fix issues + change finetuning + add results

main.py

modules/evaluators/graph_builder_llm_eval.py

modules/evaluators/graph_levenshtein_eval.py

modules/evaluators/llm_annotation_evaluator.py

modules/evaluators/llm_output_cleaner.py

modules/llm/Mistral-7b/Mistral-7b_fine_tune.py

modules/llm/Mixtral-8x7b/Mixtral-8x7b_fine_tune.py

requirements.txt

results/LLM/GPT-4/GPT-4_zero_shot_results.json

results/LLM/GPT-zs_MIX-zs_MIX-ft.png

results/LLM/Mixtral-8x7b/MIXTRAL_fine_tuned_cleaned.json

results/LLM/Mixtral-8x7b/MIXTRAL_fine_tuned_results.json

results/LLM/Mixtral-8x7b/MIXTRAL_zero_shot_results.json

results/LLM/levenshtein_distance_GPT-zs_MIX-zs_MIX-ft.png