2:41 5/31
incredible.ai
2:41
incredible.ai
Incredible.AIhttps://incredible.ai/
Artificial Intelligence and BigData
저작도구: Jekyll v3.9.0
최종 피드 수집: 2025-12-24 03:16
전체 (116)
4d
23d
4M
ToolFormer - Language Models Can Teach Themselves to Use Tools
1. ToolFormer - Language Models Can Teach Themselves to Use ToolsKey
Value
Paper
https://arxiv.org/pdf/2302.04
post-training
self-supervised
tools
+ 더보기
api-calls
instruction-tuning
llm
4M
LLM Training: Post-Training vs Fine-Tuning
LLM Training: Post-Training vs Fine-TuningLLM (Large Language Model) 훈련은 크게 Pre-training, Post-training, 그리고 Fine-tuning으로 나눌 수
post-training
fine-tuning
rlhf
+ 더보기
sft
alignment
instruction-tuning
llm
6M
7M
8M
8M
8M
8M
ML Basics Again
1. Basic Interview Questions1.1 Bias - Variance Tradeoff
Bias: underfitting
Variance: Overfitting
중간지점을 잘 찾아서 균형을 찾는게 관건.
Bias
variance-tradeoff
rocauc
performance
+ 더보기
prauc
machine-learning
1y
1y
1y
1y
1y
1y
1y
1y
1y