mirror of
https://github.com/mudler/LocalAI.git
synced 2025-06-02 17:04:59 +00:00
chore(model gallery): add allura-org_q3-30b-a3b-designant (#5502)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
parent
5ffad3b004
commit
0f2f4c7e23
1 changed files with 17 additions and 0 deletions
|
@ -894,6 +894,23 @@
|
|||
- filename: allura-org_Q3-30b-A3b-Pentiment-Q4_K_M.gguf
|
||||
sha256: b03dd17c828ea71842e73e195395eb6c02408d5354f1aedf85caa403979aa89c
|
||||
uri: huggingface://bartowski/allura-org_Q3-30b-A3b-Pentiment-GGUF/allura-org_Q3-30b-A3b-Pentiment-Q4_K_M.gguf
|
||||
- !!merge <<: *qwen3
|
||||
name: "allura-org_q3-30b-a3b-designant"
|
||||
icon: https://cdn-uploads.huggingface.co/production/uploads/6685d39f64da708c0f553c5d/1yVqoNrokaI2JbrjcCk1W.png
|
||||
urls:
|
||||
- https://huggingface.co/allura-org/Q3-30B-A3B-Designant
|
||||
- https://huggingface.co/bartowski/allura-org_Q3-30B-A3B-Designant-GGUF
|
||||
description: |
|
||||
Intended as a direct upgrade to Pentiment, Q3-30B-A3B-Designant is a roleplaying model finetuned from Qwen3-30B-A3B-Base.
|
||||
|
||||
During testing, Designant punched well above its weight class in terms of active parameters, demonstrating the potential for well-made lightweight Mixture of Experts models in the roleplay scene. While one tester observed looping behavior, repetition in general was minimal.
|
||||
overrides:
|
||||
parameters:
|
||||
model: allura-org_Q3-30B-A3B-Designant-Q4_K_M.gguf
|
||||
files:
|
||||
- filename: allura-org_Q3-30B-A3B-Designant-Q4_K_M.gguf
|
||||
sha256: b0eb5b5c040b8ec378c572b4edc975b2782ef457dca42fb7a7e84a6a1647f1ae
|
||||
uri: huggingface://bartowski/allura-org_Q3-30B-A3B-Designant-GGUF/allura-org_Q3-30B-A3B-Designant-Q4_K_M.gguf
|
||||
- &gemma3
|
||||
url: "github:mudler/LocalAI/gallery/gemma.yaml@master"
|
||||
name: "gemma-3-27b-it"
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue