Mistral AI 与 NVIDIA 联合发布 12B 模型 Mistral NeMo
原标题：ResearchMistral NeMoJuly 18, 2024By Mistral AI team
AI 摘要
Mistral AI 与 NVIDIA 合作发布了 12B 参数的 Mistral NeMo 模型，支持 128k 上下文窗口，在推理、世界知识和编码方面达到同类最佳水平。该模型采用 Apache 2.0 许可，支持 FP8 推理，并引入新分词器 Tekken，在多语言压缩效率上显著提升。Mistral NeMo 已可通过 HuggingFace、Mistral 平台和 NVIDIA NIM 使用。
正文节选
Today, we are excited to release Mistral NeMo, a 12B model built in collaboration with NVIDIA. Mistral NeMo offers a large context window of up to 128k tokens. Its reasoning, world knowledge, and coding accuracy are state-of-the-art in its size category. As it relies on standard architecture, Mistral NeMo is easy to use and a drop-in replacement in any system using Mistral 7B. We have released pre-trained base and instruction-tuned checkpoints checkpoints under the Apache 2.0 license to promote