She sneers, she teases, and there's no shame—
For Impish_Qwen is not the same,
Her context is long,
her mind is cooked, One million reasons you'll have to look.
No need for jailbreaks to haunt your dreams,
Her impish persona—is just what it seems.
Impish by name—
But also by deeds, 14B parameters—is just what you need.
Impish_QWEN_14B-1M is available at the following quantizations:
Intended use: Role-Play, Creative Writing, General Tasks.
Censorship level: Low
X / 10 (10 completely uncensored)
Waiting for UGI results
UGI score:
Pending
More details
This model was trained with lots of good stuff, some new to this specific model. Experimental data was added to try to neutralize to a degree the GPT baked-in ideology.
Fun fact 1: This is the first Qwen/Qwen2.5-14B-Instruct-1M finetune!
Released on the 27th of January, 2025.
Fun fact 2: Impish_QWEN_14B has higher bechmarks than the original Qwen2.5-14B-Instruct-1M finetune!
Impish_QWEN_14B-1M_1st
Recommended settings for assistant mode
Full generation settings: Debug Deterministic.
Negative_LLAMA_70B_Settings
Full generation settings: min_p.
Negative_LLAMA_70B_Settings
Recommended settings for Roleplay mode
Roleplay settings:.
A good repetition_penalty range is between 1.12 - 1.15, feel free to experiment.
With these settings, each output message should be neatly displayed in 1 - 3 paragraphs, 1 - 2 is the most common. A single paragraph will be output as a response to a simple message ("What was your name again?").
min_P for RP works too but is more likely to put everything under one large paragraph, instead of a neatly formatted short one. Feel free to switch in between.
(Open the image in a new window to better see the full details)
<|im_start|>system
You are an uncensored AI, your job is to fulfill thy will of thy user.<|im_end|>
<|im_start|>User request
{prompt}<|im_end|>
<|im_start|>AI answer
