GRPO (Group Relative Policy Optimization) Study Notes
We introduce Group Relative Policy Optimization (GRPO), a variant of Proximal Policy Optimization (PPO)
DeepSeek
Advertisement
DeepSeek #OpenSourceWeek - Five Consecutive Releases
We're a tiny team @deepseek_ai exploring AGI.
![Andrej Karpathy in-depth explanation of large language model (LLM) technology (Part 1) - [Pretraining and Inference]](https://res.cooltool.vip/article_res/cover/4da9a4f896a13d3c9ea34b747e7d5f92.jpeg)
Andrej Karpathy in-depth explanation of large language model (LLM) technology (Part 1) - [Pretraining and Inference]
- introduction - pretraining data (internet) - tokenization - neural network I/O - neural network internals - inference
DeepSeek Janus Series: Unified Multimodal Understanding and Generation Models
Janus-Series: Unified Multimodal Understanding and Generation Models
Comparison of the reasoning processes between ChatGPT o1 pro and DeepSeek R1
DeepSeek R1 Vs ChatGPT 01 (My Experience)
DeepSeek R1: X.com User Reviews
Deepseek-r1 is open source and on par with o1 preview - @bindureddy
Paper of DeepSeek-R1: Exploration and Breakthrough of the New Generation Inference Model
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning