반응형
태그
논문 리뷰,
LLM 추론,
llm reasoning,
Chain of Thought,
프롬프트 엔지니어링,
LLM,
트랜스포머,
ICLR 2023,
문제 분해,
L2M,
Least-to-Most Prompting,
Least-to-Most,
GSM8K,
NeurIPS 2023,
선호 학습,
LLM 정렬,
Direct Preference Optimization,
MIT HAN Lab,
엣지 LLM,
4bit 양자화,
LLM 양자화,
Weight Quantization,
NeurIPS 2017,
SOSP 2023,
GPU 메모리 관리,
LLM 서빙,
LLM 압축,
AWQ,
KV cache,
모델 경량화,
llm alignment,
rlhf,
llm 파인튜닝,
in-context learning,
gptq,
PagedAttention,
vllm,
NeurIPS 2022,
few-shot learning,
positional encoding,
self-attention,
multi-head attention,
DPO,
ppo,
cot,
Transformer,
nlp,
attention,