Skip to content

Commit c546774

Browse files
authored
chore(model gallery): add qwen3-33b-a3b-stranger-thoughts-abliterated-uncensored (#5755)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
1 parent 3fe3a7b commit c546774

File tree

1 file changed

+30
-0
lines changed

1 file changed

+30
-0
lines changed

gallery/index.yaml

Lines changed: 30 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1530,6 +1530,36 @@
15301530
- filename: Qwen3-22B-A3B-The-Harley-Quinn.Q4_K_M.gguf
15311531
sha256: a3666754efde5d6c054de53cff0f38f1bb4a20117e2502eed7018ae57017b0a2
15321532
uri: huggingface://mradermacher/Qwen3-22B-A3B-The-Harley-Quinn-GGUF/Qwen3-22B-A3B-The-Harley-Quinn.Q4_K_M.gguf
1533+
- !!merge <<: *qwen3
1534+
name: "qwen3-33b-a3b-stranger-thoughts-abliterated-uncensored"
1535+
icon: https://huggingface.co/DavidAU/Qwen3-33B-A3B-Stranger-Thoughts-Abliterated-Uncensored/resolve/main/qwen3-33b-ablit.jpg
1536+
urls:
1537+
- https://huggingface.co/DavidAU/Qwen3-33B-A3B-Stranger-Thoughts-Abliterated-Uncensored
1538+
- https://huggingface.co/mradermacher/Qwen3-33B-A3B-Stranger-Thoughts-Abliterated-Uncensored-GGUF
1539+
description: |
1540+
WARNING: NSFW. Vivid prose. INTENSE. Visceral Details. Violence. HORROR. GORE. Swearing. UNCENSORED... humor, romance, fun.
1541+
Qwen3-33B-A3B-Stranger-Thoughts-Abliterated-Uncensored
1542+
1543+
This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats. The source code can also be used directly.
1544+
1545+
ABOUT:
1546+
1547+
A stranger, yet radically different version of "Qwen/Qwen3-30B-A3B", abliterated by "huihui-ai" , with 4 added layers expanding the model to 33B total parameters.
1548+
1549+
The goal: slightly alter the model, to address some odd creative thinking and output choices AND de-censor it.
1550+
1551+
Please note that the modifications affect the entire model operation; roughly I adjusted the model to think a little "deeper" and "ponder" a bit - but this is a very rough description.
1552+
1553+
I also ran reasoning tests (non-creative) to ensure model was not damaged and roughly matched original model performance.
1554+
1555+
That being said, reasoning and output generation will be altered regardless of your use case(s)
1556+
overrides:
1557+
parameters:
1558+
model: Qwen3-33B-A3B-Stranger-Thoughts-Abliterated-Uncensored.Q4_K_M.gguf
1559+
files:
1560+
- filename: Qwen3-33B-A3B-Stranger-Thoughts-Abliterated-Uncensored.Q4_K_M.gguf
1561+
sha256: fc0f028ab04d4643032e5bf65c3b51ba947e97b4f562c4fc25c06b6a20b14616
1562+
uri: huggingface://mradermacher/Qwen3-33B-A3B-Stranger-Thoughts-Abliterated-Uncensored-GGUF/Qwen3-33B-A3B-Stranger-Thoughts-Abliterated-Uncensored.Q4_K_M.gguf
15331563
- &gemma3
15341564
url: "github:mudler/LocalAI/gallery/gemma.yaml@master"
15351565
name: "gemma-3-27b-it"

0 commit comments

Comments
 (0)