Training resume from Luminia-13B-v3.
Luminia-v4 Lora only
Luminia-13B-v4-QLora-sft (rank 32) barelly can handle new Luminia-mixture and ExtendedPrompts should give more flexible when ask prompt, e.g.:
### Instruction:
Create stable diffusion prompt based on the given english description.
### Input:
City street, night, raining, drone shot, cyberpunk
### Response:
And so Stage-B DPO: I do NOT recommend use QLora-orpo, poor lora failed to learn more . :<