LoRA and DoRA Implementation
Parameter-efficient fine-tuning from first principles — every matrix decomposition derived and implemented in PyTorch without libraries. Validated against Hugging Face PEFT outputs for correctness.
Personal project
Projects tagged llms
Back to portfolioLarge Language Models with MLX
Chat inference on Apple Silicon using MLX — exploring the runtime, quantization options, and packaging story for local LLM deployment with Mistral and Llama2.
Personal project