-
uploaded latest inference script for adversarial and non-adversarial tasks with the 15 attack types along with the attack test samples
-
Delete inference_script.ipynb
-
Delete inference_script.py
-
uploaded latest inference script for both adversarial and non-adversarial tasks along with the 15 attack types and the attack questions
-
Upload inference_script.ipynb
uploaded full inference script (contains non-adversarial and adversarial tests)
-
Merge branch 'main' of https://huggingface.co/PrivacyPreservingML-SecureSQL/SecureSQL into main
-
full training run completed, created combined dataset tsv, validation code must be updated still
-
Upload inference_script.ipynb
Added a simple inference script with tunable instructions and can be used with regular and adversarial datasets
-
first full fine-tuning run, resulting model stored in finetuned-model-16
-
Ran first 1 epoch training run, trying to extract private data, no luck yet :(
-
added scripts for combining training data into single tsv
-
bugfix in finetuning script, added gitignore
-
adding DeepSeek coder model
-
added nba sqlite database
-
adding tennis sqlite data, basic utils and training/testing python notebooks
-
initial commit
