Hacker News with Generative AI: Technical Reports

Qwen3 Technical Report [pdf] (github.com/QwenLM)
BitNet b1.58 2B4T Technical Report (arxiv.org)
We introduce BitNet b1.58 2B4T, the first open-source, native 1-bit Large Language Model (LLM) at the 2-billion parameter scale.
DeepSeek-V3 Technical Report (arxiv.org)
We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
Gemma 3 Technical Report [pdf] (googleapis.com)
Gemini 1.5 Model Family: Technical Report [pdf] (googleapis.com)
Phi-3 Technical Report (arxiv.org)