From ad6fdd21fdbaf7ff583313f4ce6ea5664d339a16 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Tue, 1 Jul 2025 16:15:22 +0200 Subject: [PATCH] chore(model gallery): add steelskull_l3.3-shakudo-70b (#5772) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index 394032cc7..bdb4167bc 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -3594,6 +3594,38 @@ - filename: sophosympatheia_StrawberryLemonade-L3-70B-v1.0-Q4_K_M.gguf sha256: 354472a2946598e0df376f9ecb91f83d7bc9c1b32db46bf48d3ea76f892f2a97 uri: huggingface://bartowski/sophosympatheia_StrawberryLemonade-L3-70B-v1.0-GGUF/sophosympatheia_StrawberryLemonade-L3-70B-v1.0-Q4_K_M.gguf +- !!merge <<: *llama33 + name: "steelskull_l3.3-shakudo-70b" + icon: https://cdn-uploads.huggingface.co/production/uploads/64545af5ec40bbbd01242ca6/Y3_fED_Re3U1rd0jOPnAR.jpeg + urls: + - https://huggingface.co/Steelskull/L3.3-Shakudo-70b + - https://huggingface.co/bartowski/Steelskull_L3.3-Shakudo-70b-GGUF + description: | + L3.3-Shakudo-70b is the result of a multi-stage merging process by Steelskull, designed to create a powerful and creative roleplaying model with a unique flavor. The creation process involved several advanced merging techniques, including weight twisting, to achieve its distinct characteristics. + Stage 1: The Cognitive Foundation & Weight Twisting + + The process began by creating a cognitive and tool-use focused base model, L3.3-Cogmoblated-70B. This was achieved through a `model_stock` merge of several models known for their reasoning and instruction-following capabilities. This base was built upon `nbeerbower/Llama-3.1-Nemotron-lorablated-70B`, a model intentionally "ablated" to skew refusal behaviors. This technique, known as weight twisting, helps the final model adopt more desirable response patterns by building upon a foundation that is already aligned against common refusal patterns. + Stage 2: The Twin Hydrargyrum - Flavor and Depth + + Two distinct models were then created from the Cogmoblated base: + + L3.3-M1-Hydrargyrum-70B: This model was merged using `SCE`, a technique that enhances creative writing and prose style, giving the model its unique "flavor." The Top_K for this merge were set at 0.22 . + L3.3-M2-Hydrargyrum-70B: This model was created using a `Della_Linear` merge, which focuses on integrating the "depth" of various roleplaying and narrative models. The settings for this merge were set at: (lambda: 1.1) (weight: 0.2) (density: 0.7) (epsilon: 0.2) + + Final Stage: Shakudo + + The final model, L3.3-Shakudo-70b, was created by merging the two Hydrargyrum variants using a 50/50 `nuslerp`. This final step combines the rich, creative prose (flavor) from the SCE merge with the strong roleplaying capabilities (depth) from the Della_Linear merge, resulting in a model with a distinct and refined narrative voice. + + A special thank you to Nectar.ai for their generous support of the open-source community and my projects. + + Additionally, a heartfelt thanks to all the Ko-fi supporters who have contributed—your generosity is deeply appreciated and helps keep this work going and the Pods spinning. + overrides: + parameters: + model: Steelskull_L3.3-Shakudo-70b-Q4_K_M.gguf + files: + - filename: Steelskull_L3.3-Shakudo-70b-Q4_K_M.gguf + sha256: 54590c02226f12c6f48a4af6bfed0e3c90130addd1fb8a2b4fcc1f0ab1674ef7 + uri: huggingface://bartowski/Steelskull_L3.3-Shakudo-70b-GGUF/Steelskull_L3.3-Shakudo-70b-Q4_K_M.gguf - &rwkv url: "github:mudler/LocalAI/gallery/rwkv.yaml@master" name: "rwkv-6-world-7b"