ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-03-13 07:54:34 +00:00
Code Issues Actions 15 Packages Projects Releases Wiki Activity

chore(model gallery): add llama-3.1-8b-instruct-uncensored-delmat-i1 (#4944)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-03-05 09:31:09 +01:00 committed by GitHub
parent 6b46c52789
commit 02aafeff75
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 18 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
gallery/index.yaml
View File

@ -6409,6 +6409,24 @@
- filename: Locutusque_Thespis-Llama-3.1-8B-Q4_K_M.gguf
sha256: 94138f3774f496e28c2e76bb6df7a073c6087f8c074216a24b3cbcdc58ec7853
uri: huggingface://bartowski/Locutusque_Thespis-Llama-3.1-8B-GGUF/Locutusque_Thespis-Llama-3.1-8B-Q4_K_M.gguf
- !!merge <<: *llama31
name: "llama-3.1-8b-instruct-uncensored-delmat-i1"
urls:
- https://huggingface.co/nkpz/Llama-3.1-8B-Instruct-Uncensored-DeLMAT
- https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Uncensored-DeLMAT-i1-GGUF
description: |
Decensored using a custom training script guided by activations, similar to ablation/"abliteration" scripts but not exactly the same approach.
I've found this effect to be stronger than most abliteration scripts, so please use responsibly etc etc.
The training script is released under the MIT license: https://github.com/nkpz/DeLMAT
overrides:
parameters:
model: Llama-3.1-8B-Instruct-Uncensored-DeLMAT.i1-Q4_K_M.gguf
files:
- filename: Llama-3.1-8B-Instruct-Uncensored-DeLMAT.i1-Q4_K_M.gguf
sha256: e05c69f6f3157aeb7c579d1bb8c3b7e0fb6631d262d76ba301b6693e068148b2
uri: huggingface://mradermacher/Llama-3.1-8B-Instruct-Uncensored-DeLMAT-i1-GGUF/Llama-3.1-8B-Instruct-Uncensored-DeLMAT.i1-Q4_K_M.gguf
- &deepseek
url: "github:mudler/LocalAI/gallery/deepseek.yaml@master" ## Deepseek
name: "deepseek-coder-v2-lite-instruct"