translation task python code fine tune LLAMA 2 or Mistral locally or on sagemaker

python code and instructions how fine tune LLAMA-2 or Mistral locally on my windows or on AWS sagemeker for medical text translation from English to French

use only one data set from Table 2
Table 2: Summary of existing widely-used biomedical NLP datasets for evaluation
https://arxiv.org/pdf/2311.05112.pdf
A Survey of Large Language Models in Medicine: Principles, Applications, and Challenges

prove quality by using one of good translation metric
for example
BLEU Score (Bilingual Evaluation Understudy)
or
https://towardsdatascience.com/exploring-gemba-a-new-llm-based-metric-for-translation-quality-assessment-3a3383de6d1f
etc
https://en.wikipedia.org/wiki/ROUGE_(metric)
https://en.wikipedia.org/wiki/BLEU
https://en.wikipedia.org/wiki/LEPOR
https://en.wikipedia.org/wiki/METEOR
https://en.wikipedia.org/wiki/NIST_(metric)


time: 2 days

some ideas
https://bdtechtalks.com/2023/11/03/gpt-llm-trainer/
https://colab.research.google.com/drive/1mV9sAY4QBKLmS58dpFGHgwCXQKRASR31
How to fine-tune GPT-3.5 or Llama 2 with a single instruction