models(gallery): add mn-backyardai-party-12b-v1-iq-arm-imatrix (#3740)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-10-07 09:46:44 +02:00 committed by GitHub
parent 55af0b1c68
commit 03bbbea039
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -1734,6 +1734,26 @@
- filename: MagnusIntellectus-12B-v1.i1-Q4_K_M.gguf
sha256: c97107983b4edc5b6f2a592d227ca2dd4196e2af3d3bc0fe6b7a8954a1fb5870
uri: huggingface://mradermacher/MagnusIntellectus-12B-v1-i1-GGUF/MagnusIntellectus-12B-v1.i1-Q4_K_M.gguf
- !!merge <<: *mistral03
url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
name: "mn-backyardai-party-12b-v1-iq-arm-imatrix"
icon: https://huggingface.co/Sao10K/MN-BackyardAI-Party-12B-v1/resolve/main/party1.png
urls:
- https://huggingface.co/Sao10K/MN-BackyardAI-Party-12B-v1
- https://huggingface.co/Lewdiculous/MN-BackyardAI-Party-12B-v1-GGUF-IQ-ARM-Imatrix
description: |
This is a group-chat based roleplaying model, based off of 12B-Lyra-v4a2, a variant of Lyra-v4 that is currently private.
It is trained on an entirely human-based dataset, based on forum / internet group roleplaying styles. The only augmentation done with LLMs is to the character sheets, to fit to the system prompt, to fit various character sheets within context.
This model is still capable of 1 on 1 roleplay, though I recommend using ChatML when doing that instead.
overrides:
parameters:
model: MN-BackyardAI-Party-12B-v1-Q4_K_M-imat.gguf
files:
- filename: MN-BackyardAI-Party-12B-v1-Q4_K_M-imat.gguf
sha256: cea68768dff58b553974b755bb40ef790ab8b86866d9b5c46bc2e6c3311b876a
uri: huggingface://Lewdiculous/MN-BackyardAI-Party-12B-v1-GGUF-IQ-ARM-Imatrix/MN-BackyardAI-Party-12B-v1-Q4_K_M-imat.gguf
- &mudler
### START mudler's LocalAI specific-models
url: "github:mudler/LocalAI/gallery/mudler.yaml@master"