chore(model gallery): add huihui-ai_qwq-32b-abliterated (#4961)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-03-08 11:34:37 +01:00 committed by GitHub
parent c6ebead8e5
commit 3def1ae232
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -4455,6 +4455,21 @@
- filename: Rombo-Org_Rombo-LLM-V3.1-QWQ-32b-Q4_K_M.gguf
sha256: ee0b5027c686f3c37938f33b62788e27211852268f9e5c32e00058f0cf1688c7
uri: huggingface://bartowski/Rombo-Org_Rombo-LLM-V3.1-QWQ-32b-GGUF/Rombo-Org_Rombo-LLM-V3.1-QWQ-32b-Q4_K_M.gguf
- !!merge <<: *qwen25
name: "huihui-ai_qwq-32b-abliterated"
urls:
- https://huggingface.co/huihui-ai/QwQ-32B-abliterated
- https://huggingface.co/bartowski/huihui-ai_QwQ-32B-abliterated-GGUF
description: |
This is an uncensored version of Qwen/QwQ-32B 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.
overrides:
parameters:
model: huihui-ai_QwQ-32B-abliterated-Q4_K_M.gguf
files:
- filename: huihui-ai_QwQ-32B-abliterated-Q4_K_M.gguf
sha256: 27d3c3e116015257985fa27b87e3f3aafbeb4762152d60474e883547d436025e
uri: huggingface://bartowski/huihui-ai_QwQ-32B-abliterated-GGUF/huihui-ai_QwQ-32B-abliterated-Q4_K_M.gguf
- &llama31
url: "github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master" ## LLama3.1
icon: https://avatars.githubusercontent.com/u/153379578