this is designed for Dark mode

L3.3-Shakudo-70b

Shakudo Mascot
โšก Top Sponsors โ–ผ

๐Ÿ† Top Supporters

If I forgot you please let me know, ko-fi doesent let me track it easily


๐Ÿค Valued Partners

Model Information

L3.3-Shakudo-70b

Llama 3.3 Multi-Stage Merge 70b Parameters V0.8

Model Composition

Model Creation Process

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.

-

Recommended Sampler Settings

Static Temperature: 1.0 - 1.2
Min P: 0.02 - 0.025
DRY:
- Multiplier: 0.8
- Base: 1.74
- Length: 4-6

Good Starting Templates & Prompts

Hamon v1 โ†’ by @Steel > Big-picture storytelling guide with world-building focus, set dialogue/narration split, and general writing rules.
Shingane v1 โ†’ by @Steel > Simplified sysprompt based on Hamon.
Kesshin v1 โ†’ by @Steel > A Hamon rethink using a Character-focused sys prompt that tracks what characters know and how they learn things, with strict interaction rules.
Kamae TTRPG v1 โ†’ by @Steel > TTRPG Game Master framework emphasizing player agency, world consistency, and adaptive session management with mechanical integration.
Kamae lite v1 โ†’ by @Steel > Simplified sysprompt based on Kamae.

Support & Community:

Downloads last month
237
Safetensors
Model size
70.6B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for Steelskull/L3.3-Shakudo-70b

Finetuned
(181)
this model
Finetunes
1 model
Quantizations
4 models

Collection including Steelskull/L3.3-Shakudo-70b