PEFT (Parameter-Efficient Fine-Tuning): PEFT is a technique that focuses on updating only a small subset of the model’s parameters during fine-tuning.
thsluck
thsluck
·
AI & ML interests
None yet
Organizations
None yet
models 10
thsluck/llm-course-hw3-tinyllama-qlora
Updated
thsluck/llm-course-hw3-dora
Text Generation • 0.3B • Updated • 6
thsluck/llm-course-hw3-lora
Text Generation • 0.3B • Updated • 6
thsluck/llm-course-hw3-tinyllamma-qlora
Updated
thsluck/llm-course-hw2-dpo
Text Generation • 0.1B • Updated • 3
thsluck/llm-course-hw2-ppo
Text Generation • 0.1B • Updated • 1
thsluck/llm-course-hw2-ppo-kag
Text Generation • 0.1B • Updated • 2
thsluck/llm-course-hw2-reward-model
Text Classification • 0.1B • Updated • 1
thsluck/trainer_output
Text Classification • 0.1B • Updated • 1
thsluck/llm-course-hw1
Updated • 5
datasets 0
None public yet