AI Engineer - LLM Fine-tuning and Prompt Engineering
TextFine Tuning
I was responsible for fine-tuning large language models, including Llama2, to perform specialized instruction-based tasks. My work included data preparation, prompt engineering, and crafting datasets to improve few-shot learning. This fine-tuning enabled the models to better respond to specific instructions and enhanced their generalization capabilities.
• Developed and implemented pipelines for model finetuning and inference.
• Engineered prompts and incorporated few-shot learning examples.
• Quantized large models for efficient deployment and cost optimization.
• Improved model output quality through iterative training and evaluation.
I was responsible for fine-tuning large language models, including Llama2, to perform specialized instruction-based tasks. My work included data preparation, prompt engineering, and crafting datasets to improve few-shot learning. This fine-tuning enabled the models to better respond to specific instructions and enhanced their generalization capabilities. • Developed and implemented pipelines for model finetuning and inference. • Engineered prompts and incorporated few-shot learning examples. • Quantized large models for efficient deployment and cost optimization. • Improved model output quality through iterative training and evaluation.
2023 - Present