-
add gpt4 generated queries on test
-
clean rag training
-
Added fine-tuning python notebook for rag
-
add train rag file
-
Notebook for augmented dataset
-
Fix bug
-
Second attempt of dynamic rag
-
adding latest test dataset run
-
Adding test set generation python notebook, and correspond train and test dataset tsv files
-
Updated Augmentation Dataset with 250 verified queries
-
Notebooks for GPT evaluation
-
Fix typo in rag
-
Add second RAG notebook
-
Add changes to save new rag dadataframe
-
Add a rag helper notebook
-
Add a pre rag prompt
-
Added testing on small database to test_rag notebook, removed excess print statements
-
Updated compare_result function to allow passing the cursor, also re-ran test_pretrained and test_rag with updated loss function
-
Tweaked compare_result to work with proper directory, updated rag python notebook prompt and vector stores to increase accuracy
-
Updating compare result function in src directory, fixing small issues in test_rag prompt, adding test_rag notebook
-
fix cuda
-
Fix colab bugs
-
Prepare fine-tune for colab
-
updated rag evaluation function to match that from baseline testing
-
Update test_rag.py
-
Merge branch 'higher_rank' into main
-
finished finetuning with 16 rank lora
-
Fix bug on function evaluation
-
Upload data_augmentation.tsv file (still need to go through queries and check if they are valid)
-
Modify path to relative path
-
Add relative path functionality for colab
-
colab support part two
-
Add support for colab
-
Add a source folder
-
Move paht to a variable
-
Create demo_rag.py
-
Create rag_metadata.py
-
Create test_rag.py
-
Add column evaluator
-
added fine-tune testing on validation set with short queries only
-
Adding validation set testing of newly fine-tuned model
-
switch fine-tuned evaluation script to use 8 rank model
-
trained 8 rank LoRA finetuned model, saving train and validation datasets to disk
-
first cut at fine-tuning with masked training, working but very very slow for inference
-
fixed bug in test_finetuned notebook to read from proper directory
-
Storing 16 and 32 rank LoRA finetuned models
-
Increasing LoRA rank to 32 and updating loss function
-
first cut at adding data augmentation python notebook
-
added python notebook for testing finetuned model
-
First decent attempt, seems to generate valid queries after pre-training. Needs evaluation still
