models(gallery): add l3.1-moe-2x8b-v0.2 (#3969)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-10-26 09:02:27 +02:00 committed by GitHub
parent 3ad920b50a
commit 9f43f37150
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -1778,6 +1778,24 @@
- filename: Baldur-8B.Q4_K_M.gguf
sha256: 645b393fbac5cd17ccfd66840a3a05c3930e01b903dd1535f0347a74cc443fc7
uri: huggingface://QuantFactory/Baldur-8B-GGUF/Baldur-8B.Q4_K_M.gguf
- !!merge <<: *llama31
name: "l3.1-moe-2x8b-v0.2"
icon: https://github.com/moeru-ai/L3.1-Moe/blob/main/cover/v0.2.png?raw=true
urls:
- https://huggingface.co/moeru-ai/L3.1-Moe-2x8B-v0.2
- https://huggingface.co/mradermacher/L3.1-Moe-2x8B-v0.2-GGUF
description: |
This model is a Mixture of Experts (MoE) made with mergekit-moe. It uses the following base models:
Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base
ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.2
Heavily inspired by mlabonne/Beyonder-4x7B-v3.
overrides:
parameters:
model: L3.1-Moe-2x8B-v0.2.Q4_K_M.gguf
files:
- filename: L3.1-Moe-2x8B-v0.2.Q4_K_M.gguf
sha256: 87f8b294aa213aa3f866e03a53923f4df8f797ea94dc93f88b8a1b58d85fbca0
uri: huggingface://mradermacher/L3.1-Moe-2x8B-v0.2-GGUF/L3.1-Moe-2x8B-v0.2.Q4_K_M.gguf
- &deepseek
## Deepseek
url: "github:mudler/LocalAI/gallery/deepseek.yaml@master"