LLaMA2 LoRA Fine Tuning

Research on LLaMA2 LoRA Fine-Tuning and Model-Merging methods

Name		Name	Last commit message	Last commit date
Latest commit History 6 Commits
README.md		README.md
SARI.py		SARI.py
config.py		config.py
data_prepare.py		data_prepare.py
eval_utils.py		eval_utils.py
evaluate.py		evaluate.py
filter_dataset.py		filter_dataset.py
filtered_tasks.json		filtered_tasks.json
load_model_and_tokenizer.py		load_model_and_tokenizer.py
postprocessors.py		postprocessors.py
preprocessors.py		preprocessors.py
prompt.py		prompt.py
train.py		train.py
useful_functions.py		useful_functions.py

Provide feedback