From b5992255ac62927960072096820131222c56e13a Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Sun, 5 Jan 2025 09:22:00 +0100 Subject: [PATCH] chore(model gallery): add qwentile2.5-32b-instruct (#4541) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index 89a4118f..1a194c9d 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -2387,6 +2387,31 @@ - filename: miscii-14b-1225.Q4_K_M.gguf sha256: f21fe73450be394055aeb87b7619e98a09e5c190b48f145bdebef4e12df871fe uri: huggingface://mradermacher/miscii-14b-1225-GGUF/miscii-14b-1225.Q4_K_M.gguf +- !!merge <<: *qwen25 + name: "qwentile2.5-32b-instruct" + icon: https://cdn-uploads.huggingface.co/production/uploads/65b19c1b098c85365af5a83e/sF7RDZA7lFYOmGy4bGy1s.png + urls: + - https://huggingface.co/maldv/Qwentile2.5-32B-Instruct + - https://huggingface.co/bartowski/Qwentile2.5-32B-Instruct-GGUF + description: | + Qwentile 2.5 32B Instruct is a normalized denoised fourier interpolation of the following models: + - { "model": "AiCloser/Qwen2.5-32B-AGI", "base": "Qwen/Qwen2.5-32B", "alpha": 0.3 } + - { "model": "EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2", "base": "Qwen/Qwen2.5-32B", "alpha": 0.7 } + - { "model": "fblgit/TheBeagle-v2beta-32B-MGS", "base": "Qwen/Qwen2.5-32B", "alpha": 0.6 } + - { "model": "huihui-ai/Qwen2.5-32B-Instruct-abliterated", "base": "Qwen/Qwen2.5-32B-Instruct", "alpha": 1.0 } + - { "model": "huihui-ai/QwQ-32B-Preview-abliterated", "base": "Qwen/Qwen2.5-32B", "alpha": 1.0 } + - { "model": "Qwen/QwQ-32B-Preview", "base": "Qwen/Qwen2.5-32B", "alpha": 0.8, "is_input": true } + - { "model": "rombodawg/Rombos-LLM-V2.5-Qwen-32b", "base": "Qwen/Qwen2.5-32B", "alpha": 1.0, "is_output": true } + - { "model": "nbeerbower/Qwen2.5-Gutenberg-Doppel-32B", "base": "Qwen/Qwen2.5-32B-Instruct", "alpha": 0.4 } + I started my experiment because of QwQ is a really nifty model, but it was giving me problems with xml output - which is what I use for my thought tokens. So, I thought... lets just merge it in! + The first model worked pretty well, but I got a sense that the balances could be tweaked. Why not throw in some other models as well for fun and see if I can't run out of disk space in the process? + overrides: + parameters: + model: Qwentile2.5-32B-Instruct-Q4_K_M.gguf + files: + - filename: Qwentile2.5-32B-Instruct-Q4_K_M.gguf + sha256: e476d6e3c15c78fc3f986d7ae8fa35c16116843827f2e6243c05767cef2f3615 + uri: huggingface://bartowski/Qwentile2.5-32B-Instruct-GGUF/Qwentile2.5-32B-Instruct-Q4_K_M.gguf - &archfunct license: apache-2.0 tags: