Delta-Vector/Austral-Xgen-9B-Winton

Austral 9B Winton

Trained by Delta-Vector

Overview

Austral 9B - Winton

Xgen Finetune X Gon Give it to ya jokes included! KTO enhanced Adventure/Roleplay generalist 9B 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 Salesforce/xgen-small-9B-instruct-r to be a generalist Roleplay/Adventure model. I trained the model to be Creative and able to handle whatever scenario the User throws at it, This was a multi-stage finetune, all previous checkpoints are released aswell.

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

Quants

Quants Formats

• GGUFFor use with LLama.cpp & Forks (Coming Soon!)
• EXL3For use with TabbyAPI (Coming soon!)
• EXL2For use with Tabby - (Xoon).

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

As the the Austral/Francois tradition, I did 4 epochs ontop with roughly the same datamix as Francois-Huali/Austral 70B/Winton as a R128 Lora, then KTO alignment with a mix of Instruct/Small writing datasets.

Config(Post-KTO SFT)

https://wandb.ai/new-eden/austral/artifacts/axolotl-config/config-8g8ku59r/v0/files/axolotl_config_shwhocgq.yml

This model was trained over 4 epochs using 8 x A100s for the base SFT, Then i used KTO to clean up some coherency issues for 1 epoch, Total was roughly 50 hours total.

Credits

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