Commit
•
653b78a
1
Parent(s):
c8300d3
Update README.md
Browse files
README.md
CHANGED
|
@@ -9,13 +9,6 @@ pipeline_tag: image-to-text
|
|
| 9 |
This model is a quantized version of the [Salesforce/blip-image-captioning-base](https://huggingface.co/Salesforce/blip-image-captioning-base), an image-to-text model.
|
| 10 |
From a memory footprint of 989 MBs -> 494 MBs by quantizing the percision of float32 to bfloat 16, reducing the model's memory size by 50 percent.
|
| 11 |
|
| 12 |
-
## Example
|
| 13 |
-
|Sample caption generation: |
|
| 14 |
-
|---|
|
| 15 |
-
|<img src="https://cdn-lfs-us-1.huggingface.co/repos/7f/10/7f109a72d03d6a2e1af427d66da2755b7af59fbdfad0074ca976d6a8cd7f54f2/1f50f922135c5880fe157eb2982992b87337cd9746eb3ca6c778ec53236e37ee?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27for_valued_gangster.png%3B+filename%3D%22for_valued_gangster.png%22%3B&response-content-type=image%2Fpng&Expires=1714485228&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTcxNDQ4NTIyOH19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmh1Z2dpbmdmYWNlLmNvL3JlcG9zLzdmLzEwLzdmMTA5YTcyZDAzZDZhMmUxYWY0MjdkNjZkYTI3NTViN2FmNTlmYmRmYWQwMDc0Y2E5NzZkNmE4Y2Q3ZjU0ZjIvMWY1MGY5MjIxMzVjNTg4MGZlMTU3ZWIyOTgyOTkyYjg3MzM3Y2Q5NzQ2ZWIzY2E2Yzc3OGVjNTMyMzZlMzdlZT9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSomcmVzcG9uc2UtY29udGVudC10eXBlPSoifV19&Signature=m7Zr7pkdPtg1Wc25X7Dv3azjUKm61Ax3Z%7EIjH2EB7Dzjjugk0IfrnjPDJEXr6kdmbFuqVBMd6KbmMatwgQKjXhv0biaSzwLfPF4jZKaoJKln%7E576rUrXpSkBsbOSTFySd7iohF5XAw357icrmm4gH7SbBJn9KrT4kDCaW%7EfaraB0TPioYa9cXskd1Ft1HgNHPSumKcXtSztPpxqoxDMO8v53KJ47Gz5HravP7u7NxudopVe0cfxHjnCNW0ElrXw-wHG%7EDSEZ5KvJmAc3rOzhKDiQoC067yIvffQ63K8qYZAoPkSfQ5GRnbGDfM38rxPpStVCp92Ka6-WTn3x5iTdww__&Key-Pair-Id=KCD77M1F0VK2B" width="400" height="300">|
|
| 16 |
-
|a man standing next to a military vehicle|
|
| 17 |
-
||
|
| 18 |
-
|
| 19 |
## How to Get Started with the Model
|
| 20 |
|
| 21 |
Use the code below to get started with the model.
|
|
|
|
| 9 |
This model is a quantized version of the [Salesforce/blip-image-captioning-base](https://huggingface.co/Salesforce/blip-image-captioning-base), an image-to-text model.
|
| 10 |
From a memory footprint of 989 MBs -> 494 MBs by quantizing the percision of float32 to bfloat 16, reducing the model's memory size by 50 percent.
|
| 11 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
## How to Get Started with the Model
|
| 13 |
|
| 14 |
Use the code below to get started with the model.
|