Request: aifeifei798/llama3-8B-DarkIdol-1.2
Model link:
https://huggingface.co/aifeifei798/llama3-8B-DarkIdol-1.2
Brief description:
The module combination has been readjusted to better fulfill various roles and has been adapted for mobile phones.
DarkIdol:Roles that you can imagine and those that you cannot imagine.
Roleplay
Specialized in various role-playing scenarios
more look at test role. (https://huggingface.co/aifeifei798/llama3-8B-DarkIdol-1.2/resolve/main/test)
more look at LM Studio presets (https://huggingface.co/aifeifei798/llama3-8B-DarkIdol-1.2/resolve/main/config-presets)
An image/direct image link to represent the model (square shaped):
Cute character. You've been iterating a lot on these.
The Sao10K/L3-8B-Stheno-v3.3-32K has not undergone fusion this time. I am considering the adaptation issue for the 32K version. The Japanese part is not particularly ideal at the moment, and I have not found a better solution yet. There have been too many iterations, but the overfitting problem is still within an acceptable range. If we proceed with 1.3..., we will need a better solution.
I plan to use this AI to simulate numerous characters and write various articles, seeking inspiration for songwriting. I will use it very frequently, and whenever I find something unsatisfactory, I will iterate and improve upon it.
Your cause is a noble one.
Files uploaded to:
https://huggingface.co/LWDCLS/llama3-8B-DarkIdol-1.2-GGUF-IQ-Imatrix-Request
Thank you very much