A finetune ontop of the original Francois-PE model that incorporates KTO to increase coherency and prose. The model aims to have short and sweet prose • 3 items • Updated • 1
François-PE-Huali 12B
👁 Model banner
Created by
Delta-Vector
→
Model Information
François-Huali 12B V2
KTO enhanced
Dans-Personality-Engine finetune
Creative & Refreshing Prose
A sequel! A sequel to my Francois-PE/Huali train, Built ontop of Dans-PE-12B that was finetuned with Light novels, Books, Roleplay logs, to change writing style to be rather short & sweet, Huali uses KTO to increase coherency and prose. The model aims to have a different style of writing/prose then any other NeMo train.
Quantized Versions
Available Downloads
- For use with LLama.cpp & Forks(Coming Soon!)
- EXL2 FormatFor use with TabbyAPI (Thanks Auri <3)
Prompting
Model has been tuned with the ChatML formatting. A typical input would look like this:
"""<|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
"""System Prompting
I would highly recommend using either Euryale's system prompt or the EVA system prompt with the model.
Training
The training was done for 1 epoch using 8 x H200s GPUs graciously provided by Kalomaze for the fine-tuning of the model.
Credits
Thank you to Lucy Knada, Ateron, Alicat, Intervitens, Cgato, Kubernetes Bad and the rest of Anthracite.
- Downloads last month
- 47
Safetensors
Model size
12B params
Tensor type
BF16
·
Model tree for Delta-Vector/Francois-PE-V2-Huali-12B
Base model
mistralai/Mistral-Nemo-Base-2407 Finetuned
Delta-Vector/Francois-PE-V2