mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-12-30 01:50:23 -05:00
Code Issues Packages Projects Releases Wiki Activity

chore(model gallery): add huihui-jan-nano-abliterated (#5806)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto
2025-07-07 11:35:39 +02:00
committed by GitHub
parent cea1703acc
commit ceda2e69db
1 changed files with 16 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
gallery/index.yaml
View File

@@ -1665,6 +1665,22 @@
- filename: Qwen-GUI-3B.i1-Q4_K_M.gguf
sha256: 39b6d842a3f5166bf01b1f50bbeb13cc2cc1ee59c3c8c09702a73c6e13b7023c
uri: huggingface://mradermacher/Qwen-GUI-3B-i1-GGUF/Qwen-GUI-3B.i1-Q4_K_M.gguf
- !!merge <<: *qwen3
name: "huihui-jan-nano-abliterated"
urls:
- https://huggingface.co/huihui-ai/Huihui-Jan-nano-abliterated
- https://huggingface.co/mradermacher/Huihui-Jan-nano-abliterated-GGUF
description: |
This is an uncensored version of Menlo/Jan-nano created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.
Ablation was performed using a new and faster method, which yields better results.
overrides:
parameters:
model: Huihui-Jan-nano-abliterated.Q4_K_M.gguf
files:
- filename: Huihui-Jan-nano-abliterated.Q4_K_M.gguf
sha256: 4390733f3f97ec36a24abe0b4e1b07980a4470e9ec4bf0f7d027c90be38670fa
uri: huggingface://mradermacher/Huihui-Jan-nano-abliterated-GGUF/Huihui-Jan-nano-abliterated.Q4_K_M.gguf
- &gemma3
url: "github:mudler/LocalAI/gallery/gemma.yaml@master"
name: "gemma-3-27b-it"