From 34d9deaf39cbf7f2c2fa052bc86d002ddb7bfb69 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Sat, 12 Jul 2025 19:37:10 +0200 Subject: [PATCH] chore(model gallery): add impish_magic_24b-i1 (#5839) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index 76ee70598..c336b12aa 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -13835,6 +13835,32 @@ - filename: Mistral-2x24B-MOE-Pwr-Magis-Devstl-Reason-Ult-44B-NEO-D_AU-Q4_K_M.gguf sha256: cafa5f41187c4799c6f37cc8d5ab95f87456488443261f19266bb587b94c960c uri: huggingface://DavidAU/Mistral-2x24B-MOE-Power-CODER-Magistral-Devstral-Reasoning-Ultimate-NEO-MAX-44B-gguf/Mistral-2x24B-MOE-Pwr-Magis-Devstl-Reason-Ult-44B-NEO-D_AU-Q4_K_M.gguf +- !!merge <<: *mistral03 + name: "impish_magic_24b-i1" + icon: https://huggingface.co/SicariusSicariiStuff/Impish_Magic_24B/resolve/main/Images/Impish_Magic_24B.png + urls: + - https://huggingface.co/SicariusSicariiStuff/Impish_Magic_24B + - https://huggingface.co/mradermacher/Impish_Magic_24B-i1-GGUF + description: | + It's the 20th of June, 2025—The world is getting more and more chaotic, but let's look at the bright side: Mistral released a new model at a very good size of 24B, no more "sign here" or "accept this weird EULA" there, a proper Apache 2.0 License, nice! 👍🏻 + + This model is based on mistralai/Magistral-Small-2506 so naturally I named it Impish_Magic. Truly excellent size, I tested it on my laptop (16GB gpu) and it works quite fast (4090m). + + This model went "full" fine-tune over 100m unique tokens. Why do I say "full"? + + I've tuned specific areas in the model to attempt to change the vocabulary usage, while keeping as much intelligence as possible. So this is definitely not a LoRA, but also not exactly a proper full finetune, but rather something in-between. + + As I mentioned in a small update, I've made nice progress regarding interesting sources of data, some of them are included in this tune. 100m tokens is a lot for a Roleplay / Adventure tune, and yes, it can do adventure as well—there is unique adventure data here, that was never used so far. + + A lot of the data still needs to be cleaned and processed. I've included it before I did any major data processing, because with the magic of 24B parameters, even "dirty" data would work well, especially when using a more "balanced" approach for tuning that does not include burning the hell of the model in a full finetune across all of its layers. Could this data be cleaner? Of course, and it will. But for now, I would hate to make perfect the enemy of the good. + Fun fact: Impish_Magic_24B is the first roleplay finetune of magistral! + overrides: + parameters: + model: Impish_Magic_24B.i1-Q4_K_M.gguf + files: + - filename: Impish_Magic_24B.i1-Q4_K_M.gguf + sha256: 38f73fb17b67837ab8b3664a6c8b54133539f58ae7a7a02e816f6a358b688562 + uri: huggingface://mradermacher/Impish_Magic_24B-i1-GGUF/Impish_Magic_24B.i1-Q4_K_M.gguf - &mudler url: "github:mudler/LocalAI/gallery/mudler.yaml@master" ### START mudler's LocalAI specific-models name: "LocalAI-llama3-8b-function-call-v0.2"