models(gallery): add aura-llama-Abliterated ()

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-05-13 18:44:10 +02:00 committed by GitHub
parent e2c3ffb09b
commit 4d70b6fb2d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -370,6 +370,27 @@
- filename: L3-Solana-8B-v1.q5_K_M.gguf
sha256: 9b8cd2c3beaab5e4f82efd10e7d44f099ad40a4e0ee286ca9fce02c8eec26d2f
uri: huggingface://Sao10K/L3-Solana-8B-v1-GGUF/L3-Solana-8B-v1.q5_K_M.gguf
- !!merge <<: *llama3
name: "aura-llama-abliterated"
icon: https://cdn-uploads.huggingface.co/production/uploads/64545af5ec40bbbd01242ca6/AwLNDVB-GIY7k0wnVV_TX.png
license: apache-2.0
urls:
- https://huggingface.co/TheSkullery/Aura-Llama-Abliterated
- https://huggingface.co/mudler/Aura-Llama-Abliterated-Q4_K_M-GGUF
description: |
Aura-llama is using the methodology presented by SOLAR for scaling LLMs called depth up-scaling (DUS), which encompasses architectural modifications with continued pretraining. Using the solar paper as a base, I integrated Llama-3 weights into the upscaled layers, and In the future plan to continue training the model.
Aura-llama is a merge of the following models to create a base model to work from:
meta-llama/Meta-Llama-3-8B-Instruct
meta-llama/Meta-Llama-3-8B-Instruct
overrides:
parameters:
model: aura-llama-abliterated.Q4_K_M.gguf
files:
- filename: aura-llama-abliterated.Q4_K_M.gguf
sha256: ad4a16b90f1ffb5b49185b3fd00ed7adb1cda69c4fad0a1d987bd344ce601dcd
uri: huggingface://mudler/Aura-Llama-Abliterated-Q4_K_M-GGUF/aura-llama-abliterated.Q4_K_M.gguf
- !!merge <<: *llama3
name: "average_normie_l3_v1_8b-gguf-iq-imatrix"
urls: