Darkhn/L3.3-Damascus-R1-5.0bpw-h8-exl2

L3.3-Damascus-R1

Created by SteelSkull →

Model Information

L3.3-Damascus-R1

L3.3 = Llama 3.3 SCE Merge 70b Parameters

Model Composition

• L3.1x3.3-Hydroblated-R1-70B-v3 Base model [Unreleased]
• EVA-LLaMA-3.33 Core capabilities
• Euryale-v2.3 Enhanced reasoning
• Cirrus-x1 Improved coherence
• Hanami-x1 Balanced responses
• Anubis-v1 Enhanced detail
• Negative_LLAMA Reduced bias

Damascus-R1 represents a complete architectural overhaul of the Nevoria foundation, built using the SCE (Selective Component Enhancement) merge method. The model is constructed on a custom Hydroblated-R1 base that prioritizes stability, intelligence, and enhanced awareness.

Technical Architecture

The model integrates specialized components from multiple high-performance models:

• EVA and EURYALE foundations for creative expression and scene comprehension
• Cirrus and Hanami elements for enhanced reasoning capabilities
• Anubis components for detailed scene description
• Negative_LLAMA integration for balanced perspective and response

Core Philosophy

Damascus-R1 embodies the principle that AI models can be intelligent and be fun. This version specifically addresses user feedback from previous iterations, optimizing the balance between technical capability and natural conversation flow.

Base Architecture

The model utilizes a custom base model called Hydroblated-R1 base, chosen specifically for its stability characteristics and enhanced reasoning capabilities. The SCE merge method enables precise component integration while maintaining model coherence and performance reliability.

Recommended Sampler Settings: By @Geechan

Dynamic Temperature

Min 1.0

Max 1.3-1.35

Exponent 1.0

Static Temperature:

1.2

Min P

0.02

DRY Settings

Multiplier 0.8

Base 1.75

Length 4

Recommended Templates & Prompts

LLam@ception → by @.konnect

Support & Community:

Support on Ko-fi Join Discord

Special Thanks

• @Geechan for feedback and sampler settings
• @Konnect for their feedback and templates
• @Kistara for their feedback and help with the model mascot design
• @Thana Alt for their feedback and Quants
• @Lightning_missile for their feedback
• @Yemosvoto for the model name
• The Arli community for feedback and testers
• The BeaverAI communty for feedback and testers

I wish I could add everyone but im pretty sure it would be as long as the card!