ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-02-11 21:25:19 +00:00
Code Issues Actions 15 Packages Projects Releases Wiki Activity

chore(model gallery): add steelskull_l3.3-damascus-r1 (#4737)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-02-03 10:30:07 +01:00 committed by GitHub
parent 52fadeded1
commit ed0094c3d0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 29 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
gallery/index.yaml
View File

@ -5623,6 +5623,35 @@
- filename: FuseO1-DeekSeekR1-QwQ-SkyT1-32B-Preview-Q4_K_M.gguf
sha256: 13911dd4a62d4714a3447bc288ea9d49dbe575a91cab9e8f645057f1d8e1100e
uri: huggingface://bartowski/FuseO1-DeekSeekR1-QwQ-SkyT1-32B-Preview-GGUF/FuseO1-DeekSeekR1-QwQ-SkyT1-32B-Preview-Q4_K_M.gguf
- !!merge <<: *deepseek-r1
name: "steelskull_l3.3-damascus-r1"
icon: https://cdn-uploads.huggingface.co/production/uploads/64545af5ec40bbbd01242ca6/iIzpqHDb9wU181AzfrjZy.png
urls:
- https://huggingface.co/Steelskull/L3.3-Damascus-R1
- https://huggingface.co/bartowski/Steelskull_L3.3-Damascus-R1-GGUF
description: |
Damascus-R1 builds upon some elements of the Nevoria foundation but represents a significant step forward with a completely custom-made DeepSeek R1 Distill base: Hydroblated-R1-V3. Constructed using the new SCE (Select, Calculate, and Erase) merge method, Damascus-R1 prioritizes stability, intelligence, and enhanced awareness.
Technical Architecture
Leveraging the SCE merge method and custom base, Damascus-R1 integrates newly added 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 recent community feedback and iterates on prior experiments, optimizing the balance between technical capability and natural conversation flow.
Base Architecture
At its core, Damascus-R1 utilizes the entirely custom Hydroblated-R1 base model, specifically engineered for stability, enhanced reasoning, and performance. The SCE merge method, with settings finely tuned based on community feedback from evaluations of Experiment-Model-Ver-A, L3.3-Exp-Nevoria-R1-70b-v0.1 and L3.3-Exp-Nevoria-70b-v0.1, enables precise and effective component integration while maintaining model coherence and reliability.
overrides:
parameters:
model: Steelskull_L3.3-Damascus-R1-Q4_K_M.gguf
files:
- filename: Steelskull_L3.3-Damascus-R1-Q4_K_M.gguf
sha256: f1df5808b2099b26631d0bae870603a08dbfab6813471f514035d3fb92a47480
uri: huggingface://bartowski/Steelskull_L3.3-Damascus-R1-GGUF/Steelskull_L3.3-Damascus-R1-Q4_K_M.gguf
- &qwen2
url: "github:mudler/LocalAI/gallery/chatml.yaml@master" ## Start QWEN2
name: "qwen2-7b-instruct"