Downloads · 30 days
64
12% of all-time downloads
Naphula/Slimaki-24B-v1
Slimaki-24B-v1 is a text generation model from Naphula. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
<audio controls src="https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/FyBiCGYn-xghTyfIrxr9I.mpga"</audio
Downloads · 30 days
64
12% of all-time downloads
All-time downloads
524
Public
Parameters
23.6B
47.2 GB on disk
Likes
11
Public
Click a slice to open those files.
.safetensors47.1 GB · 100%
From the Hugging Face model README
<audio controls src="https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/FyBiCGYn-xghTyfIrxr9I.mpga"></audio>
[!CAUTION] <span style="color:red; font-weight:bold">⚠️ Warning:</span> This model can produce narratives and RP that contain violent and graphic erotic content. Adjust your system prompt accordingly, and use Mistral Tekken chat template.
This merge has zero refusals (confirmed), no ablation needed.
<img src="https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/5ZybvYIHF-URERiO7GbWJ.png" style="float:right; width:300px; height:300px; padding:10px;">This is a merge of pre-trained language models created using mergekit.
This model was merged using the following merge method:
Note: This merge was heavily inspired by Maginum Cydoms
In particular temp 1 and topnsigma 1.25 seems to help a lot with improving quality but sometimes you need to reswipe.
Some models are more sensitive to Rep Pen settings, 1.12 is another, you may need to adjust higher for smaller models (like 1.4 if overcooked) or lower for smarter ones.
Not sure about adaptive_p that is a newer setting added to kobold
(bolded kobold non-defaults)