dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-20 10:35:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 21

chore(model gallery): qwen2.5-14b-instruct-1m-unalign-i1 (#5082)

Browse source
This commit is contained in:
Ettore Di Giacinto 2025-03-28 15:08:33 +01:00 • committed by GitHub
parent c7e99c7b59
commit ddeb9ed93e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 18 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

18
gallery/index.yaml
View file

@ -5201,6 +5201,24 @@
- filename: HelpingAI_Helpingai3-raw-Q4_K_M.gguf
sha256: de7a223ad397ba27c889dad08466de471166f1e76962b855c72cf6b779a7b857
uri: huggingface://bartowski/HelpingAI_Helpingai3-raw-GGUF/HelpingAI_Helpingai3-raw-Q4_K_M.gguf
- !!merge <<: *qwen25
name: "qwen2.5-14b-instruct-1m-unalign-i1"
urls:
- https://huggingface.co/ToastyPigeon/Qwen2.5-14B-Instruct-1M-Unalign
- https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-1M-Unalign-i1-GGUF
description: |
A simple unalignment fine-tune on ~900k tokens aiming to make the model more compliant and willing to handle user requests.
This is the same unalignment training seen in concedo/Beepo-22B, so big thanks to concedo for the dataset.
Chat template is same as the original, ChatML.
overrides:
parameters:
model: Qwen2.5-14B-Instruct-1M-Unalign.i1-Q4_K_M.gguf
files:
- filename: Qwen2.5-14B-Instruct-1M-Unalign.i1-Q4_K_M.gguf
sha256: 11b2eb96a8a4d512fceb3344dccc694972801c964cf748d723fdf436bc368915
uri: huggingface://mradermacher/Qwen2.5-14B-Instruct-1M-Unalign-i1-GGUF/Qwen2.5-14B-Instruct-1M-Unalign.i1-Q4_K_M.gguf
- &llama31
url: "github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master" ## LLama3.1
icon: https://avatars.githubusercontent.com/u/153379578