아기여우의 자기계발로그 · Scour

LLM Post-training | CSP LLM Post-training 서비스 (AWS Bedrock, Microsoft Azure, Google Vertex AI)

littlefoxdiary.tistory.com·49w

Model Compression Recipe - Generalized Knowledge Distillation (GKD)

littlefoxdiary.tistory.com·49w

Model Compression Recipe - Knowledge Distillation (KD)

littlefoxdiary.tistory.com·51w

Alignment Tuning Recipe - Direct Preference Optimization (DPO)

littlefoxdiary.tistory.com·52w

LLM 성능 향상을 위한 Post-training 방법론 개요

littlefoxdiary.tistory.com·52w

[논문리뷰] DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

littlefoxdiary.tistory.com·65w

언어 모델을 화이트 해킹하자

littlefoxdiary.tistory.com·88w

언어 모델을 화이트 해킹하자 | ① Red-Teaming Large Language Models

littlefoxdiary.tistory.com·93w

Llama3 한국어 성능 테스트 | Colab에서 Meta-Llama-3 모델 사용해보기🦙

littlefoxdiary.tistory.com·94w

[논문리뷰] SOLAR 10.7B: Scaling Large Language Models with Simple yet EffectiveDepth Up-Scaling

littlefoxdiary.tistory.com·111w

Log in to enable infinite scrolling