A brand new series of Models from yours truly, Designed for Intelligence, Creativity and Roleplay - R/Locallama keeps DELETING MY GODDAMN COMMENTS • 25 items • Updated • 10
A finetune of Mistral-7B-V0.3 to test out the Orion-Asstr dataset, This model was completion trained with Orion Asstr using Unsloth. THIS MODEL HAS NOT BEEN TRAINING WITH INSTRUCT DATA, IT IS NOT MEANT FOR CHAT, FOR THAT CHECK OUT OUT THE INSTRUCT TUNED VERSION HERE
System Prompting
I would highly recommend using either Euryale's system prompt or the EVA system prompt with the model.
Unsloth config
Credits
Thank you to Lucy Knada, jeiku, Intervitens, Kalomaze, Kubernetes Bad and the rest of Anthracite
Training
The training was done for 1 epoch. We used 1 x RTX A4000
Safety
Nein.
- Downloads last month
- 5
Safetensors
Model size
7B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support