Text Generation
Transformers
Safetensors
qwen3_moe
creative
creative writing
fiction writing
plot generation
sub-plot generation
story generation
scene continue
storytelling
fiction story
science fiction
romance
all genres
story
writing
vivid prose
vivid writing
Mixture of Experts
mixture of experts
128 experts
8 active experts
fiction
roleplaying
bfloat16
rp
qwen3
horror
finetune
thinking
reasoning
uncensored
abliterated
Not-For-All-Audiences
conversational
Update README.md
Browse files
README.md
CHANGED
@@ -52,7 +52,7 @@ pipeline_tag: text-generation
|
|
52 |
|
53 |
<h2>Qwen3-42B-A3B-Stranger-Thoughts-Deep20x-Abliterated-Uncensored</h2>
|
54 |
|
55 |
-
<img src="
|
56 |
|
57 |
This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats.
|
58 |
The source code can also be used directly.
|
@@ -63,6 +63,10 @@ Qwen's excellent "Qwen3-30B-A3B", abliterated by "huihui-ai" then combined Brain
|
|
63 |
|
64 |
This pushes Qwen's abliterated/uncensored model to the absolute limit for creative use cases.
|
65 |
|
|
|
|
|
|
|
|
|
66 |
Model retains full reasoning, and output generation of a Qwen3 MOE ; but has not been tested for "non-creative" use cases.
|
67 |
|
68 |
Model is set with Qwen's default config:
|
|
|
52 |
|
53 |
<h2>Qwen3-42B-A3B-Stranger-Thoughts-Deep20x-Abliterated-Uncensored</h2>
|
54 |
|
55 |
+
<img src="qwen-42b-ablit.jpg" style="float:right; width:300px; height:300px; padding:10px;">
|
56 |
|
57 |
This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats.
|
58 |
The source code can also be used directly.
|
|
|
63 |
|
64 |
This pushes Qwen's abliterated/uncensored model to the absolute limit for creative use cases.
|
65 |
|
66 |
+
This model will generate horror, fiction, erotica, - you name it - is vivid, stark detail.
|
67 |
+
|
68 |
+
See examples below.
|
69 |
+
|
70 |
Model retains full reasoning, and output generation of a Qwen3 MOE ; but has not been tested for "non-creative" use cases.
|
71 |
|
72 |
Model is set with Qwen's default config:
|