ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-03-13 07:54:34 +00:00
Code Issues Actions 14 Packages Projects Releases Wiki Activity

chore(model gallery): add steelskull_l3.3-san-mai-r1-70b (#4893)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-02-24 09:41:06 +01:00 committed by GitHub
parent 049a13fe78
commit 06c836a937
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 25 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
gallery/index.yaml
View File

@ -6439,6 +6439,31 @@
- filename: arcee-ai_Arcee-Maestro-7B-Preview-Q4_K_M.gguf - filename: arcee-ai_Arcee-Maestro-7B-Preview-Q4_K_M.gguf
sha256: 7b1099e67ad1d10a80868ca0c39e78e7b3f89da87aa316166f56cc259e53cb7f sha256: 7b1099e67ad1d10a80868ca0c39e78e7b3f89da87aa316166f56cc259e53cb7f
uri: huggingface://bartowski/arcee-ai_Arcee-Maestro-7B-Preview-GGUF/arcee-ai_Arcee-Maestro-7B-Preview-Q4_K_M.gguf uri: huggingface://bartowski/arcee-ai_Arcee-Maestro-7B-Preview-GGUF/arcee-ai_Arcee-Maestro-7B-Preview-Q4_K_M.gguf
- !!merge <<: *deepseek-r1
name: "steelskull_l3.3-san-mai-r1-70b"
icon: https://cdn-uploads.huggingface.co/production/uploads/64545af5ec40bbbd01242ca6/8fZQZaLM0XO9TyKh-yMQ7.jpeg
urls:
- https://huggingface.co/Steelskull/L3.3-San-Mai-R1-70b
- https://huggingface.co/bartowski/Steelskull_L3.3-San-Mai-R1-70b-GGUF
description: |
L3.3-San-Mai-R1-70b represents the foundational release in a three-part model series, followed by L3.3-Cu-Mai-R1-70b (Version A) and L3.3-Mokume-Gane-R1-70b (Version C). The name "San-Mai" draws inspiration from the Japanese bladesmithing technique of creating three-layer laminated composite metals, known for combining a hard cutting edge with a tougher spine - a metaphor for this model's balanced approach to AI capabilities.
Built on a custom DeepSeek R1 Distill base (DS-Hydroblated-R1-v4.1), San-Mai-R1 integrates specialized components through the SCE merge method:
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 Capabilities
As the OG model in the series, San-Mai-R1 serves as the gold standard and reliable baseline. User feedback consistently highlights its superior intelligence, coherence, and unique ability to provide deep character insights. Through proper prompting, the model demonstrates advanced reasoning capabilities and an "X-factor" that enables unprompted exploration of character inner thoughts and motivations.
overrides:
parameters:
model: Steelskull_L3.3-San-Mai-R1-70b-Q4_K_M.gguf
files:
- filename: Steelskull_L3.3-San-Mai-R1-70b-Q4_K_M.gguf
sha256: 2287bfa14af188b0fc3a9f4e3afc9c303b7c41cee49238434f971c090b850306
uri: huggingface://bartowski/Steelskull_L3.3-San-Mai-R1-70b-GGUF/Steelskull_L3.3-San-Mai-R1-70b-Q4_K_M.gguf
- &qwen2 - &qwen2
url: "github:mudler/LocalAI/gallery/chatml.yaml@master" ## Start QWEN2 url: "github:mudler/LocalAI/gallery/chatml.yaml@master" ## Start QWEN2
name: "qwen2-7b-instruct" name: "qwen2-7b-instruct"