DeepSeek-V3 Technical Report
Paper One-line Summary (TL;DR)DeepSeek-V3 is an open-source SOTA that combines Aux-loss-free Load-Balancing Bias, FP8 mixed-precision …
39 min
MoE
Open-Source LLM
DeepSeek
Causal LM
AI Research
MoE
1 page
Search
Start searching
Searching...
No results
↑↓
Navigate
↵
Select
ESC
Close
⌘K
Shortcut