태그
LLM,
python,
reinforcement learning,
머신러닝 상품화,
Finetuning,
MLOps,
DevOps,
til,
머신러닝,
코딩테스트,
Adapting Language Model to Domain Specific RAG,
RAG파인튜닝,
Declarative Self-improving Python,
gpt4omini,
prompttuning,
model context protocol,
dspy,
softeer-바이러스,
pow함수,
typeerror: 'list' object is not callable,
potential-based reward shaping,
llm-grounded diffusion,
reward design with language models,
traffic signal control,
sim2real transfer,
prompt to transfer,
ai agent,
promptengineering,
largelanguagemodel,
모듈러연산,
global 키워드,
PPO,
다익스트라알고리즘,
완전이진트리,
우선순위큐,
인접리스트,
데이터 유형,
Priority Queue,
우선순위 큐,
Rag,
데이터 저장소,
최단거리,
dataset,
Diffusion,
raft,
Dijkstra,
MCP,
알고리즘,
지역변수,
Heap,
전역변수,