Mirror
/
LocalAI
mirror of https://github.com/mudler/LocalAI.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

models(gallery): add Llama-3-8B-Instruct-abliterated (#2288) 

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-05-11 10:10:57 +02:00 committed by GitHub
parent 93e581dfd0
commit 7f4febd6c2
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 13 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
gallery/index.yaml
View File

@ -95,6 +95,19 @@
- filename: Meta-Llama-3-8B-Instruct.Q6_K.gguf
sha256: b7bad45618e2a76cc1e89a0fbb93a2cac9bf410e27a619c8024ed6db53aa9b4a
uri: huggingface://QuantFactory/Meta-Llama-3-8B-Instruct-GGUF/Meta-Llama-3-8B-Instruct.Q6_K.gguf
- !!merge <<: *llama3
name: "llama-3-8b-instruct-abliterated"
urls:
- https://huggingface.co/failspy/Llama-3-8B-Instruct-abliterated-GGUF
description: |
This is meta-llama/Llama-3-8B-Instruct with orthogonalized bfloat16 safetensor weights, generated with the methodology that was described in the preview paper/blog post: 'Refusal in LLMs is mediated by a single direction' which I encourage you to read to understand more.
overrides:
parameters:
model: Llama-3-8B-Instruct-abliterated-q4_k.gguf
files:
- filename: Llama-3-8B-Instruct-abliterated-q4_k.gguf
sha256: a6365f813de1977ae22dbdd271deee59f91f89b384eefd3ac1a391f391d8078a
uri: huggingface://failspy/Llama-3-8B-Instruct-abliterated-GGUF/Llama-3-8B-Instruct-abliterated-q4_k.gguf
- !!merge <<: *llama3
name: "llama-3-8b-instruct-coder"
icon: https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/0O4cIuv3wNbY68-FP7tak.jpeg