al-fariqy/gemma-3-4b-it-qat

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

mount secret

Update README.md

fixed way to read secret

switched to cli to download gated models

corrected model used

switched to google's repo due to mismatch dimension with mmproj (wrong file?)

fell back to `-m` and `--mmproj`

switched to `-hf` flag to get models

updated to 4b

changed model to 1b qat

Update README.md

Update fake.py

Update fake.py

Update Dockerfile

Update fake.py

Update Dockerfile

Update Dockerfile

Update Dockerfile

Create fake.py

Update Dockerfile

Create Dockerfile

initial commit