AISpot

llama.cpp 新增 H2O-Lightning-4B 決策模型支援

llama.cpp releases版本更新地端推論開源模型

llama.cpp 加入 h2o-lightning 決策模型型別,支援 h2oai/h2o-lightning-4b——一個在 Qwen3.5-4B 上合併決策 LoRA 的模型。它與已有型別都不相容:輸出是帶前導空格的「 A」而非「A」,最多支援 255 個標籤,訓練文字出自 Python json.dumps,12.0 這類浮點必須原樣輸出為 12.0。

原標題:b11773
閱讀原文

評分42 / 45(平均 43,門檻 60)
狀態未入選

原文

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's serve_config.json and refuses a config that doesn't match. Tests skip unless the tiny test model is available locally. Assisted-by: Claude Opus 5.5 rm redundant code put labels to gguf Co-authored-by: Jonathan C. McKinney [email protected] Co-authored-by: Xuan Son Nguyen [email protected] Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/58036290 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU) Ubuntu arm64 (CPU) Ubuntu s390x (CPU) Ubuntu x64 (Vulkan) Ubuntu arm64 (Vulkan) Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries Ubuntu x64 (CUDA 13) - CUDA 13.4 libraries Ubuntu arm64 (CUDA 13) - CUDA 13.4 libraries Ubuntu x64 (ROCm 10.0) Ubuntu x64 (OpenVINO) Ubuntu x64 (SYCL FP32) Ubuntu x64 (SYCL FP16) Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide Android: Android arm64 (CPU) Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide Windows: Windows x64 (CPU) Windows arm64 (CPU) Windows arm64 (OpenCL Adreno) Windows x64 (CUDA 12) - CUDA 12.4 DLLs Windows x64 (CUDA 13) - CUDA 13.4 DLLs Windows arm64 (CUDA 13) - CUDA 13.4 DLLs Windows x64 (Vulkan) Windows arm64 (Vulkan) Windows x64 (OpenVINO) Windows x64 (SYCL) Windows x64 (ROCm 10.0) openEuler: DISABLED openEuler x86 (310p) openEuler x86 (910b, ACL Graph) openEuler aarch64 (310p) openEuler aarch64 (910b, ACL Graph) UI: UI

相關報導

llama.cpp releasesAI 評分46

llama.cpp 新增 LiquidAI d1-omni-600M 決策模型

llama.cpp 建置 b11488 新增 LiquidAI/d1-omni-600M 決策模型支援,服務端可通過 images 與 input_audio 直接接收音訊輸入,模型與多模態輸入打通。同時決策型別 d1omni 更名為 lfm2-d1-omni,images 成為 files 的別名,無記憶的 lfm2 被限定為非因果模式,CUDA 後端保留 conformer 的 GLU sigmoid。四筆改動均標註由 Claude Opus 5.5 協助完成;

llama.cpp releasesAI 評分44

llama.cpp 新增 IBM Granite Switch 決策模型支援

llama.cpp 發布 b11700,新增對 IBM Granite Switch 決策模型的轉換與推理支援,改動覆蓋 convert、common 與 server,模板參考 granite-switch-4.1-8b。開發中曾加入 decision.chat 讓決策模型兼作聊天,隨後被回退,最終確定為只要 Granite Switch 支援決策就始終支援文字,server README 也同步更新。

llama.cpp releasesAI 評分45

llama.cpp b11572 新增 vLLM d3 模型支援

llama.cpp 發布 b11572,新增對 vLLM d3 模型的支援(d2 同步更新),並加入 pplx-decider 模型支援,同時澄清命名規則、加強校驗。該版本照例提供 macOS/iOS、Linux、Windows、Android、openEuler 的預編譯包,覆蓋 CUDA 12/13、ROCm 10.0、Vulkan、SYCL、OpenVINO 以及驍龍 CPU/Adreno GPU/Hexagon NPU 等後端。