Lightweight Fine-Tuning with PEFT & LoRA
Parameter-efficient fine-tuning pipeline using LoRA to adapt DistilBERT for sentiment analysis while training less than 1% of the model parameters.
•
1 min read
Parameter-efficient fine-tuning pipeline using LoRA to adapt DistilBERT for sentiment analysis while training less than 1% of the model parameters.
Computer vision and generative AI pipeline combining SAM and SDXL for interactive object segmentation and photorealistic image editing.
Retrieval-augmented chatbot that combines semantic search, custom embeddings, and LLM prompting for grounded domain-specific conversations.