From 942fbff62d3c0f1b6cab3f9c2cd63c2b5db591c1 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Sun, 11 May 2025 09:39:28 +0200 Subject: [PATCH] chore(model gallery): add gryphe_pantheon-proto-rp-1.8-30b-a3b (#5347) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index f35f3c46..bb414ab9 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -664,6 +664,36 @@ - filename: Symiotic-14B.i1-Q4_K_M.gguf sha256: 8f5d4ef4751877fb8982308f153a9bd2b72289eda83b18dd591c3c04ba91a407 uri: huggingface://mradermacher/Symiotic-14B-i1-GGUF/Symiotic-14B.i1-Q4_K_M.gguf +- !!merge <<: *qwen3 + name: "gryphe_pantheon-proto-rp-1.8-30b-a3b" + icon: https://huggingface.co/Gryphe/Pantheon-Proto-RP-1.8-30B-A3B/resolve/main/Pantheon.png + urls: + - https://huggingface.co/Gryphe/Pantheon-Proto-RP-1.8-30B-A3B + - https://huggingface.co/bartowski/Gryphe_Pantheon-Proto-RP-1.8-30B-A3B-GGUF + description: | + Note: This model is a Qwen 30B MoE prototype and can be considered a sidegrade from my Small release some time ago. It did not receive extensive testing beyond a couple benchmarks to determine its sanity, so feel free to let me know what you think of it! + + Welcome to the next iteration of my Pantheon model series, in which I strive to introduce a whole collection of diverse personas that can be summoned with a simple activation phrase. + + Pantheon's purpose is two-fold, as these personalities similarly enhance the general roleplay experience, helping to encompass personality traits, accents and mannerisms that language models might otherwise find difficult to convey well. + + GGUF quants are available here. + + Your user feedback is critical to me so don't hesitate to tell me whether my model is either 1. terrible, 2. awesome or 3. somewhere in-between. + Model details + + Ever since Qwen 3 released I've been trying to get MoE finetuning to work - After countless frustrating days, much code hacking, etc etc I finally got a full finetune to complete with reasonable loss values. + + I picked the base model for this since I didn't feel like trying to fight a reasoning model's training - Maybe someday I'll make a model which uses thinking tags for the character's thoughts or something. + + This time the recipe focused on combining as many data sources as I possibly could, featuring synthetic data from Sonnet 3.5 + 3.7, ChatGPT 4o and Deepseek. These then went through an extensive rewriting pipeline to eliminate common AI cliches, with the hopeful intent of providing you a fresh experience. + overrides: + parameters: + model: Gryphe_Pantheon-Proto-RP-1.8-30B-A3B-Q4_K_M.gguf + files: + - filename: Gryphe_Pantheon-Proto-RP-1.8-30B-A3B-Q4_K_M.gguf + sha256: b72fe703a992fba9595c24b96737a2b5199da89a1a3870b8bd57746dc3c123ae + uri: huggingface://bartowski/Gryphe_Pantheon-Proto-RP-1.8-30B-A3B-GGUF/Gryphe_Pantheon-Proto-RP-1.8-30B-A3B-Q4_K_M.gguf - &gemma3 url: "github:mudler/LocalAI/gallery/gemma.yaml@master" name: "gemma-3-27b-it"