Karna-49M-SFT-Model
**Karna-49M** is a hyper-optimized **49.38 Million parameter Small Language Model (SLM)** engineered for long-form narrative generation, character-anchored dialogues, and multi-genre creative writing. Trained from scratch and fine-tuned using Supervised Fine-Tuning (SFT) with ChatML format, it achieves fluent, coherent storytelling with instant Time-To-First-Token ( user Write a short story about an old clockmaker in Prague. assistant ```
译文尚未就绪,显示来源原文
**Karna-49M** is a hyper-optimized **49.38 Million parameter Small Language Model (SLM)** engineered for long-form narrative generation, character-anchored dialogues, and multi-genre creative writing. Trained from scratch and fine-tuned using Supervised Fine-Tuning (SFT) with ChatML format, it achieves fluent, coherent storytelling with instant Time-To-First-Token ( user Write a short story about an old clockmaker in Prague. assistant ```
AI正在发生 未来正在更新