USC-Applied-NLP-Group/SQL-Generation at 57326c2f8c14677cce5face037e8d6899beed31a

SQL-Generation

Ctrl+K

4 contributors

History: 60 commits

DeanGumas

Added testing on small database to test_rag notebook, removed excess print statements

57326c2 about 2 months ago

__pycache__
updated rag evaluation function to match that from baseline testing about 2 months ago
deepseek-coder-1.3b-instruct
Add column evaluator about 2 months ago
fine-tuned-model-16
finished finetuning with 16 rank lora about 2 months ago
fine-tuned-model-8-diff
trained 8 rank LoRA finetuned model, saving train and validation datasets to disk about 2 months ago
fine-tuned-model-8
first cut at fine-tuning with masked training, working but very very slow for inference about 2 months ago
nba-data
added nba kaggle sqlite database and testing python notebook 2 months ago
src
Updated compare_result function to allow passing the cursor, also re-ran test_pretrained and test_rag with updated loss function about 2 months ago
train-data
Upload data_augmentation.tsv file (still need to go through queries and check if they are valid) about 2 months ago
train.hf
trained 8 rank LoRA finetuned model, saving train and validation datasets to disk about 2 months ago
val-16.hf
finished finetuning with 16 rank lora about 2 months ago
val.hf
trained 8 rank LoRA finetuned model, saving train and validation datasets to disk about 2 months ago
.gitattributes

1.56 kB

added nba kaggle sqlite database and testing python notebook 2 months ago
README.md

5.11 kB

Test about 2 months ago
augment_data.ipynb

13.6 kB

first cut at adding data augmentation python notebook about 2 months ago
database_setup.ipynb

1.81 kB

added nba kaggle sqlite database and testing python notebook 2 months ago
demo.py

5.42 kB

Renamed demo script and added initial pre-trained test python notebook about 2 months ago
demo_rag.py

12 kB

Move paht to a variable about 2 months ago
finetune_model.ipynb

214 kB

fix cuda about 2 months ago
rag_metadata.py

2.3 kB

Create rag_metadata.py about 2 months ago
test_finetuned.ipynb

31 kB

switch fine-tuned evaluation script to use 8 rank model about 2 months ago
test_pretrained.ipynb

14.5 kB

Updated compare_result function to allow passing the cursor, also re-ran test_pretrained and test_rag with updated loss function about 2 months ago
test_rag.ipynb

23.4 kB

Added testing on small database to test_rag notebook, removed excess print statements about 2 months ago
test_rag.py

19.4 kB

Updating compare result function in src directory, fixing small issues in test_rag prompt, adding test_rag notebook about 2 months ago