Performance Testing Scripts for LLMs
Budget: $30 – $250 USD
I need a skilled individual to develop performance testing scripts in Python for Colab and Jupyter notebook.
The performance metrics that the scripts should measure are: F1 score, Perplexity, Accuracy, and BLEU score. These metrics can be found in the provided GitHub link.
Ideal skills and experience for this job include:
- Proficiency in Python, Jupyter-notebook, and Colab
- Experience with performance testing and metrics
- Ability to create scripts that accurately measure the metrics provided
- Experience with NLP tasks and language models would be a plus
https://github.com/aiegoo/datasets/tree/main/metrics
LLM: mixtral and Korean Datasets
The performance metrics that the scripts should measure are: F1 score, Perplexity, Accuracy, and BLEU score. These metrics can be found in the provided GitHub link.
Ideal skills and experience for this job include:
- Proficiency in Python, Jupyter-notebook, and Colab
- Experience with performance testing and metrics
- Ability to create scripts that accurately measure the metrics provided
- Experience with NLP tasks and language models would be a plus
https://github.com/aiegoo/datasets/tree/main/metrics
LLM: mixtral and Korean Datasets