The Llama 3 Herd of Models
LLaMA3 技术报告的简要分析。
Tech Blog
This is a tech blog that focuses on my research. I'll try to use both Chinese(my native language) and English in this blog.
LLaMA 2: Open Foundation and Fine-Tuned Chat Models
Abstract: In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billio...
LLaMA: Open and Efficient Foundation Language Models
LLaMA (Large Language Model Meta AI) is a series of foundational language models developed by Meta AI. The LLaMA models are designed to be efficient and effe...
Transformer: Attention is All You Need
1. Overall Architecture
From Q-learning to Soft Actor Critic
We shall introduce the foundation of value-base RL algos, Q-learning. Then from Q-learning to DQN, A2C, and finally to SAC.
The Bottleneck of Numpy due to Different Version
Check the MKL or OpenBLAS version of NumPy.
Make PX4 from Git Clone
Build PX4-Autopilot from source code.
T-Motor F60Pro Kv2550 Parameters
T-Motor F60Pro Kv2550 建模所需参数。
MC Rate Control PX4 1.13 Release
Multicopter Rate Control in PX4 1.13 Release.
From Policy Gradient to Proximal Policy Optimization
Basis of Policy Gradient methods, from PG to PPO.
3D Rigid Motion
三维空间刚体运动，参考自《视觉SLAM十四讲》