Delta-Vector/Austral-4.5B-Winton

Austral 4.5B Winton

Trained by Delta-Vector

Overview

Austral 4.5B - Winton

AFM-Based KTO enhanced Adventure/Roleplay generalist 4.5B Sized model

More than 1.5-metres tall, about six-metres long and up to 1000-kilograms heavy, Australovenator Wintonensis was a fast and agile hunter. The largest known Australian theropod.

This is a finetune of arcee-ai/AFM-4.5B to be a generalist Roleplay/Adventure model. This was a multi-stage finetune (SFT->KTO), In testing it has shown to be a great model for Adventure cards & Roleplay, Often pushing the plot forward better then other models, While avoiding some of the slops you'd find in models from Drummer and Co. It also enhanced knowledge of roleplaying domains compared to the base.

Support my finetunes / Me on Kofi: https://Ko-fi.com/deltavector | Thank you to Auri/Joe for helping/Testing ♥

Quants

Quants Formats

• GGUFFor use with LLama.cpp & Forks(Coming soon!)
• EXL3For use with TabbyAPI(Coming soon!)

Chat Format

This model utilizes ChatML.

<|im_start|>user
Hi there!<|im_end|>
<|im_start|>assistant
Nice to meet you!<|im_end|>
<|im_start|>user
Can I ask a question?<|im_end|>
<|im_start|>assistant

Training

This model was trained over 4 epochs using 8 x 3090s for the base SFT, Then i used KTO to clean up some coherency issues for 1 epoch, Total time was roughly 8 hours.

Credits

TYSM to my friends: Auri, Minh, Trappu, Alicat, Kubernetes Bad, Intervitens, NyxKrage & Kalomaze