Hybrid Mamba-2 + Transformer 2.94B LLM (Nemotron-H style) — Korean 3B model pretrained from scratch on ×ばつ NVIDIA B200 GPUs with SFT + DPO alignment

transformer sft dpo pretraining fp8 korean-llm nemotron hybrid-architecture mamba2 nvidia-b200

• Updated Mar 26, 2026
• Python

Korean 3B LLM (pure Transformer) pretrained from scratch on ×ばつ NVIDIA B200 GPUs with SFT + ORPO alignment

transformer sft gqa pretraining fp8 korean-llm flash-attention gguf orpo nvidia-b200

• Updated Mar 26, 2026
• Python

Real-time Global Semiconductor Supply Chain API. Programmatic JSON-LD feed for Nvidia H100, B200, TSMC 3nm/5nm wafer pricing, ASML EUV capacity & silicon spot markets. Optimized for autonomous AI agents, LLM-scrapers & hedge fund quant-trading. Supports HTTP 402 M2M Solana settlement. Essential data for Bloomberg, Reuters & supply chain disruption.

dataset web-scraping micropayments market-data quantitative-finance real-time-data semiconductor autonomous-agents ai-agents machine-to-machine solana alternative-data blackwell tsmc high-bandwidth-memory agentic-workflow http-402 llm-tooling nvidia-b200 algorithmic-trading-dotnet

• Updated May 6, 2026
• Python