Zhaokai Huang's starred repositories
DeepLearning-500-questions
深度学习500问,以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述,以帮助自己及有需要的读者。 全书分为18个章节,50余万字。由于水平有限,书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作,联系scutjy2015@163.com 版权所有,违权必究 Tan 2018.06
tuning_playbook
A playbook for systematically maximizing the performance of deep learning models.
flash-attention
Fast and memory-efficient exact attention
modelscope
ModelScope: bring the notion of Model-as-a-Service to life.
ChatGLM-Efficient-Tuning
Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调
LLM-As-Chatbot
LLM as a Chatbot Service
Algorithm-Practice-in-Industry
搜索、推荐、广告、用增等工业界实践文章收集(来源:知乎、Datafuntalk、技术公众号)
recommenders-addons
Additional utils and helpers to extend TensorFlow when build recommendation systems, contributed and maintained by SIG Recommenders.
chatgpt-briefing
极客时间 - ChatGPT公开课
es_dfm
Implementation and experimental comparison of ES-DFM (Yang et al. 2021), Delayed feedback model(DFM, Chapelle 2014), Feedback Shift Importance Weighting (FSIW) (Yasui et al. 2020), Fake Negative Weighted (FNW) (Ktena et al. 2019) and Fake Negative calibration(FNC) (Ktena et al. 2019)
awesome-models
基于TensorFlow实现推荐系统的model