ポスト

340Bクラスだと、H100x8で推論すらできない、、😇 Required Hardware BF16 Inference: •8x H200 (1x H200 node) •16x H100 (2x H100 nodes) •16x A100 80GB (2x A100 80GB nodes) huggingface.co/nvidia/Nemotro…

メニューを開く
NVIDIA AI Developer@NVIDIAAIDev

📢 Just released: Open synthetic data generation pipeline for training LLMs. ➡️ nvda.ws/4cnGPZp ✨ Introducing Nemotron-4 340B, a family of open models, now ranking 🏆 first place on the @HuggingFace RewardBench leaderboard.🎊 Optimized for #generativeAI training.

k kanou@k_kanou

人気ポスト

もっと見る
Yahoo!リアルタイム検索アプリ