From 987b5dcac1112b9b1b76d5c9c458feef207f1e68 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Thu, 7 Aug 2025 00:31:17 +0200 Subject: [PATCH] chore(model gallery): add openai_gpt-oss-20b-neo (#5986) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index 7d53b5dbc..04be07934 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -127,6 +127,30 @@ - filename: gpt-oss-120b-mxfp4-00003-of-00003.gguf sha256: b326bfd8ac696c4b9a14e9e84d5529b2bb86847aea0e65443cbf075accba8b71 uri: huggingface://ggml-org/gpt-oss-120b-GGUF/gpt-oss-120b-mxfp4-00003-of-00003.gguf +- !!merge <<: *gptoss + name: "openai_gpt-oss-20b-neo" + icon: https://huggingface.co/DavidAU/Openai_gpt-oss-20b-NEO-GGUF/resolve/main/matrix1.gif + urls: + - https://huggingface.co/DavidAU/Openai_gpt-oss-20b-NEO-GGUF + description: | + These are NEO Imatrix GGUFs, NEO dataset by DavidAU. + + NEO dataset improves overall performance, and is for all use cases. + + Example output below (creative), using settings below. + + Model also passed "hard" coding test too (6 experts); no issues (IQ4_NL). + + (Forcing the model to create code with no dependencies and limits of coding short cuts, with multiple loops, and in real time with no blocking in a language that does not support it normally.) + + Due to quanting issues with this model (which result in oddball quant sizes / mixtures), only TESTED quants will be uploaded (at the moment). + overrides: + parameters: + model: OpenAI-20B-NEO-MXFP4_MOE4.gguf + files: + - filename: OpenAI-20B-NEO-MXFP4_MOE4.gguf + sha256: 066c84a0844b1f1f4515e5c64095fe4c67e86d5eb70db4e368e283b1134d9c1e + uri: huggingface://DavidAU/Openai_gpt-oss-20b-NEO-GGUF/OpenAI-20B-NEO-MXFP4_MOE4.gguf - &afm name: "arcee-ai_afm-4.5b" url: "github:mudler/LocalAI/gallery/chatml.yaml@master"