3 contributors

History: 15 commits

edugp

Update README and add a training doc

5019883 almost 3 years ago

clip_spanish_141230_samples
Add model trained on 141230 samples, achieving a validation loss of 2.1384739875793457 almost 3 years ago
clip_spanish_1_percent
Add training scripts and initial model trained on 1% of the data. about 3 years ago
clip_spanish_20_percent
Add new model trained on the spanish subset of suitable images of the 20% of the WIT dataset, with a validation loss of 2.4001 about 3 years ago
clip_spanish_20_percent_98_1_1_split
Add new model trained on the spanish subset of suitable images of the 20% of the WIT dataset, using a 998/1/1 train/valid/test split with a validation loss of 22.3439 about 3 years ago
clip_spanish_72972_samples
Add model trained on 72972 samples almost 3 years ago
.gitattributes

737 Bytes

Add training scripts and initial model trained on 1% of the data. about 3 years ago
README.md

1.64 kB

Update README and add a training doc almost 3 years ago
config.json

4.16 kB

Copy latest model to repo root almost 3 years ago
configuration_hybrid_clip.py

4.39 kB

Add actual files instead of symlinks almost 3 years ago
discard_incorrect_files.py

1.11 kB

Add all necessary files to replicate training run almost 3 years ago
flax_model.msgpack

792 MB
LFS

Copy latest model to repo root almost 3 years ago
join_datasets_custom_split.py

1.35 kB

Add all necessary files to replicate training run almost 3 years ago
modeling_hybrid_clip.py

18 kB

Add actual files instead of symlinks almost 3 years ago
prepare_wit.py

4.27 kB

Add all necessary files to replicate training run almost 3 years ago
run-clip.sh

805 Bytes

Add all necessary files to replicate training run almost 3 years ago
run_hybrid_clip.py

21.7 kB

Add all necessary files to replicate training run almost 3 years ago
scale_convert.py

1.39 kB

Add all necessary files to replicate training run almost 3 years ago
test_on_image.py

1.37 kB

Add all necessary files to replicate training run almost 3 years ago
training.md

530 Bytes

Update README and add a training doc almost 3 years ago