From 978ee96fd3d93d03300591017c1e2d260096d3e9 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Mon, 28 Apr 2025 19:43:49 +0200 Subject: [PATCH] chore(model gallery): add nvidia_openmath-nemotron-14b (#5263) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index 0af174bd..4872af02 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -6265,6 +6265,22 @@ - filename: nvidia_OpenMath-Nemotron-7B-Q4_K_M.gguf sha256: e205dd86ab9c73614d88dc3a84bd1a4e94255528f9ddb33e739ea23830342ee4 uri: huggingface://bartowski/nvidia_OpenMath-Nemotron-7B-GGUF/nvidia_OpenMath-Nemotron-7B-Q4_K_M.gguf +- !!merge <<: *qwen25 + name: "nvidia_openmath-nemotron-14b" + icon: https://cdn-avatars.huggingface.co/v1/production/uploads/1613114437487-60262a8e0703121c822a80b6.png + urls: + - https://huggingface.co/nvidia/OpenMath-Nemotron-14B + - https://huggingface.co/bartowski/nvidia_OpenMath-Nemotron-14B-GGUF + description: | + OpenMath-Nemotron-14B is created by finetuning Qwen/Qwen2.5-14B on OpenMathReasoning dataset. This model is ready for commercial use. + OpenMath-Nemotron models achieve state-of-the-art results on popular mathematical benchmarks. We present metrics as pass@1 (maj@64) where pass@1 is an average accuracy across 64 generations and maj@64 is the result of majority voting. Please see our paper for more details on the evaluation setup. + overrides: + parameters: + model: nvidia_OpenMath-Nemotron-14B-Q4_K_M.gguf + files: + - filename: nvidia_OpenMath-Nemotron-14B-Q4_K_M.gguf + sha256: 2abeccea53899b81cea11fd84fe458d673783f68e7790489fff5c295da6d8026 + uri: huggingface://bartowski/nvidia_OpenMath-Nemotron-14B-GGUF/nvidia_OpenMath-Nemotron-14B-Q4_K_M.gguf - &llama31 url: "github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master" ## LLama3.1 icon: https://avatars.githubusercontent.com/u/153379578