Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

modified inference script and custom preprocessing script #1

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
+685 −0
Open

modified inference script and custom preprocessing script #1

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4fcc216
Create molmo-7B-D-bnb-4bit_no_tensorflow.py
BBC-Esq Sep 26, 2024
ce597f0
Create image_preprocessing_molmo.py
BBC-Esq Sep 26, 2024
9ce2408
Update README.md
BBC-Esq Sep 26, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,6 +42,7 @@ Additional stuff
```
pip install einops tensorflow-cpu transformers accelerate bitsandbytes
```
> NOTE: If you use the "no_tensorflow" version of the script above you do not need to install tensorflow. However, you MUST also replace the current version of ```image_preprocessing_molmo.py``` downloaded from the huggingface repo with the one in this repository above.

## Run

Expand All @@ -52,3 +53,4 @@ python molmo-7B-O-bnb-4bit.py

python molmo-7B-D-bnb-4bit.py
```
> NOTE: If you use the "no_tensorflow" version of the script above you must enter into the script the hardcoded path to the model on your computer as well as a hardcoded path to the image you want to process. As such, you must download the huggingface repo files first in order have a hardcoded path to specify.
Loading