7b](https://huggingface.co/Salesforce/blip2-opt-2.7b) trained using [EILEV](https://github.com/yukw777/EILEV), a novel training method that can elicit in-context learning in vision-language models (VLMs) for egocentric videos without requiring massive, naturalistic egocentric video datasets.
18
 
19
  ## Model Details
@@ -22,7 +24,7 @@ tags:
22
 
23
  EILEV BLIP-2-OPT-2.7B is a VLM optimized for egocentric video. It can perform in-context learning over videos and texts.
24
 
25
- ### Model Sources [optional]
26
 
27
  - **Repository:** https://github.com/yukw777/EILEV
28
  - **Paper:** [More Information Needed]
 
14
  ---
15
  # Model Card for EILEV BLIP-2-OPT-2.7B
16
 
17
+ ![Teaser](teaser.png)
18
+
19
  [Salesforce/blip2-opt-2.7b](https://huggingface.co/Salesforce/blip2-opt-2.7b) trained using [EILEV](https://github.com/yukw777/EILEV), a novel training method that can elicit in-context learning in vision-language models (VLMs) for egocentric videos without requiring massive, naturalistic egocentric video datasets.
20
 
21
  ## Model Details
 
24
 
25
  EILEV BLIP-2-OPT-2.7B is a VLM optimized for egocentric video. It can perform in-context learning over videos and texts.
26
 
27
+ ### Model Sources
28
 
29
  - **Repository:** https://github.com/yukw777/EILEV
30
  - **Paper:** [More Information Needed]