CLIP (ViT) (#315)

Browse Source

* probably approximatelly correct CLIPTextEncoder

* implemented CLIPEncoderLayer as built-in nn.TransformerEncoderLayer

* replaced embedding layer with simple matrix

* implemented ViT

* added ViT tests

* fixed tests

* added pooler_output for text

* implemented complete CLIPModel

* implemented init

* implemented convert.py and from_pretrained

* fixed some minor bugs and added the README.md

* removed tokenizer unused comments

* removed unused deps

* updated ACKNOWLEDGEMENTS.md

* Feat: Image Processor for CLIP (#1)

@nkasmanoff:
* clip image processor
* added example usage

* refactored image preprocessing

* deleted unused image_config.py

* removed preprocessing port

* added dependency to mlx-data

* fixed attribution and moved photos to assets

* implemented a simple port of CLIPImageProcessor

* review changes

* PR review changes

* renamed too verbose arg

* updated README.md

* nits in readme / conversion

* simplify some stuff, remove unneeded inits

* remove more init stuff

* more simplify

* make test a unit test

* update main readme

* readme nits

---------

Co-authored-by: Noah Kasmanoff <nkasmanoff@gmail.com>
Co-authored-by: Awni Hannun <awni@apple.com>

...

This commit is contained in:

Gabrijel Boduljak

2024-01-31 23:19:53 +01:00

committed by GitHub

parent ba3a9355d1

commit 94358219cf

14 changed files with 890 additions and 0 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

BIN

clip/assets/cat.jpeg Normal file

Binary file not shown.

Side by Side After Width:  |  Height:  |  Size: 193 KiB

BIN

clip/assets/dog.jpeg Normal file

Binary file not shown.

Side by Side After Width:  |  Height:  |  Size: 90 KiB