models(gallery): add lumimaidv2 (#2312)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-05-13 18:44:44 +02:00 committed by GitHub
parent fa7b2aee9c
commit 2db22087ae
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -572,6 +572,29 @@
- filename: Llama-3-Lumimaid-8B-v0.1-OAS-Q4_K_M-imat.gguf
sha256: 1199440aa13c55f5f2cad1cb215535306f21e52a81de23f80a9e3586c8ac1c50
uri: huggingface://Lewdiculous/Llama-3-Lumimaid-8B-v0.1-OAS-GGUF-IQ-Imatrix/Llama-3-Lumimaid-8B-v0.1-OAS-Q4_K_M-imat.gguf
- !!merge <<: *llama3
name: "llama-3-lumimaid-v2-8b-v0.1-oas-iq-imatrix"
urls:
- https://huggingface.co/Lewdiculous/Llama-3-Lumimaid-8B-v0.1-OAS-GGUF-IQ-Imatrix
icon: https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/JUxfdTot7v7LTdIGYyzYM.png
license: cc-by-nc-4.0
description: |
This model uses the Llama3 prompting format.
Llama3 trained on our RP datasets, we tried to have a balance between the ERP and the RP, not too horny, but just enough.
We also added some non-RP dataset, making the model less dumb overall. It should look like a 40%/60% ratio for Non-RP/RP+ERP data.
"This model received the Orthogonal Activation Steering treatment, meaning it will rarely refuse any request."
This is v2!
overrides:
parameters:
model: v2-Llama-3-Lumimaid-8B-v0.1-OAS-Q4_K_M-imat.gguf
files:
- filename: v2-Llama-3-Lumimaid-8B-v0.1-OAS-Q4_K_M-imat.gguf
sha256: b00b4cc2ea4e06db592e5f581171758387106626bcbf445c03a1cb7b424be881
uri: huggingface://Lewdiculous/Llama-3-Lumimaid-8B-v0.1-OAS-GGUF-IQ-Imatrix/v2-Llama-3-Lumimaid-8B-v0.1-OAS-Q4_K_M-imat.gguf
- !!merge <<: *llama3
name: "suzume-llama-3-8B-multilingual"
urls: