StandardOne-8B-GGUF v2.2 发布并支持 llama.cpp 决策端点
原标题:StandardThinking/StandardOne-8B-GGUF
AI 摘要
StandardThinking 在 Hugging Face 发布了 StandardOne-8B-GGUF 的 v2.2 版本,基于 Ministral 3 8B 文本模型与 Pixtral 视觉塔(mistral3 架构),提供从 BF16 到 IQ2_M 共九种量化文件及视觉投影器。更新为九个语言模型文件新增了决策元数据,使其支持 llama.cpp 原生的 /v1/systemone 决策端点,无需引擎分叉或权重转换。
正文节选
--- base_model: StandardThinking/StandardOne-8B base_model_relation: quantized license: apache-2.0 library_name: gguf pipeline_tag: text-generation tags: - gguf - llama.cpp - mistral3 - decision-model --- # Standard One 8B — GGUF > **Updated weights (v2.2, 2026-10-04).** These files are built from Standard One 8B v2.2. If you downloaded them before, download them again or > pin a full commit revision. Earlier versions stay available under the tags `v1`, `v1.1` and `v2`. > **Decision