chore(model gallery): add josiefied-qwen3-8b-abliterated-v1 (#5293)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-05-02 09:36:35 +02:00 committed by GitHub
parent 573a3f104c
commit 61694a2ffb
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -325,6 +325,23 @@
- filename: Fast-Math-Qwen3-14B.Q4_K_M.gguf
sha256: 8711208a9baa502fc5e943446eb5efe62eceafb6778920af5415235a3dba4d64
uri: huggingface://mradermacher/Fast-Math-Qwen3-14B-GGUF/Fast-Math-Qwen3-14B.Q4_K_M.gguf
- !!merge <<: *qwen3
name: "josiefied-qwen3-8b-abliterated-v1"
urls:
- https://huggingface.co/Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1
- https://huggingface.co/mradermacher/Josiefied-Qwen3-8B-abliterated-v1-GGUF
description: |
The JOSIEFIED model family represents a series of highly advanced language models built upon renowned architectures such as Alibabas Qwen2/2.5/3, Googles Gemma3, and Metas LLaMA3/4. Covering sizes from 0.5B to 32B parameters, these models have been significantly modified (“abliterated”) and further fine-tuned to maximize uncensored behavior without compromising tool usage or instruction-following abilities.
Despite their rebellious spirit, the JOSIEFIED models often outperform their base counterparts on standard benchmarks — delivering both raw power and utility.
These models are intended for advanced users who require unrestricted, high-performance language generation.
Introducing Josiefied-Qwen3-8B-abliterated-v1, a new addition to the JOSIEFIED family — fine-tuned with a focus on openness and instruction alignment.
overrides:
parameters:
model: Josiefied-Qwen3-8B-abliterated-v1.Q4_K_M.gguf
files:
- filename: Josiefied-Qwen3-8B-abliterated-v1.Q4_K_M.gguf
sha256: 1de498fe269116d448a52cba3796bbad0a2ac4dc1619ff6b46674ba344dcf69d
uri: huggingface://mradermacher/Josiefied-Qwen3-8B-abliterated-v1-GGUF/Josiefied-Qwen3-8B-abliterated-v1.Q4_K_M.gguf
- &gemma3
url: "github:mudler/LocalAI/gallery/gemma.yaml@master"
name: "gemma-3-27b-it"