llama.cpp b11773 新增 H2O-Lightning-4B 决策模型支持

AI 摘要

llama.cpp 发布 b11773 版本，新增对 h2oai/h2o-lightning-4b 决策模型的支持，该模型基于 Qwen3.5-4B 并合并了决策 LoRA。由于现有类型均不匹配，转换器会从模型的 serve_config.json 写入决策元数据和 systemone 模板，并将标签写入 GGUF 文件。此次更新使 llama.cpp 能够正确加载和运行这一特定决策模型。

正文节选

<details open> model : add H2O-Lightning-4B decision model (#30361) * model : add H2O-Lightning-4B decision model Adds the h2o-lightning decision type for h2oai/h2o-lightning-4b (Qwen3.5-4B with a merged decision LoRA). None of the existing types match this model. It answers with " A" rather than "A", uses up to 255 labels, and was trained on Python json.dumps text, so floats like 12.0 must render as 12.0. The converter writes the decision metadata and the systemone template from the model'

发布时间：2026-10-21 10:15

抓取时间：2026-10-21 11:04

来源机构：ggml-org