CMSManhattan 发布 JiRack Ultra 7B CPU 三元量化模型
原标题:CMSManhattan/JiRackUltra_7b
AI 摘要
CMSManhattan 在 Hugging Face 发布 JiRack Ultra 7B(CPU)模型,基于 DeepSeek R1-7B 架构并引入 BitNet 风格的三元(1.58bit)量化,面向 CPU 推理优化。模型更新了分词器,新增 Routing、Media、Vision、Sound、Tool call、Robotics 等标签,并提供 GGUF 量化版本与 Docker 部署方式。页面还介绍了 JiRack 编码 IDE、Ollama 支持及与 NVIDIA、FISERV 的合作关系。
正文节选
--- language: - en - zh - ja - ko - fr - es - pt - de - it - ru - ar - vi - th tags: - text-generation - ternary - bitnet - 1.58bit - cpu - gguf - qwen2.5 - deepseek - efficient - low-memory - jirack - web-ui - routing - tool-call - robotics license: mit --- # JiRack Ultra 7B (CPU) A fast and efficient 7B model optimized for CPU inference. The model was refactored with BitNet features and an updated tokenizer that includes new **Routing**, **Media**, **Vision** , **Sound** ,**Tool call**, and